anil988 commited on
Commit
393f27f
·
1 Parent(s): 096d021

Include agents code without heavy binaries

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. agents/agent_1_transaction_context/__pycache__/agent.cpython-314.pyc +0 -0
  2. agents/agent_1_transaction_context/agent.py +32 -0
  3. agents/agent_1_triage_hitl/.agent/CLI_REFERENCE.md +949 -0
  4. agents/agent_1_triage_hitl/.agent/REQUIRED_STRUCTURE.md +92 -0
  5. agents/agent_1_triage_hitl/.agent/SDK_REFERENCE.md +971 -0
  6. agents/agent_1_triage_hitl/.claude/commands/eval.md +287 -0
  7. agents/agent_1_triage_hitl/.claude/commands/new-agent.md +103 -0
  8. agents/agent_1_triage_hitl/.env +0 -0
  9. agents/agent_1_triage_hitl/.uipath/.telemetry.json +3 -0
  10. agents/agent_1_triage_hitl/.uipath/studio_metadata.json +4 -0
  11. agents/agent_1_triage_hitl/AGENTS.md +21 -0
  12. agents/agent_1_triage_hitl/CLAUDE.md +1 -0
  13. agents/agent_1_triage_hitl/__pycache__/main.cpython-313.pyc +0 -0
  14. agents/agent_1_triage_hitl/__pycache__/main.cpython-314.pyc +0 -0
  15. agents/agent_1_triage_hitl/__uipath/state.db +0 -0
  16. agents/agent_1_triage_hitl/agent.mermaid +8 -0
  17. agents/agent_1_triage_hitl/bindings.json +4 -0
  18. agents/agent_1_triage_hitl/entry-points.json +87 -0
  19. agents/agent_1_triage_hitl/langgraph.json +5 -0
  20. agents/agent_1_triage_hitl/main.mermaid +4 -0
  21. agents/agent_1_triage_hitl/main.py +75 -0
  22. agents/agent_1_triage_hitl/project.uiproj +6 -0
  23. agents/agent_1_triage_hitl/pyproject.toml +12 -0
  24. agents/agent_1_triage_hitl/uipath.json +6 -0
  25. agents/agent_1_triage_hitl/uv.lock +0 -0
  26. agents/agent_2_investigation_api/.agent/CLI_REFERENCE.md +949 -0
  27. agents/agent_2_investigation_api/.agent/REQUIRED_STRUCTURE.md +64 -0
  28. agents/agent_2_investigation_api/.agent/SDK_REFERENCE.md +971 -0
  29. agents/agent_2_investigation_api/.claude/commands/eval.md +287 -0
  30. agents/agent_2_investigation_api/.claude/commands/new-agent.md +103 -0
  31. agents/agent_2_investigation_api/.env +0 -0
  32. agents/agent_2_investigation_api/.uipath/.telemetry.json +3 -0
  33. agents/agent_2_investigation_api/.uipath/studio_metadata.json +4 -0
  34. agents/agent_2_investigation_api/AGENTS.md +21 -0
  35. agents/agent_2_investigation_api/__pycache__/main.cpython-313.pyc +0 -0
  36. agents/agent_2_investigation_api/agent_2_investigation_api.mermaid +4 -0
  37. agents/agent_2_investigation_api/bindings.json +4 -0
  38. agents/agent_2_investigation_api/entry-points.json +30 -0
  39. agents/agent_2_investigation_api/main.py +61 -0
  40. agents/agent_2_investigation_api/project.uiproj +6 -0
  41. agents/agent_2_investigation_api/pyproject.toml +15 -0
  42. agents/agent_2_investigation_api/uipath.json +8 -0
  43. agents/agent_2_sanctions_screener/.agent/CLI_REFERENCE.md +949 -0
  44. agents/agent_2_sanctions_screener/.agent/REQUIRED_STRUCTURE.md +64 -0
  45. agents/agent_2_sanctions_screener/.agent/SDK_REFERENCE.md +971 -0
  46. agents/agent_2_sanctions_screener/.claude/commands/eval.md +287 -0
  47. agents/agent_2_sanctions_screener/.claude/commands/new-agent.md +103 -0
  48. agents/agent_2_sanctions_screener/.env +0 -0
  49. agents/agent_2_sanctions_screener/.uipath/.telemetry.json +3 -0
  50. agents/agent_2_sanctions_screener/.uipath/studio_metadata.json +4 -0
agents/agent_1_transaction_context/__pycache__/agent.cpython-314.pyc ADDED
Binary file (2.06 kB). View file
 
agents/agent_1_transaction_context/agent.py ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import datetime
2
+
3
+ class ContextEnrichmentAgent:
4
+ @staticmethod
5
+ def run(case_data: dict) -> dict:
6
+ """
7
+ Agent 1: Context Enrichment
8
+ Simulates fetching 90-day transaction history and KYC records from a Core Banking System.
9
+ """
10
+ print("[AGENT 1] Starting Context Enrichment...")
11
+
12
+ # Simulate KYC lookup
13
+ kyc_data = {
14
+ "account_age_days": 450,
15
+ "kyc_status": "VERIFIED",
16
+ "risk_rating": "HIGH",
17
+ "business_type": "Import/Export",
18
+ "expected_monthly_volume": 500000
19
+ }
20
+
21
+ # Simulate 90-day history volume calculation
22
+ historical_volume = sum(txn.get('amount', 0) for txn in case_data.get('transactions', [])) * 1.5
23
+
24
+ enriched_data = case_data.copy()
25
+ enriched_data['context'] = {
26
+ "kyc": kyc_data,
27
+ "90_day_historical_volume": historical_volume,
28
+ "timestamp": datetime.datetime.now().isoformat()
29
+ }
30
+
31
+ print("[AGENT 1] Enrichment Complete.")
32
+ return enriched_data
agents/agent_1_triage_hitl/.agent/CLI_REFERENCE.md ADDED
@@ -0,0 +1,949 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## CLI Commands Reference
2
+
3
+ The UiPath Python SDK provides a comprehensive CLI for managing coded agents and automation projects. All commands should be executed with `uv run uipath <command>`.
4
+
5
+ ### Command Overview
6
+
7
+ | Command | Purpose | When to Use |
8
+ |---------|---------|-------------|
9
+ | `init` | Initialize agent project | Creating a new agent or updating schema |
10
+ | `run` | Execute agent | Running agent locally or testing |
11
+ | `eval` | Evaluate agent | Testing agent performance with evaluation sets |
12
+
13
+ ---
14
+
15
+ ### `uipath init`
16
+
17
+ **Description:** Initialize the project.
18
+
19
+ **Options:**
20
+
21
+ | Option | Type | Default | Description |
22
+ |--------|------|---------|-------------|
23
+ | `--no-agents-md-override` | flag | false | Won't override existing .agent files and AGENTS.md file. |
24
+
25
+ **Usage Examples:**
26
+
27
+ ```bash
28
+ # Initialize a new agent project
29
+ uv run uipath init
30
+
31
+ # Initialize with specific entrypoint
32
+ uv run uipath init main.py
33
+
34
+ # Initialize and infer bindings from code
35
+ uv run uipath init --infer-bindings
36
+ ```
37
+
38
+ **When to use:** Run this command when you've modified the Input/Output models and need to regenerate the `uipath.json` schema file.
39
+
40
+ ---
41
+
42
+ ### `uipath run`
43
+
44
+ **Description:** Execute the project.
45
+
46
+ **Arguments:**
47
+
48
+ | Argument | Required | Description |
49
+ |----------|----------|-------------|
50
+ | `entrypoint` | No | N/A |
51
+ | `input` | No | N/A |
52
+
53
+ **Options:**
54
+
55
+ | Option | Type | Default | Description |
56
+ |--------|------|---------|-------------|
57
+ | `--resume` | flag | false | Resume execution from a previous state |
58
+ | `-f`, `--file` | value | `Sentinel.UNSET` | File path for the .json input |
59
+ | `--input-file` | value | `Sentinel.UNSET` | Alias for '-f/--file' arguments |
60
+ | `--output-file` | value | `Sentinel.UNSET` | File path where the output will be written |
61
+ | `--trace-file` | value | `Sentinel.UNSET` | File path where the trace spans will be written (JSON Lines format) |
62
+ | `--state-file` | value | `Sentinel.UNSET` | File path where the state file is stored for persisting execution state. If not provided, a temporary file will be used. |
63
+ | `--debug` | flag | false | Enable debugging with debugpy. The process will wait for a debugger to attach. |
64
+ | `--debug-port` | value | `5678` | Port for the debug server (default: 5678) |
65
+ | `--keep-state-file` | flag | false | Keep the temporary state file even when not resuming and no job id is provided |
66
+ | `--simulation` | value | none | Simulation config as a JSON object (same schema as simulation.json) |
67
+
68
+ **Usage Examples:**
69
+
70
+ ```bash
71
+ # Run agent with inline JSON input
72
+ uv run uipath run main.py '{"query": "What is the weather?"}'
73
+
74
+ # Run agent with input from file
75
+ uv run uipath run main.py --file input.json
76
+
77
+ # Run agent and save output to file
78
+ uv run uipath run agent '{"task": "Process data"}' --output-file result.json
79
+
80
+ # Run agent with debugging enabled
81
+ uv run uipath run main.py '{"input": "test"}' --debug --debug-port 5678
82
+
83
+ # Resume agent execution from previous state
84
+ uv run uipath run --resume
85
+ ```
86
+
87
+ **When to use:** Run this command to execute your agent locally for development, testing, or debugging. Use `--debug` flag to attach a debugger for step-by-step debugging.
88
+
89
+ ---
90
+
91
+ ### `uipath eval`
92
+
93
+ **Description:** Run an evaluation set against the agent.
94
+
95
+ Args:
96
+ entrypoint: Path to the agent script to evaluate (optional, will auto-discover if not specified)
97
+ eval_set: Path to the evaluation set JSON file (optional, will auto-discover if not specified)
98
+ eval_ids: Optional list of evaluation IDs
99
+ eval_set_run_id: Custom evaluation set run ID (optional, will generate UUID if not specified)
100
+ workers: Number of parallel workers for running evaluations
101
+ no_report: Do not report the evaluation results
102
+ enable_mocker_cache: Enable caching for LLM mocker responses
103
+ report_coverage: Report evaluation coverage
104
+ model_settings_id: Model settings ID to override agent settings
105
+ trace_file: File path where traces will be written in JSONL format
106
+ max_llm_concurrency: Maximum concurrent LLM requests
107
+ input_overrides: Input field overrides mapping (direct field override with deep merge)
108
+ resume: Resume execution from a previous suspended state
109
+
110
+
111
+ **Arguments:**
112
+
113
+ | Argument | Required | Description |
114
+ |----------|----------|-------------|
115
+ | `entrypoint` | No | N/A |
116
+ | `eval_set` | No | N/A |
117
+
118
+ **Options:**
119
+
120
+ | Option | Type | Default | Description |
121
+ |--------|------|---------|-------------|
122
+ | `--eval-set-run-id` | value | `Sentinel.UNSET` | Custom evaluation set run ID (if not provided, a UUID will be generated) |
123
+ | `--no-report` | flag | false | Do not report the evaluation results |
124
+ | `--workers` | value | `1` | Number of parallel workers for running evaluations (default: 1) |
125
+ | `--output-file` | value | `Sentinel.UNSET` | File path where the output will be written |
126
+ | `--enable-mocker-cache` | flag | false | Enable caching for LLM mocker responses |
127
+ | `--report-coverage` | flag | false | Report evaluation coverage |
128
+ | `--model-settings-id` | value | `"default"` | Model settings ID from evaluation set to override agent settings (default: 'default') |
129
+ | `--trace-file` | value | `Sentinel.UNSET` | File path where traces will be written in JSONL format |
130
+ | `--max-llm-concurrency` | value | `20` | Maximum concurrent LLM requests (default: 20) |
131
+ | `--resume` | flag | false | Resume execution from a previous suspended state |
132
+ | `--verbose` | flag | false | Include agent execution output (trace, result) in the output file |
133
+
134
+ **Usage Examples:**
135
+
136
+ ```bash
137
+ # Run evaluation with auto-discovered files
138
+ uv run uipath eval
139
+
140
+ # Run evaluation with specific entrypoint and eval set
141
+ uv run uipath eval main.py eval_set.json
142
+
143
+ # Run evaluation without reporting results
144
+ uv run uipath eval --no-report
145
+
146
+ # Run evaluation with custom number of workers
147
+ uv run uipath eval --workers 4
148
+
149
+ # Save evaluation output to file
150
+ uv run uipath eval --output-file eval_results.json
151
+ ```
152
+
153
+ **When to use:** Run this command to test your agent's performance against a predefined evaluation set. This helps validate agent behavior and measure quality metrics.
154
+
155
+ ---
156
+
157
+ ### Common Workflows
158
+
159
+ **1. Creating a New Agent:**
160
+ ```bash
161
+ # Step 1: Initialize project
162
+ uv run uipath init
163
+
164
+ # Step 2: Run agent to test
165
+ uv run uipath run main.py '{"input": "test"}'
166
+
167
+ # Step 3: Evaluate agent performance
168
+ uv run uipath eval
169
+ ```
170
+
171
+ **2. Development & Testing:**
172
+ ```bash
173
+ # Run with debugging
174
+ uv run uipath run main.py '{"input": "test"}' --debug
175
+
176
+ # Test with input file
177
+ uv run uipath run main.py --file test_input.json --output-file test_output.json
178
+ ```
179
+
180
+ **3. Schema Updates:**
181
+ ```bash
182
+ # After modifying Input/Output models, regenerate schema
183
+ uv run uipath init --infer-bindings
184
+ ```
185
+
186
+ ### Configuration File (uipath.json)
187
+
188
+ The `uipath.json` file is automatically generated by `uipath init` and defines your agent's schema and bindings.
189
+
190
+ **Structure:**
191
+
192
+ ```json
193
+ {
194
+ "entryPoints": [
195
+ {
196
+ "filePath": "agent",
197
+ "uniqueId": "uuid-here",
198
+ "type": "agent",
199
+ "input": {
200
+ "type": "object",
201
+ "properties": { ... },
202
+ "description": "Input schema",
203
+ "required": [ ... ]
204
+ },
205
+ "output": {
206
+ "type": "object",
207
+ "properties": { ... },
208
+ "description": "Output schema",
209
+ "required": [ ... ]
210
+ }
211
+ }
212
+ ],
213
+ "bindings": {
214
+ "version": "2.0",
215
+ "resources": []
216
+ }
217
+ }
218
+ ```
219
+
220
+ **When to Update:**
221
+
222
+ 1. **After Modifying Input/Output Models**: Run `uv run uipath init --infer-bindings` to regenerate schemas
223
+ 2. **Changing Entry Point**: Update `filePath` if you rename or move your main file
224
+ 3. **Manual Schema Adjustments**: Edit `input.jsonSchema` or `output.jsonSchema` directly if needed
225
+ 4. **Bindings Updates**: The `bindings` section maps the exported graph variable - update if you rename your graph
226
+
227
+ **Important Notes:**
228
+
229
+ - The `uniqueId` should remain constant for the same agent
230
+ - Always use `type: "agent"` for LangGraph agents
231
+ - The `jsonSchema` must match your Pydantic models exactly
232
+ - Re-run `uipath init --infer-bindings` instead of manual edits when possible
233
+
234
+
235
+ ## Service Commands Reference
236
+
237
+ The UiPath CLI provides commands for interacting with UiPath platform services. These commands allow you to manage buckets, assets, jobs, and other resources.
238
+
239
+ ### `uipath assets`
240
+
241
+ Manage UiPath assets.
242
+
243
+ Assets are key-value pairs that store configuration data, credentials,
244
+ and settings used by automation processes.
245
+
246
+ \b
247
+ Examples:
248
+ # List all assets in a folder
249
+ uipath assets list --folder-path "Shared"
250
+
251
+ # List with filter
252
+ uipath assets list --filter "ValueType eq 'Text'"
253
+
254
+ # List with ordering
255
+ uipath assets list --orderby "Name asc"
256
+
257
+
258
+ **Subcommands:**
259
+
260
+ **`uipath assets list`**
261
+
262
+ List assets in a folder.
263
+
264
+ \b
265
+ Examples:
266
+ uipath assets list
267
+ uipath assets list --folder-path "Shared"
268
+ uipath assets list --filter "ValueType eq 'Text'"
269
+ uipath assets list --filter "Name eq 'MyAsset'"
270
+ uipath assets list --orderby "Name asc"
271
+ uipath assets list --top 50 --skip 100
272
+
273
+
274
+ Options:
275
+ - `--filter`: OData $filter expression (default: `Sentinel.UNSET`)
276
+ - `--orderby`: OData $orderby expression (default: `Sentinel.UNSET`)
277
+ - `--top`: Maximum number of items to return (default: 100, max: 1000) (default: `100`)
278
+ - `--skip`: Number of items to skip (default: `0`)
279
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
280
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
281
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
282
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
283
+
284
+ ---
285
+
286
+ ### `uipath buckets`
287
+
288
+ Manage UiPath storage buckets and files.
289
+
290
+ Buckets are cloud storage containers for files used by automation processes.
291
+
292
+ 
293
+ Bucket Operations:
294
+ list - List all buckets
295
+ create - Create a new bucket
296
+ delete - Delete a bucket
297
+ retrieve - Get bucket details
298
+ exists - Check if bucket exists
299
+
300
+ 
301
+ File Operations (use 'buckets files' subcommand):
302
+ files list - List files in a bucket
303
+ files search - Search files using glob patterns
304
+ files upload - Upload a file to a bucket
305
+ files download - Download a file from a bucket
306
+ files delete - Delete a file from a bucket
307
+ files exists - Check if a file exists
308
+
309
+ 
310
+ Examples:
311
+ 
312
+ # Bucket operations with explicit folder
313
+ uipath buckets list --folder-path "Shared"
314
+ uipath buckets create my-bucket --description "Data storage"
315
+ uipath buckets exists my-bucket
316
+ uipath buckets delete my-bucket --confirm
317
+ 
318
+ # Using environment variable for folder context
319
+ export UIPATH_FOLDER_PATH="Shared"
320
+ uipath buckets list
321
+ uipath buckets create my-bucket --description "Data storage"
322
+ 
323
+ # File operations
324
+ uipath buckets files list my-bucket
325
+ uipath buckets files search my-bucket "*.pdf"
326
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
327
+ uipath buckets files download my-bucket data.csv ./local.csv
328
+ uipath buckets files delete my-bucket old-data.csv --confirm
329
+ uipath buckets files exists my-bucket data.csv
330
+
331
+
332
+ **Subcommands:**
333
+
334
+ **`uipath buckets create`**
335
+
336
+ Create a new Bucket.
337
+
338
+ Examples:
339
+ uipath buckets create my-resource
340
+ uipath buckets create my-resource --folder-path Shared
341
+
342
+
343
+ Arguments:
344
+ - `name` (required): N/A
345
+
346
+ Options:
347
+ - `--description`: Bucket description
348
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
349
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
350
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
351
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
352
+
353
+ **`uipath buckets delete`**
354
+
355
+ Delete a bucket.
356
+
357
+ 
358
+ Examples:
359
+ uipath buckets delete my-bucket --confirm
360
+ uipath buckets delete my-bucket --dry-run
361
+
362
+
363
+ Arguments:
364
+ - `name` (required): N/A
365
+
366
+ Options:
367
+ - `--confirm`: Skip confirmation prompt
368
+ - `--dry-run`: Show what would be deleted without deleting
369
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
370
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
371
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
372
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
373
+
374
+ **`uipath buckets exists`**
375
+
376
+ Check if a Bucket exists.
377
+
378
+ Examples:
379
+ uipath buckets exists my-resource
380
+ uipath buckets exists my-resource --folder-path Shared
381
+
382
+
383
+ Arguments:
384
+ - `name` (required): N/A
385
+
386
+ Options:
387
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
388
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
389
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
390
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
391
+
392
+ #### `uipath buckets files`
393
+
394
+ Manage files within buckets.
395
+
396
+ 
397
+ Examples:
398
+ 
399
+ # List files in a bucket
400
+ uipath buckets files list my-bucket
401
+ 
402
+ # Search for files with glob pattern
403
+ uipath buckets files search my-bucket "*.pdf"
404
+ 
405
+ # Upload a file
406
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
407
+ 
408
+ # Download a file
409
+ uipath buckets files download my-bucket data.csv ./local.csv
410
+ 
411
+ # Delete a file
412
+ uipath buckets files delete my-bucket old-data.csv --confirm
413
+ 
414
+ # Check if file exists
415
+ uipath buckets files exists my-bucket data.csv
416
+
417
+
418
+ **`uipath buckets files delete`**
419
+
420
+ Delete a file from a bucket.
421
+
422
+ 
423
+ Arguments:
424
+ BUCKET_NAME: Name of the bucket
425
+ FILE_PATH: Path to file in bucket
426
+
427
+ 
428
+ Examples:
429
+ uipath buckets files delete my-bucket old-data.csv --confirm
430
+ uipath buckets files delete reports archive/old.pdf --dry-run
431
+
432
+
433
+ Arguments:
434
+ - `bucket_name` (required): N/A
435
+ - `file_path` (required): N/A
436
+
437
+ Options:
438
+ - `--confirm`: Skip confirmation prompt
439
+ - `--dry-run`: Show what would be deleted
440
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
441
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
442
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
443
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
444
+
445
+ **`uipath buckets files download`**
446
+
447
+ Download a file from a bucket.
448
+
449
+ 
450
+ Arguments:
451
+ BUCKET_NAME: Name of the bucket
452
+ REMOTE_PATH: Path to file in bucket
453
+ LOCAL_PATH: Local destination path
454
+
455
+ 
456
+ Examples:
457
+ uipath buckets files download my-bucket data.csv ./downloads/data.csv
458
+ uipath buckets files download reports monthly/report.pdf ./report.pdf
459
+
460
+
461
+ Arguments:
462
+ - `bucket_name` (required): N/A
463
+ - `remote_path` (required): N/A
464
+ - `local_path` (required): N/A
465
+
466
+ Options:
467
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
468
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
469
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
470
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
471
+
472
+ **`uipath buckets files exists`**
473
+
474
+ Check if a file exists in a bucket.
475
+
476
+ 
477
+ Arguments:
478
+ BUCKET_NAME: Name of the bucket
479
+ FILE_PATH: Path to file in bucket
480
+
481
+ 
482
+ Examples:
483
+ uipath buckets files exists my-bucket data.csv
484
+ uipath buckets files exists reports monthly/report.pdf
485
+
486
+
487
+ Arguments:
488
+ - `bucket_name` (required): N/A
489
+ - `file_path` (required): N/A
490
+
491
+ Options:
492
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
493
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
494
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
495
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
496
+
497
+ **`uipath buckets files list`**
498
+
499
+ List files in a bucket.
500
+
501
+ 
502
+ Arguments:
503
+ BUCKET_NAME: Name of the bucket
504
+
505
+ 
506
+ Examples:
507
+ uipath buckets files list my-bucket
508
+ uipath buckets files list my-bucket --prefix "data/"
509
+ uipath buckets files list reports --limit 10 --format json
510
+ uipath buckets files list my-bucket --all
511
+
512
+
513
+ Arguments:
514
+ - `bucket_name` (required): N/A
515
+
516
+ Options:
517
+ - `--prefix`: Filter files by prefix (default: ``)
518
+ - `--limit`: Maximum number of files to return (default: `Sentinel.UNSET`)
519
+ - `--offset`: Number of files to skip (default: `0`)
520
+ - `--all`: Fetch all files (auto-paginate)
521
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
522
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
523
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
524
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
525
+
526
+ **`uipath buckets files search`**
527
+
528
+ Search for files using glob patterns.
529
+
530
+ Uses the GetFiles API which supports glob patterns like *.pdf or data_*.csv.
531
+
532
+ 
533
+ Arguments:
534
+ BUCKET_NAME: Name of the bucket
535
+ PATTERN: Glob pattern to match files (e.g., "*.pdf", "data_*.csv")
536
+
537
+ 
538
+ Examples:
539
+ uipath buckets files search my-bucket "*.pdf"
540
+ uipath buckets files search reports "*.csv" --recursive
541
+ uipath buckets files search my-bucket "data_*.json" --prefix "archive/"
542
+
543
+
544
+ Arguments:
545
+ - `bucket_name` (required): N/A
546
+ - `pattern` (required): N/A
547
+
548
+ Options:
549
+ - `--prefix`: Directory path to search in (default: ``)
550
+ - `--recursive`: Search subdirectories recursively
551
+ - `--limit`: Maximum number of files to return (default: `Sentinel.UNSET`)
552
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
553
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
554
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
555
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
556
+
557
+ **`uipath buckets files upload`**
558
+
559
+ Upload a file to a bucket.
560
+
561
+ 
562
+ Arguments:
563
+ BUCKET_NAME: Name of the bucket
564
+ LOCAL_PATH: Local file to upload
565
+ REMOTE_PATH: Destination path in bucket
566
+
567
+ 
568
+ Examples:
569
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
570
+ uipath buckets files upload reports ./report.pdf monthly/report.pdf
571
+
572
+
573
+ Arguments:
574
+ - `bucket_name` (required): N/A
575
+ - `local_path` (required): N/A
576
+ - `remote_path` (required): N/A
577
+
578
+ Options:
579
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
580
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
581
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
582
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
583
+
584
+ **`uipath buckets list`**
585
+
586
+ List all Buckets.
587
+
588
+ Examples:
589
+ uipath buckets list
590
+ uipath buckets list --folder-path Shared
591
+
592
+
593
+ Options:
594
+ - `--limit`: Maximum number of items to return (default: `Sentinel.UNSET`)
595
+ - `--offset`: Number of items to skip (default: `0`)
596
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
597
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
598
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
599
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
600
+
601
+ **`uipath buckets retrieve`**
602
+
603
+ Retrieve a bucket by name or key.
604
+
605
+ 
606
+ Examples:
607
+ uipath buckets retrieve --name "my-bucket"
608
+ uipath buckets retrieve --key "abc-123-def-456" --format json
609
+
610
+
611
+ Options:
612
+ - `--name`: Bucket name (default: `Sentinel.UNSET`)
613
+ - `--key`: Bucket key (UUID) (default: `Sentinel.UNSET`)
614
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
615
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
616
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
617
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
618
+
619
+ ---
620
+
621
+ ### `uipath context-grounding`
622
+
623
+ Manage UiPath Context Grounding indexes.
624
+
625
+ Context Grounding indexes store and search contextual information
626
+ used to enhance AI-enabled automation processes.
627
+
628
+ 
629
+ Two index types:
630
+ Regular - Persistent, backed by bucket or connection, created via 'create'
631
+ Ephemeral - Temporary, no Orchestrator folder, created from local files via 'create-ephemeral'
632
+
633
+ 
634
+ Examples:
635
+ uipath context-grounding list --folder-path "Shared"
636
+
637
+
638
+ **Subcommands:**
639
+
640
+ #### `uipath context-grounding batch-transform`
641
+
642
+ Manage Batch Transform tasks.
643
+
644
+ Batch Transform processes and transforms CSV files from context
645
+ grounding indexes.
646
+
647
+ 
648
+ Examples:
649
+ uipath context-grounding batch-transform start --help
650
+
651
+
652
+ **`uipath context-grounding batch-transform download`**
653
+
654
+ Download a Batch Transform result file.
655
+
656
+ 
657
+ Examples:
658
+ uipath context-grounding batch-transform download --task-id abc-123 --output-file result.csv
659
+
660
+
661
+ Options:
662
+ - `--task-id`: ID of the Batch Transform task (default: `Sentinel.UNSET`)
663
+ - `--output-file`: Local destination path for the result file (default: `Sentinel.UNSET`)
664
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
665
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
666
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
667
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
668
+
669
+ **`uipath context-grounding batch-transform retrieve`**
670
+
671
+ Retrieve a Batch Transform task status.
672
+
673
+ 
674
+ Examples:
675
+ uipath context-grounding batch-transform retrieve --task-id abc-123-def-456
676
+
677
+
678
+ Options:
679
+ - `--task-id`: ID of the Batch Transform task (default: `Sentinel.UNSET`)
680
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
681
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
682
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
683
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
684
+
685
+ **`uipath context-grounding batch-transform start`**
686
+
687
+ Start a Batch Transform task on an index.
688
+
689
+ The index must contain CSV files. Only one file is processed per task.
690
+
691
+ 
692
+ Two ways to specify the index:
693
+ Regular index: --index-name + --folder-path
694
+ Ephemeral index: --index-id
695
+
696
+ 
697
+ --columns-file is a JSON array defining output columns:
698
+ [
699
+ {"name": "entity", "description": "Extracted entity name"},
700
+ {"name": "category", "description": "Entity category"}
701
+ ]
702
+
703
+ 
704
+ Examples:
705
+ uipath context-grounding batch-transform start --index-name my-index --task-name my-task --prompt "Extract" --columns-file cols.json
706
+ uipath context-grounding batch-transform start --index-id abc-123 --task-name my-task --prompt "Extract" --columns-file cols.json
707
+
708
+
709
+ Options:
710
+ - `--index-name`: Name of the context grounding index (default: `Sentinel.UNSET`)
711
+ - `--index-id`: ID of the context grounding index (ephemeral indexes only) (default: `Sentinel.UNSET`)
712
+ - `--task-name`: Name for the Batch Transform task (default: `Sentinel.UNSET`)
713
+ - `--prompt`: Task prompt describing what to process (default: `Sentinel.UNSET`)
714
+ - `--columns-file`: JSON file defining output columns (see format above) (default: `Sentinel.UNSET`)
715
+ - `--target-file`: Specific file name to target in the index (default: `Sentinel.UNSET`)
716
+ - `--prefix`: Storage bucket folder path prefix for filtering files (default: `Sentinel.UNSET`)
717
+ - `--web-search`: Enable web search grounding
718
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
719
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
720
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
721
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
722
+
723
+ **`uipath context-grounding create`**
724
+
725
+ Create a new context grounding index (persistent).
726
+
727
+ The created index lives in an Orchestrator folder. Ingestion must be
728
+ triggered separately after creation.
729
+
730
+ 
731
+ Two ways to specify the data source:
732
+ --bucket-source Bucket name for bucket-backed indexes
733
+ --source-file JSON file for connections (use 'source-schema' to see formats)
734
+
735
+ 
736
+ Examples:
737
+ uipath context-grounding create --index-name my-index --bucket-source my-bucket
738
+ uipath context-grounding create --index-name my-index --source-file config.json
739
+
740
+
741
+ Options:
742
+ - `--index-name`: Name of the index to create (default: `Sentinel.UNSET`)
743
+ - `--source-file`: JSON file with connection source configuration (Google Drive, OneDrive, Dropbox, Confluence) (default: `Sentinel.UNSET`)
744
+ - `--bucket-source`: Bucket name for bucket-backed indexes (default: `Sentinel.UNSET`)
745
+ - `--description`: Description of the index (default: ``)
746
+ - `--extraction-strategy`: Extraction strategy (default: LLMV4) (default: `LLMV4`)
747
+ - `--file-type`: File type filter (e.g., 'pdf', 'txt') (default: `Sentinel.UNSET`)
748
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
749
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
750
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
751
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
752
+
753
+ **`uipath context-grounding create-ephemeral`**
754
+
755
+ Create an ephemeral index from local files (temporary).
756
+
757
+ Uploads files as attachments and creates a temporary index. Reference it
758
+ in other commands with --index-id (no folder, no name). Ingestion starts
759
+ automatically. Poll with 'retrieve --index-id <id>' until
760
+ lastIngestionStatus is Successful before starting a task.
761
+
762
+ 
763
+ Supported file types:
764
+ DeepRAG: PDF, TXT
765
+ BatchRAG: CSV
766
+
767
+ 
768
+ Examples:
769
+ uipath context-grounding create-ephemeral --usage DeepRAG --files doc1.pdf --files doc2.pdf
770
+ uipath context-grounding create-ephemeral --usage BatchRAG --files data.csv
771
+
772
+
773
+ Options:
774
+ - `--usage`: Task type for the ephemeral index (default: `Sentinel.UNSET`)
775
+ - `--files`: Local file paths to upload as attachments (repeatable) (default: `Sentinel.UNSET`)
776
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
777
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
778
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
779
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
780
+
781
+ #### `uipath context-grounding deep-rag`
782
+
783
+ Manage Deep RAG tasks.
784
+
785
+ Deep RAG performs multi-document research and synthesis on context
786
+ grounding indexes.
787
+
788
+ 
789
+ Examples:
790
+ uipath context-grounding deep-rag start --help
791
+
792
+
793
+ **`uipath context-grounding deep-rag retrieve`**
794
+
795
+ Retrieve a Deep RAG task result (status, summary, citations).
796
+
797
+ 
798
+ Examples:
799
+ uipath context-grounding deep-rag retrieve --task-id abc-123-def-456
800
+
801
+
802
+ Options:
803
+ - `--task-id`: ID of the Deep RAG task (default: `Sentinel.UNSET`)
804
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
805
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
806
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
807
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
808
+
809
+ **`uipath context-grounding deep-rag start`**
810
+
811
+ Start a Deep RAG task on an index.
812
+
813
+ 
814
+ Two ways to specify the index:
815
+ Regular index: --index-name + --folder-path
816
+ Ephemeral index: --index-id
817
+
818
+ 
819
+ Examples:
820
+ uipath context-grounding deep-rag start --index-name my-index --folder-path Shared --task-name my-task --prompt "Summarize"
821
+ uipath context-grounding deep-rag start --index-id abc-123 --task-name my-task --prompt "Summarize"
822
+
823
+
824
+ Options:
825
+ - `--index-name`: Name of the context grounding index (default: `Sentinel.UNSET`)
826
+ - `--index-id`: ID of the context grounding index (ephemeral indexes only) (default: `Sentinel.UNSET`)
827
+ - `--task-name`: Name for the Deep RAG task (default: `Sentinel.UNSET`)
828
+ - `--prompt`: Task prompt describing what to research (default: `Sentinel.UNSET`)
829
+ - `--glob-pattern`: Glob pattern to filter files in the index (default: **) (default: `**`)
830
+ - `--citation-mode`: Citation mode (default: Skip) (default: `Skip`)
831
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
832
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
833
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
834
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
835
+
836
+ **`uipath context-grounding delete`**
837
+
838
+ Delete a context grounding index.
839
+
840
+ 
841
+ Examples:
842
+ uipath context-grounding delete --index-name my-index --confirm
843
+ uipath context-grounding delete --index-name my-index --dry-run
844
+
845
+
846
+ Options:
847
+ - `--index-name`: Name of the index to delete (default: `Sentinel.UNSET`)
848
+ - `--confirm`: Skip confirmation prompt
849
+ - `--dry-run`: Show what would be deleted without deleting
850
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
851
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
852
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
853
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
854
+
855
+ **`uipath context-grounding ingest`**
856
+
857
+ Trigger ingestion on a context grounding index.
858
+
859
+ Ingestion runs asynchronously. Use 'retrieve' to poll lastIngestionStatus
860
+ until it reaches Successful or Failed.
861
+
862
+ 
863
+ Examples:
864
+ uipath context-grounding ingest --index-name my-index --folder-path "Shared"
865
+
866
+
867
+ Options:
868
+ - `--index-name`: Name of the index to ingest (default: `Sentinel.UNSET`)
869
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
870
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
871
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
872
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
873
+
874
+ **`uipath context-grounding list`**
875
+
876
+ List all context grounding indexes.
877
+
878
+ 
879
+ Examples:
880
+ uipath context-grounding list --folder-path "Shared"
881
+
882
+
883
+ Options:
884
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
885
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
886
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
887
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
888
+
889
+ **`uipath context-grounding retrieve`**
890
+
891
+ Retrieve a context grounding index.
892
+
893
+ 
894
+ Two ways to specify the index:
895
+ Regular index: --index-name + --folder-path
896
+ Ephemeral index: --index-id
897
+
898
+ 
899
+ Examples:
900
+ uipath context-grounding retrieve --index-name my-index --folder-path "Shared"
901
+ uipath context-grounding retrieve --index-id abc-123-def-456 --format json
902
+
903
+
904
+ Options:
905
+ - `--index-name`: Name of the index to retrieve (default: `Sentinel.UNSET`)
906
+ - `--index-id`: ID of the index to retrieve (ephemeral indexes only) (default: `Sentinel.UNSET`)
907
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
908
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
909
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
910
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
911
+
912
+ **`uipath context-grounding search`**
913
+
914
+ Search a context grounding index (regular indexes only).
915
+
916
+ 
917
+ Examples:
918
+ uipath context-grounding search --index-name my-index --query "What is the revenue?"
919
+ uipath context-grounding search --index-name my-index --query "results" --limit 5
920
+
921
+
922
+ Options:
923
+ - `--index-name`: Name of the index to search (default: `Sentinel.UNSET`)
924
+ - `--query`: Search query in natural language (default: `Sentinel.UNSET`)
925
+ - `--limit`: Maximum number of results (default: 10) (default: `10`)
926
+ - `--threshold`: Minimum similarity threshold (default: 0.0) (default: `0.0`)
927
+ - `--search-mode`: Search mode (default: Semantic) (default: `Semantic`)
928
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
929
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
930
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
931
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
932
+
933
+ **`uipath context-grounding source-schema`**
934
+
935
+ Show JSON source file formats for connection-backed indexes.
936
+
937
+ Use this to see the required fields for --source-file when creating
938
+ an index backed by Google Drive, OneDrive, Dropbox, or Confluence.
939
+
940
+ 
941
+ Examples:
942
+ uipath context-grounding source-schema --type google_drive
943
+
944
+
945
+ Options:
946
+ - `--type`: Show schema for a specific source type (omit to show all) (default: `Sentinel.UNSET`)
947
+
948
+ ---
949
+
agents/agent_1_triage_hitl/.agent/REQUIRED_STRUCTURE.md ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Required Agent Structure
2
+
3
+ **IMPORTANT**: All UiPath coded agents MUST follow this standard structure unless explicitly specified otherwise by the user.
4
+
5
+ ### Required Components
6
+
7
+ Every agent implementation MUST include these three Pydantic models:
8
+
9
+ ```python
10
+ from pydantic import BaseModel
11
+
12
+ class Input(BaseModel):
13
+ """Define input fields that the agent accepts"""
14
+ # Add your input fields here
15
+ pass
16
+
17
+ class State(BaseModel):
18
+ """Define the agent's internal state that flows between nodes"""
19
+ # Add your state fields here
20
+ pass
21
+
22
+ class Output(BaseModel):
23
+ """Define output fields that the agent returns"""
24
+ # Add your output fields here
25
+ pass
26
+ ```
27
+
28
+ ### Required LLM Initialization
29
+
30
+ Unless the user explicitly requests a different LLM provider, always use `UiPathChat`:
31
+
32
+ ```python
33
+ from uipath_langchain.chat import UiPathChat
34
+
35
+ llm = UiPathChat(model="gpt-4.1-mini-2025-04-14", temperature=0.7)
36
+ ```
37
+
38
+ **Alternative LLMs** (only use if explicitly requested):
39
+ - `ChatOpenAI` from `langchain_openai`
40
+ - `ChatAnthropic` from `langchain_anthropic`
41
+ - Other LangChain-compatible LLMs
42
+
43
+ ### Standard Agent Template
44
+
45
+ Every agent should follow this basic structure:
46
+
47
+ ```python
48
+ from langchain_core.messages import SystemMessage, HumanMessage
49
+ from langgraph.graph import START, StateGraph, END
50
+ from uipath_langchain.chat import UiPathChat
51
+ from pydantic import BaseModel
52
+
53
+ # 1. Define Input, State, and Output models
54
+ class Input(BaseModel):
55
+ field: str
56
+
57
+ class State(BaseModel):
58
+ field: str
59
+ result: str = ""
60
+
61
+ class Output(BaseModel):
62
+ result: str
63
+
64
+ # 2. Initialize UiPathChat LLM
65
+ llm = UiPathChat(model="gpt-4.1-mini-2025-04-14", temperature=0.7)
66
+
67
+ # 3. Define agent nodes (async functions)
68
+ async def process_node(state: State) -> State:
69
+ response = await llm.ainvoke([HumanMessage(state.field)])
70
+ return State(field=state.field, result=response.content)
71
+
72
+ async def output_node(state: State) -> Output:
73
+ return Output(result=state.result)
74
+
75
+ # 4. Build the graph
76
+ builder = StateGraph(State, input=Input, output=Output)
77
+ builder.add_node("process", process_node)
78
+ builder.add_node("output", output_node)
79
+ builder.add_edge(START, "process")
80
+ builder.add_edge("process", "output")
81
+ builder.add_edge("output", END)
82
+
83
+ # 5. Compile the graph
84
+ graph = builder.compile()
85
+ ```
86
+
87
+ **Key Rules**:
88
+ 1. Always use async/await for all node functions
89
+ 2. All nodes (except output) must accept and return `State`
90
+ 3. The final output node must return `Output`
91
+ 4. Use `StateGraph(State, input=Input, output=Output)` for initialization
92
+ 5. Always compile with `graph = builder.compile()`
agents/agent_1_triage_hitl/.agent/SDK_REFERENCE.md ADDED
@@ -0,0 +1,971 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## API Reference
2
+
3
+ This section provides a comprehensive reference for all UiPath SDK services and methods. Each service is documented with complete method signatures, including parameter types and return types.
4
+
5
+ ### SDK Initialization
6
+
7
+ Initialize the UiPath SDK client
8
+
9
+ ```python
10
+ from uipath.platform import UiPath
11
+
12
+ # Initialize with environment variables
13
+ sdk = UiPath()
14
+
15
+ # Or with explicit credentials
16
+ sdk = UiPath(base_url="https://cloud.uipath.com/...", secret="your_token")
17
+ ```
18
+
19
+ ### Agenthub
20
+
21
+ Agenthub service
22
+
23
+ ```python
24
+ # Fetch available models from LLM Gateway discovery endpoint.
25
+ sdk.agenthub.get_available_llm_models(headers: dict[str, Any] | None=None) -> list[uipath.platform.agenthub.agenthub.LlmModel]
26
+
27
+ # Asynchronously fetch available models from LLM Gateway discovery endpoint.
28
+ sdk.agenthub.get_available_llm_models_async(headers: dict[str, Any] | None=None) -> list[uipath.platform.agenthub.agenthub.LlmModel]
29
+
30
+ # Start a system agent job.
31
+ sdk.agenthub.invoke_system_agent(agent_name: str, entrypoint: str, input_arguments: dict[str, Any] | None=None, folder_key: str | None=None, folder_path: str | None=None, headers: dict[str, Any] | None=None) -> str
32
+
33
+ # Asynchronously start a system agent and return the job.
34
+ sdk.agenthub.invoke_system_agent_async(agent_name: str, entrypoint: str, input_arguments: dict[str, Any] | None=None, folder_key: str | None=None, folder_path: str | None=None, headers: dict[str, Any] | None=None) -> str
35
+
36
+ ```
37
+
38
+ ### Api Client
39
+
40
+ Api Client service
41
+
42
+ ```python
43
+ # Access api_client service methods
44
+ service = sdk.api_client
45
+
46
+ ```
47
+
48
+ ### Assets
49
+
50
+ Assets service
51
+
52
+ ```python
53
+ # List assets using OData API with offset-based pagination.
54
+ sdk.assets.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.assets.Asset]
55
+
56
+ # Asynchronously list assets using OData API with offset-based pagination.
57
+ sdk.assets.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.assets.Asset]
58
+
59
+ # Retrieve an asset by its name.
60
+ sdk.assets.retrieve(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.assets.UserAsset | uipath.platform.orchestrator.assets.Asset
61
+
62
+ # Asynchronously retrieve an asset by its name.
63
+ sdk.assets.retrieve_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.assets.UserAsset | uipath.platform.orchestrator.assets.Asset
64
+
65
+ # Gets a specified Orchestrator credential.
66
+ sdk.assets.retrieve_credential(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Optional[str]
67
+
68
+ # Asynchronously gets a specified Orchestrator credential.
69
+ sdk.assets.retrieve_credential_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Optional[str]
70
+
71
+ # Update an asset's value.
72
+ sdk.assets.update(robot_asset: uipath.platform.orchestrator.assets.UserAsset, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
73
+
74
+ # Asynchronously update an asset's value.
75
+ sdk.assets.update_async(robot_asset: uipath.platform.orchestrator.assets.UserAsset, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
76
+
77
+ ```
78
+
79
+ ### Attachments
80
+
81
+ Attachments service
82
+
83
+ ```python
84
+ # Delete an attachment.
85
+ sdk.attachments.delete(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> None
86
+
87
+ # Delete an attachment asynchronously.
88
+ sdk.attachments.delete_async(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> None
89
+
90
+ # Download an attachment.
91
+ sdk.attachments.download(key: uuid.UUID, destination_path: str, folder_key: str | None=None, folder_path: str | None=None) -> str
92
+
93
+ # Download an attachment asynchronously.
94
+ sdk.attachments.download_async(key: uuid.UUID, destination_path: str, folder_key: str | None=None, folder_path: str | None=None) -> str
95
+
96
+ # Get the BlobFileAccess information for an attachment.
97
+ sdk.attachments.get_blob_file_access_uri(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.attachments.attachments.BlobFileAccessInfo
98
+
99
+ # Get the BlobFileAccess information for an attachment asynchronously.
100
+ sdk.attachments.get_blob_file_access_uri_async(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.attachments.attachments.BlobFileAccessInfo
101
+
102
+ # Open an attachment.
103
+ sdk.attachments.open(attachment: uipath.platform.attachments.attachments.Attachment, mode: <enum 'AttachmentMode="AttachmentMode.READ", content: Union[str, bytes, Iterable[bytes], AsyncIterable[bytes], NoneType]=None, folder_key: str | None=None, folder_path: str | None=None) -> typing.Iterator[typing.Tuple[uipath.platform.attachments.attachments.Attachment, httpx.Response]]
104
+
105
+ # Open an attachment asynchronously.
106
+ sdk.attachments.open_async(attachment: uipath.platform.attachments.attachments.Attachment, mode: <enum 'AttachmentMode="AttachmentMode.READ", content: Union[str, bytes, Iterable[bytes], AsyncIterable[bytes], NoneType]=None, folder_key: str | None=None, folder_path: str | None=None) -> typing.AsyncIterator[typing.Tuple[uipath.platform.attachments.attachments.Attachment, httpx.Response]]
107
+
108
+ # Upload a file or content to UiPath as an attachment.
109
+ sdk.attachments.upload(name: str, content: str | bytes | None=None, source_path: str | None=None, folder_key: str | None=None, folder_path: str | None=None) -> uuid.UUID
110
+
111
+ # Upload a file or content to UiPath as an attachment asynchronously.
112
+ sdk.attachments.upload_async(name: str, content: str | bytes | None=None, source_path: str | None=None, folder_key: str | None=None, folder_path: str | None=None) -> uuid.UUID
113
+
114
+ ```
115
+
116
+ ### Automation Ops
117
+
118
+ Automation Ops service
119
+
120
+ ```python
121
+ # Retrieve the deployed policy.
122
+ sdk.automation_ops.get_deployed_policy() -> dict[str, typing.Any]
123
+
124
+ # Retrieve the deployed policy (async).
125
+ sdk.automation_ops.get_deployed_policy_async() -> dict[str, typing.Any]
126
+
127
+ ```
128
+
129
+ ### Automation Tracker
130
+
131
+ Automation Tracker service
132
+
133
+ ```python
134
+ # End tracking an operation within a transaction.
135
+ sdk.automation_tracker.end_operation(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
136
+
137
+ # End tracking an operation within a transaction (async).
138
+ sdk.automation_tracker.end_operation_async(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
139
+
140
+ # End tracking a business transaction.
141
+ sdk.automation_tracker.end_transaction(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
142
+
143
+ # End tracking a business transaction (async).
144
+ sdk.automation_tracker.end_transaction_async(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
145
+
146
+ # Start tracking an operation within a transaction.
147
+ sdk.automation_tracker.start_operation(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
148
+
149
+ # Start tracking an operation within a transaction (async).
150
+ sdk.automation_tracker.start_operation_async(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
151
+
152
+ # Start tracking a business transaction.
153
+ sdk.automation_tracker.start_transaction(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
154
+
155
+ # Start tracking a business transaction (async).
156
+ sdk.automation_tracker.start_transaction_async(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
157
+
158
+ ```
159
+
160
+ ### Buckets
161
+
162
+ Buckets service
163
+
164
+ ```python
165
+ # Create a new bucket.
166
+ sdk.buckets.create(name: str, description: Optional[str]=None, identifier: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
167
+
168
+ # Async version of create().
169
+ sdk.buckets.create_async(name: str, description: Optional[str]=None, identifier: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
170
+
171
+ # Delete a bucket.
172
+ sdk.buckets.delete(name: Optional[str]=None, key: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
173
+
174
+ # Async version of delete().
175
+ sdk.buckets.delete_async(name: Optional[str]=None, key: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
176
+
177
+ # Delete a file from a bucket.
178
+ sdk.buckets.delete_file(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
179
+
180
+ # Delete a file from a bucket asynchronously.
181
+ sdk.buckets.delete_file_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
182
+
183
+ # Download a file from a bucket.
184
+ sdk.buckets.download(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, destination_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
185
+
186
+ # Download a file from a bucket asynchronously.
187
+ sdk.buckets.download_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, destination_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
188
+
189
+ # Check if bucket exists.
190
+ sdk.buckets.exists(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
191
+
192
+ # Async version of exists().
193
+ sdk.buckets.exists_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
194
+
195
+ # Check if a file exists in a bucket.
196
+ sdk.buckets.exists_file(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
197
+
198
+ # Async version of exists_file().
199
+ sdk.buckets.exists_file_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
200
+
201
+ # Get files using OData GetFiles API with offset-based pagination.
202
+ sdk.buckets.get_files(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", recursive: bool=False, file_name_glob: Optional[str]=None, skip: int=0, top: int=500, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
203
+
204
+ # Async version of get_files() with offset-based pagination.
205
+ sdk.buckets.get_files_async(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", recursive: bool=False, file_name_glob: Optional[str]=None, skip: int=0, top: int=500, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
206
+
207
+ # List buckets using OData API with offset-based pagination.
208
+ sdk.buckets.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, name: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.Bucket]
209
+
210
+ # Async version of list() with offset-based pagination.
211
+ sdk.buckets.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, name: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.Bucket]
212
+
213
+ # List files in a bucket using cursor-based pagination.
214
+ sdk.buckets.list_files(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", take_hint: int=500, continuation_token: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
215
+
216
+ # Async version of list_files() with cursor-based pagination.
217
+ sdk.buckets.list_files_async(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", take_hint: int=500, continuation_token: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
218
+
219
+ # Retrieve bucket information by its name.
220
+ sdk.buckets.retrieve(name: Optional[str]=None, key: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
221
+
222
+ # Asynchronously retrieve bucket information by its name.
223
+ sdk.buckets.retrieve_async(name: Optional[str]=None, key: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
224
+
225
+ # Upload a file to a bucket.
226
+ sdk.buckets.upload(key: Optional[str]=None, name: Optional[str]=None, blob_file_path: str, content_type: Optional[str]=None, source_path: Optional[str]=None, content: Union[str, bytes, NoneType]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
227
+
228
+ # Upload a file to a bucket asynchronously.
229
+ sdk.buckets.upload_async(key: Optional[str]=None, name: Optional[str]=None, blob_file_path: str, content_type: Optional[str]=None, source_path: Optional[str]=None, content: Union[str, bytes, NoneType]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
230
+
231
+ ```
232
+
233
+ ### Connections
234
+
235
+ Connections service
236
+
237
+ ```python
238
+ # Invoke an activity synchronously.
239
+ sdk.connections.invoke_activity(activity_metadata: uipath.platform.connections.connections.ActivityMetadata, connection_id: str, activity_input: Dict[str, Any]) -> typing.Any
240
+
241
+ # Invoke an activity asynchronously.
242
+ sdk.connections.invoke_activity_async(activity_metadata: uipath.platform.connections.connections.ActivityMetadata, connection_id: str, activity_input: Dict[str, Any]) -> typing.Any
243
+
244
+ # Lists all connections with optional filtering.
245
+ sdk.connections.list(name: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, connector_key: Optional[str]=None, skip: Optional[int]=None, top: Optional[int]=None) -> typing.List[uipath.platform.connections.connections.Connection]
246
+
247
+ # Asynchronously lists all connections with optional filtering.
248
+ sdk.connections.list_async(name: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, connector_key: Optional[str]=None, skip: Optional[int]=None, top: Optional[int]=None) -> typing.List[uipath.platform.connections.connections.Connection]
249
+
250
+ # Synchronously retrieve connection API metadata.
251
+ sdk.connections.metadata(element_instance_id: int, connector_key: str, tool_path: str, parameters: Optional[Dict[str, str]]=None, schema_mode: bool=True, max_jit_depth: int=5) -> uipath.platform.connections.connections.ConnectionMetadata
252
+
253
+ # Asynchronously retrieve connection API metadata.
254
+ sdk.connections.metadata_async(element_instance_id: int, connector_key: str, tool_path: str, parameters: Optional[Dict[str, str]]=None, schema_mode: bool=True, max_jit_depth: int=5) -> uipath.platform.connections.connections.ConnectionMetadata
255
+
256
+ # Retrieve connection details by its key.
257
+ sdk.connections.retrieve(key: str) -> uipath.platform.connections.connections.Connection
258
+
259
+ # Asynchronously retrieve connection details by its key.
260
+ sdk.connections.retrieve_async(key: str) -> uipath.platform.connections.connections.Connection
261
+
262
+ # Retrieve event payload from UiPath Integration Service.
263
+ sdk.connections.retrieve_event_payload(event_args: uipath.platform.connections.connections.EventArguments) -> typing.Dict[str, typing.Any]
264
+
265
+ # Retrieve event payload from UiPath Integration Service.
266
+ sdk.connections.retrieve_event_payload_async(event_args: uipath.platform.connections.connections.EventArguments) -> typing.Dict[str, typing.Any]
267
+
268
+ # Retrieve an authentication token for a connection.
269
+ sdk.connections.retrieve_token(key: str, token_type: <enum 'ConnectionTokenType="ConnectionTokenType.DIRECT") -> uipath.platform.connections.connections.ConnectionToken
270
+
271
+ # Asynchronously retrieve an authentication token for a connection.
272
+ sdk.connections.retrieve_token_async(key: str, token_type: <enum 'ConnectionTokenType="ConnectionTokenType.DIRECT") -> uipath.platform.connections.connections.ConnectionToken
273
+
274
+ ```
275
+
276
+ ### Context Grounding
277
+
278
+ Context Grounding service
279
+
280
+ ```python
281
+ # Add content to the index.
282
+ sdk.context_grounding.add_to_index(name: str, blob_file_path: str, content_type: Optional[str]=None, content: Union[str, bytes, NoneType]=None, source_path: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, ingest_data: bool=True) -> None
283
+
284
+ # Asynchronously add content to the index.
285
+ sdk.context_grounding.add_to_index_async(name: str, blob_file_path: str, content_type: Optional[str]=None, content: Union[str, bytes, NoneType]=None, source_path: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, ingest_data: bool=True) -> None
286
+
287
+ # Create a new ephemeral context grounding index.
288
+ sdk.context_grounding.create_ephemeral_index(usage: <enum 'EphemeralIndexUsage, attachments: List[str], folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
289
+
290
+ # Create a new ephemeral context grounding index.
291
+ sdk.context_grounding.create_ephemeral_index_async(usage: <enum 'EphemeralIndexUsage, attachments: List[str], folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
292
+
293
+ # Create a new context grounding index.
294
+ sdk.context_grounding.create_index(name: str, source: Union[uipath.platform.context_grounding.context_grounding_payloads.BucketSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.GoogleDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.DropboxSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.OneDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.ConfluenceSourceConfig], description: Optional[str]=None, extraction_strategy: Optional[str]=None, embeddings_enabled: Optional[bool]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
295
+
296
+ # Create a new context grounding index.
297
+ sdk.context_grounding.create_index_async(name: str, source: Union[uipath.platform.context_grounding.context_grounding_payloads.BucketSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.GoogleDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.DropboxSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.OneDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.ConfluenceSourceConfig], description: Optional[str]=None, extraction_strategy: Optional[str]=None, embeddings_enabled: Optional[bool]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
298
+
299
+ # Delete a context grounding index by its name.
300
+ sdk.context_grounding.delete_by_name(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
301
+
302
+ # Asynchronously delete a context grounding index by its name.
303
+ sdk.context_grounding.delete_by_name_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
304
+
305
+ # Delete a context grounding index.
306
+ sdk.context_grounding.delete_index(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
307
+
308
+ # Asynchronously delete a context grounding index.
309
+ sdk.context_grounding.delete_index_async(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
310
+
311
+ # Downloads the Batch Transform result file to the specified path.
312
+ sdk.context_grounding.download_batch_transform_result(id: str, destination_path: str, validate_status: bool=True, index_name: str | None=None) -> None
313
+
314
+ # Asynchronously downloads the Batch Transform result file to the specified path.
315
+ sdk.context_grounding.download_batch_transform_result_async(id: str, destination_path: str, validate_status: bool=True, index_name: str | None=None) -> None
316
+
317
+ # Trigger ingestion on a context grounding index by its name.
318
+ sdk.context_grounding.ingest_by_name(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
319
+
320
+ # Asynchronously trigger ingestion on a context grounding index by its name.
321
+ sdk.context_grounding.ingest_by_name_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
322
+
323
+ # Ingest data into the context grounding index.
324
+ sdk.context_grounding.ingest_data(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
325
+
326
+ # Asynchronously ingest data into the context grounding index.
327
+ sdk.context_grounding.ingest_data_async(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
328
+
329
+ # List all context grounding indexes in a folder.
330
+ sdk.context_grounding.list(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
331
+
332
+ # Asynchronously list all context grounding indexes in a folder.
333
+ sdk.context_grounding.list_async(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
334
+
335
+ # List all context grounding indexes in a folder.
336
+ sdk.context_grounding.list_indexes(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
337
+
338
+ # Asynchronously list all context grounding indexes in a folder.
339
+ sdk.context_grounding.list_indexes_async(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
340
+
341
+ # Retrieve context grounding index information by its name.
342
+ sdk.context_grounding.retrieve(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
343
+
344
+ # Retrieve all context grounding indexes across all folders.
345
+ sdk.context_grounding.retrieve_across_folders(name: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
346
+
347
+ # Asynchronously retrieve all context grounding indexes across all folders.
348
+ sdk.context_grounding.retrieve_across_folders_async(name: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
349
+
350
+ # Asynchronously retrieve context grounding index information by its name.
351
+ sdk.context_grounding.retrieve_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
352
+
353
+ # Retrieves a Batch Transform task status.
354
+ sdk.context_grounding.retrieve_batch_transform(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformResponse
355
+
356
+ # Asynchronously retrieves a Batch Transform task status.
357
+ sdk.context_grounding.retrieve_batch_transform_async(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformResponse
358
+
359
+ # Retrieve context grounding index information by its ID.
360
+ sdk.context_grounding.retrieve_by_id(id: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Any
361
+
362
+ # Retrieve asynchronously context grounding index information by its ID.
363
+ sdk.context_grounding.retrieve_by_id_async(id: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Any
364
+
365
+ # Retrieves a Deep RAG task.
366
+ sdk.context_grounding.retrieve_deep_rag(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagResponse
367
+
368
+ # Asynchronously retrieves a Deep RAG task.
369
+ sdk.context_grounding.retrieve_deep_rag_async(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagResponse
370
+
371
+ # Search for contextual information within a specific index.
372
+ sdk.context_grounding.search(name: str, query: str, number_of_results: int=10, threshold: Optional[float]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding.ContextGroundingQueryResponse]
373
+
374
+ # Search asynchronously for contextual information within a specific index.
375
+ sdk.context_grounding.search_async(name: str, query: str, number_of_results: int=10, threshold: Optional[float]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding.ContextGroundingQueryResponse]
376
+
377
+ # Starts a Batch Transform, task on the targeted index.
378
+ sdk.context_grounding.start_batch_transform(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, target_file_name: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_name: str | None=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
379
+
380
+ # Asynchronously starts a Batch Transform, task on the targeted index.
381
+ sdk.context_grounding.start_batch_transform_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, target_file_name: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_name: str | None=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
382
+
383
+ # Asynchronously starts a Batch Transform, task on the targeted index.
384
+ sdk.context_grounding.start_batch_transform_ephemeral(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
385
+
386
+ # Asynchronously starts a Batch Transform, task on the targeted index.
387
+ sdk.context_grounding.start_batch_transform_ephemeral_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
388
+
389
+ # Starts a Deep RAG task on the targeted index.
390
+ sdk.context_grounding.start_deep_rag(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_name: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
391
+
392
+ # Asynchronously starts a Deep RAG task on the targeted index.
393
+ sdk.context_grounding.start_deep_rag_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_name: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
394
+
395
+ # Asynchronously starts a Deep RAG task on the targeted index.
396
+ sdk.context_grounding.start_deep_rag_ephemeral(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
397
+
398
+ # Asynchronously starts a Deep RAG task on the targeted index.
399
+ sdk.context_grounding.start_deep_rag_ephemeral_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
400
+
401
+ # Perform a unified search on a context grounding index.
402
+ sdk.context_grounding.unified_search(name: str, query: str, search_mode: <enum 'SearchMode="SearchMode.SEMANTIC", number_of_results: int=10, threshold: float=0.0, scope: Optional[uipath.platform.context_grounding.context_grounding.UnifiedSearchScope]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding.UnifiedQueryResult
403
+
404
+ # Asynchronously perform a unified search on a context grounding index.
405
+ sdk.context_grounding.unified_search_async(name: str, query: str, search_mode: <enum 'SearchMode="SearchMode.SEMANTIC", number_of_results: int=10, threshold: float=0.0, scope: Optional[uipath.platform.context_grounding.context_grounding.UnifiedSearchScope]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding.UnifiedQueryResult
406
+
407
+ ```
408
+
409
+ ### Conversational
410
+
411
+ Conversational service
412
+
413
+ ```python
414
+ # Access conversational service methods
415
+ service = sdk.conversational
416
+
417
+ ```
418
+
419
+ ### Documents
420
+
421
+ Documents service
422
+
423
+ ```python
424
+ # Classify a document using a DU Modern project.
425
+ sdk.documents.classify(project_type: <enum 'ProjectType, tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
426
+
427
+ # Asynchronously version of the [`classify`][uipath.platform.documents._documents_service.DocumentsService.classify] method.
428
+ sdk.documents.classify_async(project_type: <enum 'ProjectType, tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
429
+
430
+ # Create a validate classification action for a document based on the classification results. More details about validation actions can be found in the [official documentation](https://docs.uipath.com/ixp/automation-cloud/latest/user-guide/validating-classifications).
431
+ sdk.documents.create_validate_classification_action(classification_results: List[uipath.platform.documents.documents.ClassificationResult], action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateClassificationAction
432
+
433
+ # Asynchronous version of the [`create_validation_action`][uipath.platform.documents._documents_service.DocumentsService.create_validate_classification_action] method.
434
+ sdk.documents.create_validate_classification_action_async(classification_results: List[uipath.platform.documents.documents.ClassificationResult], action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateClassificationAction
435
+
436
+ # Create a validate extraction action for a document based on the extraction response. More details about validation actions can be found in the [official documentation](https://docs.uipath.com/ixp/automation-cloud/latest/user-guide/validating-extractions).
437
+ sdk.documents.create_validate_extraction_action(extraction_response: uipath.platform.documents.documents.ExtractionResponse, action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateExtractionAction
438
+
439
+ # Asynchronous version of the [`create_validation_action`][uipath.platform.documents._documents_service.DocumentsService.create_validate_extraction_action] method.
440
+ sdk.documents.create_validate_extraction_action_async(extraction_response: uipath.platform.documents.documents.ExtractionResponse, action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateExtractionAction
441
+
442
+ # Extract predicted data from a document using an DU Modern/IXP project.
443
+ sdk.documents.extract(tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None, classification_result: Optional[uipath.platform.documents.documents.ClassificationResult]=None, project_type: Optional[uipath.platform.documents.documents.ProjectType]=None, document_type_name: Optional[str]=None) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
444
+
445
+ # Asynchronously version of the [`extract`][uipath.platform.documents._documents_service.DocumentsService.extract] method.
446
+ sdk.documents.extract_async(tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None, classification_result: Optional[uipath.platform.documents.documents.ClassificationResult]=None, project_type: Optional[uipath.platform.documents.documents.ProjectType]=None, document_type_name: Optional[str]=None) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
447
+
448
+ # Get the result of a validate classification action.
449
+ sdk.documents.get_validate_classification_result(validation_action: uipath.platform.documents.documents.ValidateClassificationAction) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
450
+
451
+ # Asynchronous version of the [`get_validation_result`][uipath.platform.documents._documents_service.DocumentsService.get_validate_classification_result] method.
452
+ sdk.documents.get_validate_classification_result_async(validation_action: uipath.platform.documents.documents.ValidateClassificationAction) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
453
+
454
+ # Get the result of a validate extraction action.
455
+ sdk.documents.get_validate_extraction_result(validation_action: uipath.platform.documents.documents.ValidateExtractionAction) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
456
+
457
+ # Asynchronous version of the [`get_validation_result`][uipath.platform.documents._documents_service.DocumentsService.get_validate_extraction_result] method.
458
+ sdk.documents.get_validate_extraction_result_async(validation_action: uipath.platform.documents.documents.ValidateExtractionAction) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
459
+
460
+ # Retrieve the result of an IXP extraction operation (single-shot, non-blocking).
461
+ sdk.documents.retrieve_ixp_extraction_result(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ExtractionResponseIXP
462
+
463
+ # Asynchronous version of the [`retrieve_ixp_extraction_result`][uipath.platform.documents._documents_service.DocumentsService.retrieve_ixp_extraction_result] method.
464
+ sdk.documents.retrieve_ixp_extraction_result_async(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ExtractionResponseIXP
465
+
466
+ # Retrieve the result of an IXP create validate extraction action operation (single-shot, non-blocking).
467
+ sdk.documents.retrieve_ixp_extraction_validation_result(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ValidateExtractionAction
468
+
469
+ # Asynchronous version of the [`retrieve_ixp_extraction_validation_result`][uipath.platform.documents._documents_service.DocumentsService.retrieve_ixp_extraction_validation_result] method.
470
+ sdk.documents.retrieve_ixp_extraction_validation_result_async(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ValidateExtractionAction
471
+
472
+ # Start an IXP extraction process without waiting for results (non-blocking).
473
+ sdk.documents.start_ixp_extraction(project_name: str, tag: str, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionResponse
474
+
475
+ # Asynchronous version of the [`start_ixp_extraction`][uipath.platform.documents._documents_service.DocumentsService.start_ixp_extraction] method.
476
+ sdk.documents.start_ixp_extraction_async(project_name: str, tag: str, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionResponse
477
+
478
+ # Start an IXP extraction validation action without waiting for results (non-blocking).
479
+ sdk.documents.start_ixp_extraction_validation(extraction_response: uipath.platform.documents.documents.ExtractionResponseIXP, action_title: str, action_catalog: Optional[str]=None, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionValidationResponse
480
+
481
+ # Asynchronous version of the [`start_ixp_extraction_validation`][uipath.platform.documents._documents_service.DocumentsService.start_ixp_extraction_validation] method.
482
+ sdk.documents.start_ixp_extraction_validation_async(extraction_response: uipath.platform.documents.documents.ExtractionResponseIXP, action_title: str, action_catalog: Optional[str]=None, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionValidationResponse
483
+
484
+ ```
485
+
486
+ ### Entities
487
+
488
+ Entities service
489
+
490
+ ```python
491
+ # Create a new entity with the given schema and return its id.
492
+ sdk.entities.create_entity(name: str, fields: List[uipath.platform.entities.entities.EntityCreateFieldOptions], options: Optional[uipath.platform.entities.entities.EntityCreateOptions]=None) -> str
493
+
494
+ # Asynchronously create a new entity with the given schema.
495
+ sdk.entities.create_entity_async(name: str, fields: List[uipath.platform.entities.entities.EntityCreateFieldOptions], options: Optional[uipath.platform.entities.entities.EntityCreateOptions]=None) -> str
496
+
497
+ # Remove the file attached to a File-type field on a record.
498
+ sdk.entities.delete_attachment(entity_id: str, record_id: str, field_name: str, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
499
+
500
+ # Asynchronously remove the file attached to a File-type field.
501
+ sdk.entities.delete_attachment_async(entity_id: str, record_id: str, field_name: str, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
502
+
503
+ # Delete an entity and all of its records.
504
+ sdk.entities.delete_entity(entity_id: str) -> None
505
+
506
+ # Asynchronously delete an entity and all of its records.
507
+ sdk.entities.delete_entity_async(entity_id: str) -> None
508
+
509
+ # Delete a single record by id.
510
+ sdk.entities.delete_record(entity_key: str, record_id: str) -> None
511
+
512
+ # Asynchronously delete a single record by id.
513
+ sdk.entities.delete_record_async(entity_key: str, record_id: str) -> None
514
+
515
+ # Delete multiple records from an entity in a single batch operation.
516
+ sdk.entities.delete_records(entity_key: str, record_ids: List[str], fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
517
+
518
+ # Asynchronously delete multiple records from an entity in a single batch operation.
519
+ sdk.entities.delete_records_async(entity_key: str, record_ids: List[str], fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
520
+
521
+ # Download a file attached to a record and return its raw bytes.
522
+ sdk.entities.download_attachment(entity_id: str, record_id: str, field_name: str) -> bytes
523
+
524
+ # Asynchronously download a file attached to a record.
525
+ sdk.entities.download_attachment_async(entity_id: str, record_id: str, field_name: str) -> bytes
526
+
527
+ # Get the values of a choice set by its ID.
528
+ sdk.entities.get_choiceset_values(choiceset_id: str, start: Optional[int]=None, limit: Optional[int]=None) -> typing.List[uipath.platform.entities.entities.ChoiceSetValue]
529
+
530
+ # Asynchronously get the values of a choice set by its ID.
531
+ sdk.entities.get_choiceset_values_async(choiceset_id: str, start: Optional[int]=None, limit: Optional[int]=None) -> typing.List[uipath.platform.entities.entities.ChoiceSetValue]
532
+
533
+ # Fetch a single entity record by its id.
534
+ sdk.entities.get_record(entity_key: str, record_id: str, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
535
+
536
+ # Asynchronously fetch a single entity record by its id.
537
+ sdk.entities.get_record_async(entity_key: str, record_id: str, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
538
+
539
+ # Bulk-import records into an entity from a CSV file.
540
+ sdk.entities.import_records(entity_id: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.entities.entities.EntityImportRecordsResponse
541
+
542
+ # Asynchronously bulk-import records into an entity from a CSV file.
543
+ sdk.entities.import_records_async(entity_id: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.entities.entities.EntityImportRecordsResponse
544
+
545
+ # Insert a single record into an entity and return the inserted row.
546
+ sdk.entities.insert_record(entity_key: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
547
+
548
+ # Asynchronously insert a single record into an entity.
549
+ sdk.entities.insert_record_async(entity_key: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
550
+
551
+ # Insert multiple records into an entity in a single batch operation.
552
+ sdk.entities.insert_records(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
553
+
554
+ # Asynchronously insert multiple records into an entity in a single batch operation.
555
+ sdk.entities.insert_records_async(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
556
+
557
+ # List all choice sets in Data Service.
558
+ sdk.entities.list_choicesets() -> typing.List[uipath.platform.entities.entities.Entity]
559
+
560
+ # Asynchronously list all choice sets in Data Service.
561
+ sdk.entities.list_choicesets_async() -> typing.List[uipath.platform.entities.entities.Entity]
562
+
563
+ # List all entities in Data Service.
564
+ sdk.entities.list_entities() -> typing.List[uipath.platform.entities.entities.Entity]
565
+
566
+ # Asynchronously list all entities in the Data Service.
567
+ sdk.entities.list_entities_async() -> typing.List[uipath.platform.entities.entities.Entity]
568
+
569
+ # List records from an entity with optional pagination and schema validation.
570
+ sdk.entities.list_records(entity_key: str, schema: Optional[Type[Any]]=None, start: Optional[int]=None, limit: Optional[int]=None, expansion_level: Optional[int]=None, filter: Optional[str]=None, orderby: Optional[str]=None, select: Optional[List[str]]=None, expand: Optional[List[str]]=None) -> uipath.platform.entities.entities.EntityRecordsListResponse
571
+
572
+ # Asynchronously list records from an entity with optional pagination and schema validation.
573
+ sdk.entities.list_records_async(entity_key: str, schema: Optional[Type[Any]]=None, start: Optional[int]=None, limit: Optional[int]=None, expansion_level: Optional[int]=None, filter: Optional[str]=None, orderby: Optional[str]=None, select: Optional[List[str]]=None, expand: Optional[List[str]]=None) -> uipath.platform.entities.entities.EntityRecordsListResponse
574
+
575
+ # Query entity records using a validated SQL query.
576
+ sdk.entities.query_entity_records(sql_query: str) -> typing.List[typing.Dict[str, typing.Any]]
577
+
578
+ # Asynchronously query entity records using a validated SQL query.
579
+ sdk.entities.query_entity_records_async(sql_query: str) -> typing.List[typing.Dict[str, typing.Any]]
580
+
581
+ # Resolve an agent entity set, applying resource overwrites.
582
+ sdk.entities.resolve_entity_set(items: List[uipath.platform.entities.entities.DataFabricEntityItem]) -> uipath.platform.entities.entities.EntitySetResolution
583
+
584
+ # Resolve an agent entity set, applying resource overwrites.
585
+ sdk.entities.resolve_entity_set_async(items: List[uipath.platform.entities.entities.DataFabricEntityItem]) -> uipath.platform.entities.entities.EntitySetResolution
586
+
587
+ # Retrieve an entity by its key.
588
+ sdk.entities.retrieve(entity_key: str) -> uipath.platform.entities.entities.Entity
589
+
590
+ # Asynchronously retrieve an entity by its key.
591
+ sdk.entities.retrieve_async(entity_key: str) -> uipath.platform.entities.entities.Entity
592
+
593
+ # Retrieve an entity by its name.
594
+ sdk.entities.retrieve_by_name(entity_name: str, folder_key: Optional[str]=None) -> uipath.platform.entities.entities.Entity
595
+
596
+ # Asynchronously retrieve an entity by its name.
597
+ sdk.entities.retrieve_by_name_async(entity_name: str, folder_key: Optional[str]=None) -> uipath.platform.entities.entities.Entity
598
+
599
+ # Retrieve records with structured filters, sorting, expansion, joins, and aggregates.
600
+ sdk.entities.retrieve_records(entity_key: str, filter_group: Optional[uipath.platform.entities.entities.EntityQueryFilterGroup]=None, sort_options: Optional[List[uipath.platform.entities.entities.EntityQuerySortOption]]=None, selected_fields: Optional[List[str]]=None, expansions: Optional[List[Any]]=None, expansion_level: Optional[int]=None, aggregates: Optional[List[uipath.platform.entities.entities.EntityAggregate]]=None, group_by: Optional[List[str]]=None, joins: Optional[List[uipath.platform.entities.entities.EntityJoin]]=None, binnings: Optional[List[uipath.platform.entities.entities.EntityBinning]]=None, start: Optional[int]=None, limit: Optional[int]=None) -> uipath.platform.entities.entities.RetrieveEntityRecordsResponse
601
+
602
+ # Asynchronously retrieve records with structured filters, sorting, expansion, joins, and aggregates.
603
+ sdk.entities.retrieve_records_async(entity_key: str, filter_group: Optional[uipath.platform.entities.entities.EntityQueryFilterGroup]=None, sort_options: Optional[List[uipath.platform.entities.entities.EntityQuerySortOption]]=None, selected_fields: Optional[List[str]]=None, expansions: Optional[List[Any]]=None, expansion_level: Optional[int]=None, aggregates: Optional[List[uipath.platform.entities.entities.EntityAggregate]]=None, group_by: Optional[List[str]]=None, joins: Optional[List[uipath.platform.entities.entities.EntityJoin]]=None, binnings: Optional[List[uipath.platform.entities.entities.EntityBinning]]=None, start: Optional[int]=None, limit: Optional[int]=None) -> uipath.platform.entities.entities.RetrieveEntityRecordsResponse
604
+
605
+ # Update an entity's display name, description, and/or RBAC flag.
606
+ sdk.entities.update_entity_metadata(entity_id: str, metadata: Union[uipath.platform.entities.entities.EntityMetadataUpdateOptions, Dict[str, Any]]) -> None
607
+
608
+ # Asynchronously update an entity's display name, description, and/or RBAC flag.
609
+ sdk.entities.update_entity_metadata_async(entity_id: str, metadata: Union[uipath.platform.entities.entities.EntityMetadataUpdateOptions, Dict[str, Any]]) -> None
610
+
611
+ # Update a single record by id and return the updated row.
612
+ sdk.entities.update_record(entity_key: str, record_id: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
613
+
614
+ # Asynchronously update a single record by id.
615
+ sdk.entities.update_record_async(entity_key: str, record_id: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
616
+
617
+ # Update multiple records in an entity in a single batch operation.
618
+ sdk.entities.update_records(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
619
+
620
+ # Asynchronously update multiple records in an entity in a single batch operation.
621
+ sdk.entities.update_records_async(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
622
+
623
+ # Upload a file attachment to a File-type field on a record.
624
+ sdk.entities.upload_attachment(entity_id: str, record_id: str, field_name: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
625
+
626
+ # Asynchronously upload a file attachment to a File-type field on a record.
627
+ sdk.entities.upload_attachment_async(entity_id: str, record_id: str, field_name: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
628
+
629
+ # Parse a batch response, optionally validating success records against ``schema``.
630
+ sdk.entities.validate_entity_batch(batch_response: httpx.Response, schema: Optional[Type[Any]]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
631
+
632
+ ```
633
+
634
+ ### Folders
635
+
636
+ Folders service
637
+
638
+ ```python
639
+ # Retrieve the personal workspace folder for the current user.
640
+ sdk.folders.get_personal_workspace() -> uipath.platform.orchestrator.folder.PersonalWorkspace
641
+
642
+ # Asynchronously retrieve the personal workspace folder for the current user.
643
+ sdk.folders.get_personal_workspace_async() -> uipath.platform.orchestrator.folder.PersonalWorkspace
644
+
645
+ # Resolve a folder path to its corresponding folder key.
646
+ sdk.folders.retrieve_folder_key(folder_path: str | None) -> str | None
647
+
648
+ # Asynchronously resolve a folder path to its corresponding folder key.
649
+ sdk.folders.retrieve_folder_key_async(folder_path: str | None) -> str | None
650
+
651
+ # Retrieve the folder key by folder path with pagination support.
652
+ sdk.folders.retrieve_key(folder_path: str) -> typing.Optional[str]
653
+
654
+ # Retrieve the folder key by folder path with pagination support.
655
+ sdk.folders.retrieve_key_async(folder_path: str) -> typing.Optional[str]
656
+
657
+ ```
658
+
659
+ ### Guardrails
660
+
661
+ Guardrails service
662
+
663
+ ```python
664
+ # Validate input text using the provided guardrail.
665
+ sdk.guardrails.evaluate_guardrail(input_data: str | dict[str, Any], guardrail: uipath.platform.guardrails.guardrails.BuiltInValidatorGuardrail) -> uipath.core.guardrails.guardrails.GuardrailValidationResult
666
+
667
+ ```
668
+
669
+ ### Jobs
670
+
671
+ Jobs service
672
+
673
+ ```python
674
+ # Create and upload an attachment, optionally linking it to a job.
675
+ sdk.jobs.create_attachment(name: str, content: Union[str, bytes, NoneType]=None, source_path: Union[str, pathlib.Path, NoneType]=None, job_key: Union[str, uuid.UUID, NoneType]=None, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uuid.UUID
676
+
677
+ # Create and upload an attachment asynchronously, optionally linking it to a job.
678
+ sdk.jobs.create_attachment_async(name: str, content: Union[str, bytes, NoneType]=None, source_path: Union[str, pathlib.Path, NoneType]=None, job_key: Union[str, uuid.UUID, NoneType]=None, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uuid.UUID
679
+
680
+ # Check if job exists.
681
+ sdk.jobs.exists(job_key: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
682
+
683
+ # Async version of exists().
684
+ sdk.jobs.exists_async(job_key: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
685
+
686
+ # Get the actual output data, downloading from attachment if necessary.
687
+ sdk.jobs.extract_output(job: uipath.platform.orchestrator.job.Job) -> typing.Optional[str]
688
+
689
+ # Asynchronously fetch the actual output data, downloading from attachment if necessary.
690
+ sdk.jobs.extract_output_async(job: uipath.platform.orchestrator.job.Job) -> typing.Optional[str]
691
+
692
+ # Link an attachment to a job.
693
+ sdk.jobs.link_attachment(attachment_key: uuid.UUID, job_key: uuid.UUID, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None)
694
+
695
+ # Link an attachment to a job asynchronously.
696
+ sdk.jobs.link_attachment_async(attachment_key: uuid.UUID, job_key: uuid.UUID, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None)
697
+
698
+ # List jobs using OData API with offset-based pagination.
699
+ sdk.jobs.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.job.Job]
700
+
701
+ # Async version of list() with offset-based pagination.
702
+ sdk.jobs.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.job.Job]
703
+
704
+ # List attachments associated with a specific job.
705
+ sdk.jobs.list_attachments(job_key: uuid.UUID, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[str]
706
+
707
+ # List attachments associated with a specific job asynchronously.
708
+ sdk.jobs.list_attachments_async(job_key: uuid.UUID, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[str]
709
+
710
+ # Restart a completed or failed job.
711
+ sdk.jobs.restart(job_key: str, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.job.Job
712
+
713
+ # Async version of restart().
714
+ sdk.jobs.restart_async(job_key: str, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.job.Job
715
+
716
+ # Sends a payload to resume a paused job waiting for input, identified by its inbox ID.
717
+ sdk.jobs.resume(inbox_id: Optional[str]=None, job_id: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, payload: Any) -> None
718
+
719
+ # Asynchronously sends a payload to resume a paused job waiting for input, identified by its inbox ID.
720
+ sdk.jobs.resume_async(inbox_id: Optional[str]=None, job_id: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, payload: Any) -> None
721
+
722
+ # Retrieve a job identified by its key.
723
+ sdk.jobs.retrieve(job_key: str, folder_key: str | None=None, folder_path: str | None=None, process_name: str | None=None) -> uipath.platform.orchestrator.job.Job
724
+
725
+ # Fetch payload data for API triggers.
726
+ sdk.jobs.retrieve_api_payload(inbox_id: str) -> typing.Any
727
+
728
+ # Asynchronously fetch payload data for API triggers.
729
+ sdk.jobs.retrieve_api_payload_async(inbox_id: str) -> typing.Any
730
+
731
+ # Asynchronously retrieve a job identified by its key.
732
+ sdk.jobs.retrieve_async(job_key: str, folder_key: str | None=None, folder_path: str | None=None, process_name: str | None=None) -> uipath.platform.orchestrator.job.Job
733
+
734
+ # Fetch payload data for Integration Services (Inbox) triggers.
735
+ sdk.jobs.retrieve_inbox_payload(inbox_id: str) -> typing.Any
736
+
737
+ # Asynchronously fetch payload data for Integration Services (Inbox) triggers.
738
+ sdk.jobs.retrieve_inbox_payload_async(inbox_id: str) -> typing.Any
739
+
740
+ # Stop one or more jobs with specified strategy.
741
+ sdk.jobs.stop(job_keys: List[str], strategy: str="SoftStop", folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
742
+
743
+ # Async version of stop().
744
+ sdk.jobs.stop_async(job_keys: List[str], strategy: str="SoftStop", folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
745
+
746
+ ```
747
+
748
+ ### Llm
749
+
750
+ Llm service
751
+
752
+ ```python
753
+ # Generate chat completions using UiPath's normalized LLM Gateway API.
754
+ sdk.llm.chat_completions(messages: list[dict[str, str]] | list[tuple[str, str]], model: str="gpt-4.1-mini-2025-04-14", max_tokens: int=4096, temperature: float=0, n: int=1, frequency_penalty: float=0, presence_penalty: float=0, top_p: float | None=1, top_k: int | None=None, tools: list[uipath.platform.chat.llm_gateway.ToolDefinition] | None=None, tool_choice: Union[uipath.platform.chat.llm_gateway.AutoToolChoice, uipath.platform.chat.llm_gateway.RequiredToolChoice, uipath.platform.chat.llm_gateway.SpecificToolChoice, Literal['auto', 'none'], NoneType]=None, response_format: dict[str, Any] | type[pydantic.main.BaseModel] | None=None, api_version: str="2024-08-01-preview")
755
+
756
+ ```
757
+
758
+ ### Llm Openai
759
+
760
+ Llm Openai service
761
+
762
+ ```python
763
+ # Generate chat completions using UiPath's LLM Gateway service.
764
+ sdk.llm_openai.chat_completions(messages: list[dict[str, str]], model: str="gpt-4.1-mini-2025-04-14", max_tokens: int=4096, temperature: float=0, response_format: dict[str, Any] | type[pydantic.main.BaseModel] | None=None, api_version: str="2024-10-21")
765
+
766
+ # Generate text embeddings using UiPath's LLM Gateway service.
767
+ sdk.llm_openai.embeddings(input: str, embedding_model: str="text-embedding-ada-002", openai_api_version: str="2024-10-21")
768
+
769
+ ```
770
+
771
+ ### Mcp
772
+
773
+ Mcp service
774
+
775
+ ```python
776
+ # List all MCP servers.
777
+ sdk.mcp.list(folder_path: str | None=None) -> typing.List[uipath.platform.orchestrator.mcp.McpServer]
778
+
779
+ # Asynchronously list all MCP servers.
780
+ sdk.mcp.list_async(folder_path: str | None=None) -> typing.List[uipath.platform.orchestrator.mcp.McpServer]
781
+
782
+ # Retrieve a specific MCP server by its slug.
783
+ sdk.mcp.retrieve(slug: str, folder_path: str | None=None) -> uipath.platform.orchestrator.mcp.McpServer
784
+
785
+ # Asynchronously retrieve a specific MCP server by its slug.
786
+ sdk.mcp.retrieve_async(slug: str, folder_path: str | None=None) -> uipath.platform.orchestrator.mcp.McpServer
787
+
788
+ ```
789
+
790
+ ### Memory
791
+
792
+ Memory service
793
+
794
+ ```python
795
+ # Create a new memory space.
796
+ sdk.memory.create(name: str, description: Optional[str]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpace
797
+
798
+ # Asynchronously create a new memory space.
799
+ sdk.memory.create_async(name: str, description: Optional[str]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpace
800
+
801
+ # Ingest a resolved escalation outcome into memory.
802
+ sdk.memory.escalation_ingest(memory_space_id: str, request: uipath.platform.memory.memory.EscalationMemoryIngestRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
803
+
804
+ # Asynchronously ingest a resolved escalation outcome into memory.
805
+ sdk.memory.escalation_ingest_async(memory_space_id: str, request: uipath.platform.memory.memory.EscalationMemoryIngestRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
806
+
807
+ # Search escalation memory for previously resolved outcomes.
808
+ sdk.memory.escalation_search(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.EscalationMemorySearchResponse
809
+
810
+ # Asynchronously search escalation memory for previously resolved outcomes.
811
+ sdk.memory.escalation_search_async(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.EscalationMemorySearchResponse
812
+
813
+ # List memory spaces with optional OData query parameters.
814
+ sdk.memory.list(filter: Optional[str]=None, orderby: Optional[str]=None, top: Optional[int]=None, skip: Optional[int]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpaceListResponse
815
+
816
+ # Asynchronously list memory spaces.
817
+ sdk.memory.list_async(filter: Optional[str]=None, orderby: Optional[str]=None, top: Optional[int]=None, skip: Optional[int]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpaceListResponse
818
+
819
+ # Search a memory space via LLMOps.
820
+ sdk.memory.search(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySearchResponse
821
+
822
+ # Asynchronously search a memory space via LLMOps.
823
+ sdk.memory.search_async(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySearchResponse
824
+
825
+ ```
826
+
827
+ ### Orchestrator Setup
828
+
829
+ Orchestrator Setup service
830
+
831
+ ```python
832
+ # Fire-and-forget POST requests to enable first run for StudioWeb.
833
+ sdk.orchestrator_setup.enable_first_run() -> None
834
+
835
+ # Fire-and-forget POST requests to enable first run for StudioWeb.
836
+ sdk.orchestrator_setup.enable_first_run_async() -> None
837
+
838
+ ```
839
+
840
+ ### Processes
841
+
842
+ Processes service
843
+
844
+ ```python
845
+ # Start execution of a process by its name.
846
+ sdk.processes.invoke(name: str, input_arguments: Optional[Dict[str, Any]]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, attachments: Optional[list[uipath.platform.attachments.attachments.Attachment]]=None, parent_operation_id: Optional[str]=None, run_as_me: Optional[bool]=None, **kwargs) -> uipath.platform.orchestrator.job.Job
847
+
848
+ # Asynchronously start execution of a process by its name.
849
+ sdk.processes.invoke_async(name: str, input_arguments: Optional[Dict[str, Any]]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, attachments: Optional[list[uipath.platform.attachments.attachments.Attachment]]=None, parent_operation_id: Optional[str]=None, run_as_me: Optional[bool]=None, **kwargs) -> uipath.platform.orchestrator.job.Job
850
+
851
+ ```
852
+
853
+ ### Queues
854
+
855
+ Queues service
856
+
857
+ ```python
858
+ # Completes a transaction item with the specified result.
859
+ sdk.queues.complete_transaction_item(transaction_key: str, result: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItemResult], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
860
+
861
+ # Asynchronously completes a transaction item with the specified result.
862
+ sdk.queues.complete_transaction_item_async(transaction_key: str, result: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItemResult], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
863
+
864
+ # Creates a new queue item in the Orchestrator.
865
+ sdk.queues.create_item(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
866
+
867
+ # Asynchronously creates a new queue item in the Orchestrator.
868
+ sdk.queues.create_item_async(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
869
+
870
+ # Creates multiple queue items in bulk.
871
+ sdk.queues.create_items(items: List[Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem]], queue_name: str, commit_type: <enum 'CommitType, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
872
+
873
+ # Asynchronously creates multiple queue items in bulk.
874
+ sdk.queues.create_items_async(items: List[Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem]], queue_name: str, commit_type: <enum 'CommitType, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
875
+
876
+ # Creates a new transaction item in a queue.
877
+ sdk.queues.create_transaction_item(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItem], queue_name: Optional[str]=None, no_robot: bool=False, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
878
+
879
+ # Asynchronously creates a new transaction item in a queue.
880
+ sdk.queues.create_transaction_item_async(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItem], queue_name: Optional[str]=None, no_robot: bool=False, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
881
+
882
+ # Retrieves a list of queue items from the Orchestrator.
883
+ sdk.queues.list_items(queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
884
+
885
+ # Asynchronously retrieves a list of queue items from the Orchestrator.
886
+ sdk.queues.list_items_async(queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
887
+
888
+ # Updates the progress of a transaction item.
889
+ sdk.queues.update_progress_of_transaction_item(transaction_key: str, progress: str, queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
890
+
891
+ # Asynchronously updates the progress of a transaction item.
892
+ sdk.queues.update_progress_of_transaction_item_async(transaction_key: str, progress: str, queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
893
+
894
+ ```
895
+
896
+ ### Remote A2A
897
+
898
+ Remote A2A service
899
+
900
+ ```python
901
+ # List Remote A2A agents.
902
+ sdk.remote_a2a.list(top: int | None=None, skip: int | None=None, search: str | None=None, folder_path: str | None=None) -> typing.List[uipath.platform.agenthub.remote_a2a.RemoteA2aAgent]
903
+
904
+ # Asynchronously list Remote A2A agents.
905
+ sdk.remote_a2a.list_async(top: int | None=None, skip: int | None=None, search: str | None=None, folder_path: str | None=None) -> typing.List[uipath.platform.agenthub.remote_a2a.RemoteA2aAgent]
906
+
907
+ # Retrieve a specific Remote A2A agent by slug.
908
+ sdk.remote_a2a.retrieve(slug: str, folder_path: str | None=None) -> uipath.platform.agenthub.remote_a2a.RemoteA2aAgent
909
+
910
+ # Asynchronously retrieve a specific Remote A2A agent by slug.
911
+ sdk.remote_a2a.retrieve_async(slug: str, folder_path: str | None=None) -> uipath.platform.agenthub.remote_a2a.RemoteA2aAgent
912
+
913
+ ```
914
+
915
+ ### Resource Catalog
916
+
917
+ Resource Catalog service
918
+
919
+ ```python
920
+ # Get tenant scoped resources and folder scoped resources (accessible to the user).
921
+ sdk.resource_catalog.list(resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
922
+
923
+ # Asynchronously get tenant scoped resources and folder scoped resources (accessible to the user).
924
+ sdk.resource_catalog.list_async(resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
925
+
926
+ # Get resources of a specific type (tenant scoped or folder scoped).
927
+ sdk.resource_catalog.list_by_type(resource_type: <enum 'ResourceType, name: Optional[str]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
928
+
929
+ # Asynchronously get resources of a specific type (tenant scoped or folder scoped).
930
+ sdk.resource_catalog.list_by_type_async(resource_type: <enum 'ResourceType, name: Optional[str]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
931
+
932
+ # Search for tenant scoped resources and folder scoped resources (accessible to the user).
933
+ sdk.resource_catalog.search(name: Optional[str]=None, resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
934
+
935
+ # Asynchronously search for tenant scoped resources and folder scoped resources (accessible to the user).
936
+ sdk.resource_catalog.search_async(name: Optional[str]=None, resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
937
+
938
+ ```
939
+
940
+ ### Semantic Proxy
941
+
942
+ Semantic Proxy service
943
+
944
+ ```python
945
+ # Detect PII in the provided documents and/or files.
946
+ sdk.semantic_proxy.detect_pii(request: uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionRequest) -> uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionResponse
947
+
948
+ # Detect PII in the provided documents and/or files (async).
949
+ sdk.semantic_proxy.detect_pii_async(request: uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionRequest) -> uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionResponse
950
+
951
+ ```
952
+
953
+ ### Tasks
954
+
955
+ Tasks service
956
+
957
+ ```python
958
+ # Creates a new task synchronously.
959
+ sdk.tasks.create(title: str, data: Optional[Dict[str, Any]]=None, app_name: Optional[str]=None, app_key: Optional[str]=None, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, assignee: Optional[str]=None, recipient: Optional[uipath.platform.action_center.tasks.TaskRecipient]=None, priority: Optional[str]=None, labels: Optional[List[str]]=None, is_actionable_message_enabled: Optional[bool]=None, actionable_message_metadata: Optional[Dict[str, Any]]=None, source_name: str="Agent") -> uipath.platform.action_center.tasks.Task
960
+
961
+ # Creates a new action asynchronously.
962
+ sdk.tasks.create_async(title: str, data: Optional[Dict[str, Any]]=None, app_name: Optional[str]=None, app_key: Optional[str]=None, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, assignee: Optional[str]=None, recipient: Optional[uipath.platform.action_center.tasks.TaskRecipient]=None, priority: Optional[str]=None, labels: Optional[List[str]]=None, is_actionable_message_enabled: Optional[bool]=None, actionable_message_metadata: Optional[Dict[str, Any]]=None, source_name: str="Agent") -> uipath.platform.action_center.tasks.Task
963
+
964
+ # Retrieves a task by its key synchronously.
965
+ sdk.tasks.retrieve(action_key: str, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, app_name: str | None=None) -> uipath.platform.action_center.tasks.Task
966
+
967
+ # Retrieves a task by its key asynchronously.
968
+ sdk.tasks.retrieve_async(action_key: str, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, app_name: str | None=None) -> uipath.platform.action_center.tasks.Task
969
+
970
+ ```
971
+
agents/agent_1_triage_hitl/.claude/commands/eval.md ADDED
@@ -0,0 +1,287 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ allowed-tools: Bash, Read, Write, Edit, Glob
3
+ description: Create and run agent evaluations
4
+ ---
5
+
6
+ I'll help you create and run evaluations for your UiPath agent.
7
+
8
+ ## Step 1: Check project setup
9
+
10
+ Let me check your project structure:
11
+
12
+ !ls -la evaluations/ entry-points.json 2>/dev/null || echo "NEEDS_SETUP"
13
+
14
+ # Check if schemas might be stale (main.py newer than entry-points.json)
15
+ !if [ -f main.py ] && [ -f entry-points.json ] && [ main.py -nt entry-points.json ]; then echo "SCHEMAS_MAY_BE_STALE"; fi
16
+
17
+ ### If NEEDS_SETUP
18
+
19
+ If `entry-points.json` doesn't exist, initialize the project first:
20
+
21
+ !uv run uipath init
22
+
23
+ Then re-run this skill.
24
+
25
+ ### If SCHEMAS_MAY_BE_STALE
26
+
27
+ Your `main.py` is newer than `entry-points.json`. Refresh schemas:
28
+
29
+ !uv run uipath init --no-agents-md-override
30
+
31
+ ## Step 2: What would you like to do?
32
+
33
+ 1. **Create new eval set** - Set up evaluations from scratch
34
+ 2. **Add test case** - Add a test to existing eval set
35
+ 3. **Run evaluations** - Execute tests and see results
36
+ 4. **Analyze failures** - Debug failing tests
37
+
38
+ ---
39
+
40
+ ## Creating an Eval Set
41
+
42
+ First, create the directory structure:
43
+
44
+ !mkdir -p evaluations/eval-sets evaluations/evaluators
45
+
46
+ Read the agent's Input/Output schema from entry-points.json to understand the data types.
47
+
48
+ ### Evaluator Selection Guide
49
+
50
+ | If your output is... | Use this evaluator | evaluatorTypeId |
51
+ |---------------------|-------------------|-----------------|
52
+ | Exact string/number | `ExactMatchEvaluator` | `uipath-exact-match` |
53
+ | Contains key phrases | `ContainsEvaluator` | `uipath-contains` |
54
+ | Semantically correct | `LLMJudgeOutputEvaluator` | `uipath-llm-judge-output-semantic-similarity` |
55
+ | JSON with numbers | `JsonSimilarityEvaluator` | `uipath-json-similarity` |
56
+
57
+ ### Step 1: Create Evaluator Config Files
58
+
59
+ **Each evaluator needs a JSON config file** in `evaluations/evaluators/`.
60
+
61
+ **ExactMatchEvaluator** (`evaluations/evaluators/exact-match.json`):
62
+ ```json
63
+ {
64
+ "version": "1.0",
65
+ "id": "ExactMatchEvaluator",
66
+ "name": "ExactMatchEvaluator",
67
+ "description": "Checks for exact output match",
68
+ "evaluatorTypeId": "uipath-exact-match",
69
+ "evaluatorConfig": {
70
+ "name": "ExactMatchEvaluator",
71
+ "targetOutputKey": "*"
72
+ }
73
+ }
74
+ ```
75
+
76
+ **LLMJudgeOutputEvaluator** (`evaluations/evaluators/llm-judge-output.json`):
77
+ ```json
78
+ {
79
+ "version": "1.0",
80
+ "id": "LLMJudgeOutputEvaluator",
81
+ "name": "LLMJudgeOutputEvaluator",
82
+ "description": "Uses LLM to judge semantic similarity",
83
+ "evaluatorTypeId": "uipath-llm-judge-output-semantic-similarity",
84
+ "evaluatorConfig": {
85
+ "name": "LLMJudgeOutputEvaluator",
86
+ "model": "gpt-4o-mini-2024-07-18"
87
+ }
88
+ }
89
+ ```
90
+
91
+ **JsonSimilarityEvaluator** (`evaluations/evaluators/json-similarity.json`):
92
+ ```json
93
+ {
94
+ "version": "1.0",
95
+ "id": "JsonSimilarityEvaluator",
96
+ "name": "JsonSimilarityEvaluator",
97
+ "description": "Compares JSON structures",
98
+ "evaluatorTypeId": "uipath-json-similarity",
99
+ "evaluatorConfig": {
100
+ "name": "JsonSimilarityEvaluator",
101
+ "targetOutputKey": "*"
102
+ }
103
+ }
104
+ ```
105
+
106
+ **ContainsEvaluator** (`evaluations/evaluators/contains.json`):
107
+ ```json
108
+ {
109
+ "version": "1.0",
110
+ "id": "ContainsEvaluator",
111
+ "name": "ContainsEvaluator",
112
+ "description": "Checks if output contains text",
113
+ "evaluatorTypeId": "uipath-contains",
114
+ "evaluatorConfig": {
115
+ "name": "ContainsEvaluator"
116
+ }
117
+ }
118
+ ```
119
+
120
+ ### Step 2: Create Eval Set
121
+
122
+ **Eval Set Template** (`evaluations/eval-sets/default.json`):
123
+ ```json
124
+ {
125
+ "version": "1.0",
126
+ "id": "default-eval-set",
127
+ "name": "Default Evaluation Set",
128
+ "evaluatorRefs": ["ExactMatchEvaluator"],
129
+ "evaluations": [
130
+ {
131
+ "id": "test-1",
132
+ "name": "Test description",
133
+ "inputs": {
134
+ "field": "value"
135
+ },
136
+ "evaluationCriterias": {
137
+ "ExactMatchEvaluator": {
138
+ "expectedOutput": {
139
+ "result": "expected value"
140
+ }
141
+ }
142
+ }
143
+ }
144
+ ]
145
+ }
146
+ ```
147
+
148
+ **Important notes:**
149
+ - `evaluatorRefs` must list ALL evaluators used in any test case
150
+ - Each evaluator in `evaluatorRefs` needs a matching JSON config in `evaluations/evaluators/`
151
+ - `evaluationCriterias` keys must match entries in `evaluatorRefs`
152
+ - Use `expectedOutput` for most evaluators
153
+ - LLM evaluators need `model` in their config. Available models are defined in the SDK's `ChatModels` class (`uipath.platform.chat.ChatModels`):
154
+ - `gpt-4o-mini-2024-07-18` (recommended for cost-efficiency)
155
+ - `gpt-4o-2024-08-06` (higher quality, higher cost)
156
+ - `o3-mini-2025-01-31` (latest reasoning model)
157
+ - Model availability varies by region and tenant configuration
158
+ - Check your UiPath Automation Cloud portal under AI Trust Layer for available models in your region
159
+
160
+ ---
161
+
162
+ ## Adding a Test Case
163
+
164
+ When adding a test to an existing eval set:
165
+
166
+ 1. Read the existing eval set
167
+ 2. Check which evaluators are in `evaluatorRefs`
168
+ 3. Add the new test to `evaluations` array
169
+ 4. If using a new evaluator, add it to `evaluatorRefs`
170
+
171
+ ### Test Case Template
172
+
173
+ ```json
174
+ {
175
+ "id": "test-{n}",
176
+ "name": "Description of what this tests",
177
+ "inputs": { },
178
+ "evaluationCriterias": {
179
+ "EvaluatorName": {
180
+ "expectedOutput": { }
181
+ }
182
+ }
183
+ }
184
+ ```
185
+
186
+ ---
187
+
188
+ ## Running Evaluations
189
+
190
+ First, read entry-points.json to get the entrypoint name (e.g., `main`):
191
+
192
+ !uv run uipath eval main evaluations/eval-sets/default.json --output-file eval-results.json
193
+
194
+ **Note:** Replace `main` with your actual entrypoint from entry-points.json.
195
+
196
+ ### Analyze Results
197
+
198
+ After running, read `eval-results.json` and show:
199
+ - Pass/fail summary table
200
+ - For failures: expected vs actual output
201
+ - Suggestions for fixing or changing evaluators
202
+
203
+ ### Results Format
204
+
205
+ ```json
206
+ {
207
+ "evaluationSetResults": [{
208
+ "evaluationRunResults": [
209
+ {
210
+ "evaluationId": "test-1",
211
+ "evaluatorId": "ExactMatchEvaluator",
212
+ "result": { "score": 1.0 },
213
+ "errorMessage": null
214
+ }
215
+ ]
216
+ }]
217
+ }
218
+ ```
219
+
220
+ - Score 1.0 = PASS
221
+ - Score < 1.0 = FAIL (show expected vs actual)
222
+ - errorMessage present = ERROR (show message)
223
+
224
+ ---
225
+
226
+ ## Evaluator Reference
227
+
228
+ ### Deterministic Evaluators
229
+
230
+ **ExactMatchEvaluator** - Exact output matching
231
+ ```json
232
+ "ExactMatchEvaluator": {
233
+ "expectedOutput": { "result": "exact value" }
234
+ }
235
+ ```
236
+
237
+ **ContainsEvaluator** - Output contains substring
238
+ ```json
239
+ "ContainsEvaluator": {
240
+ "searchText": "must contain this"
241
+ }
242
+ ```
243
+
244
+ **JsonSimilarityEvaluator** - JSON comparison with tolerance
245
+ ```json
246
+ "JsonSimilarityEvaluator": {
247
+ "expectedOutput": { "value": 10.0 }
248
+ }
249
+ ```
250
+
251
+ ### LLM-Based Evaluators
252
+
253
+ **LLMJudgeOutputEvaluator** - Semantic correctness
254
+ ```json
255
+ "LLMJudgeOutputEvaluator": {
256
+ "expectedOutput": { "summary": "Expected semantic meaning" }
257
+ }
258
+ ```
259
+
260
+ **LLMJudgeTrajectoryEvaluator** - Validate agent reasoning
261
+ ```json
262
+ "LLMJudgeTrajectoryEvaluator": {
263
+ "expectedAgentBehavior": "The agent should first fetch data, then process it"
264
+ }
265
+ ```
266
+
267
+ ---
268
+
269
+ ## Common Issues
270
+
271
+ ### "No evaluations found"
272
+ - Check `evaluations/eval-sets/` directory exists
273
+ - Verify JSON file is valid
274
+
275
+ ### Evaluator not found
276
+ - Each evaluator needs a JSON config file in `evaluations/evaluators/`
277
+ - Config file must have correct `evaluatorTypeId` (see templates above)
278
+ - Config file must have `name` field at root level
279
+ - LLM evaluators need `model` in `evaluatorConfig`
280
+
281
+ ### Evaluator skipped
282
+ - Ensure evaluator is listed in root `evaluatorRefs` array
283
+ - Check evaluator config file exists in `evaluations/evaluators/`
284
+
285
+ ### Schema mismatch
286
+ - Run `uv run uipath init --no-agents-md-override` to refresh schemas
287
+ - Check `entry-points.json` matches your Input/Output models
agents/agent_1_triage_hitl/.claude/commands/new-agent.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ allowed-tools: Bash, Read, Write, Edit, Glob
3
+ description: Create a new UiPath coded agent from a description
4
+ ---
5
+
6
+ I'll help you create a new UiPath coded agent.
7
+
8
+ ## Step 1: Check existing project
9
+
10
+ Let me check if this is an existing UiPath project:
11
+
12
+ !ls uipath.json main.py 2>/dev/null || echo "NEW_PROJECT"
13
+
14
+ ## Step 2: Gather requirements
15
+
16
+ **What should this agent do?**
17
+
18
+ Please describe:
19
+
20
+ - What inputs it needs (e.g., "a file path and bucket name")
21
+ - What it should accomplish (e.g., "process CSV data")
22
+ - What outputs it should return (e.g., "total count and status")
23
+
24
+ I'll generate the agent structure based on your description.
25
+
26
+ ## Step 3: Generate agent
27
+
28
+ After you describe the agent, I will:
29
+
30
+ 1. Create `main.py` with Input/Output Pydantic models and `async def main()`
31
+ 2. Add entrypoint to `uipath.json` under `"functions": {"agent_name": "main.py:main"}`
32
+ 3. Run `uv run uipath init --no-agents-md-override` to generate schemas
33
+
34
+ **Template structure** (from .agent/REQUIRED_STRUCTURE.md):
35
+
36
+ ```python
37
+ from pydantic import BaseModel
38
+ from uipath.platform import UiPath
39
+
40
+ class Input(BaseModel):
41
+ """Input fields for the agent."""
42
+ # Fields based on your description
43
+ pass
44
+
45
+
46
+ class Output(BaseModel):
47
+ """Output fields returned by the agent."""
48
+ # Fields based on your description
49
+ pass
50
+
51
+
52
+ async def main(input: Input) -> Output:
53
+ """Main entry point for the agent.
54
+
55
+ Args:
56
+ input: The input data for the agent.
57
+
58
+ Returns:
59
+ The output data from the agent.
60
+ """
61
+
62
+ uipath = UiPath()
63
+
64
+ # TODO: Implement agent logic
65
+ return Output()
66
+ ```
67
+
68
+ **Important notes:**
69
+
70
+ - Use `async def main` - many SDK methods are async
71
+ - Initialize `UiPath()` inside the function, not at module level
72
+ - After creating main.py, add entrypoint to `uipath.json` under `"functions"`
73
+
74
+ ## Step 4: Update entry-point schemas
75
+
76
+ After creating main.py, regenerate the schemas:
77
+
78
+ !uv run uipath init --no-agents-md-override
79
+
80
+ ## Step 5: Verify
81
+
82
+ Quick test to verify the setup:
83
+
84
+ !uv run uipath run main '{}' 2>&1 | head -30
85
+
86
+ ## Summary
87
+
88
+ Once complete, you'll have:
89
+
90
+ | File | Purpose |
91
+ | ------------------- | ----------------------------------- |
92
+ | `main.py` | Agent code with Input/Output models |
93
+ | `uipath.json` | Project configuration |
94
+ | `entry-points.json` | Entry point schemas |
95
+ | `bindings.json` | Resource bindings |
96
+ | `.agent/` | SDK and CLI reference docs |
97
+
98
+ **Next steps:**
99
+
100
+ 1. Implement your logic in `main()`
101
+ 2. Test: `uv run uipath run main '{"field": "value"}'`
102
+ 3. Create `eval_set.json` for evaluations
103
+ 4. Evaluate: `uv run uipath eval`
agents/agent_1_triage_hitl/.env ADDED
File without changes
agents/agent_1_triage_hitl/.uipath/.telemetry.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "ProjectKey": "a228c0d2-8c19-4dd2-9e8b-4fa9592e88e3"
3
+ }
agents/agent_1_triage_hitl/.uipath/studio_metadata.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "schemaVersion": 1,
3
+ "codeVersion": "1.0.0"
4
+ }
agents/agent_1_triage_hitl/AGENTS.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Agent Code Patterns Reference
2
+
3
+ This document provides practical code patterns for building UiPath coded agents using LangGraph and the UiPath Python SDK.
4
+
5
+ ---
6
+
7
+ ## Documentation Structure
8
+
9
+ This documentation is split into multiple files for efficient context loading. Load only the files you need:
10
+
11
+ 1. **@.agent/REQUIRED_STRUCTURE.md** - Agent structure patterns and templates
12
+ - **When to load:** Creating a new agent or understanding required patterns
13
+ - **Contains:** Required Pydantic models (Input, State, Output), LLM initialization patterns, standard agent template
14
+
15
+ 2. **@.agent/SDK_REFERENCE.md** - Complete SDK API reference
16
+ - **When to load:** Calling UiPath SDK methods, working with services (actions, assets, jobs, etc.)
17
+ - **Contains:** All SDK services and methods with full signatures and type annotations
18
+
19
+ 3. **@.agent/CLI_REFERENCE.md** - CLI commands documentation
20
+ - **When to load:** Working with `uipath init`, `uipath run`, or `uipath eval` commands
21
+ - **Contains:** Command syntax, options, usage examples, and workflows
agents/agent_1_triage_hitl/CLAUDE.md ADDED
@@ -0,0 +1 @@
 
 
1
+ @AGENTS.md
agents/agent_1_triage_hitl/__pycache__/main.cpython-313.pyc ADDED
Binary file (3.55 kB). View file
 
agents/agent_1_triage_hitl/__pycache__/main.cpython-314.pyc ADDED
Binary file (4.18 kB). View file
 
agents/agent_1_triage_hitl/__uipath/state.db ADDED
Binary file (20.5 kB). View file
 
agents/agent_1_triage_hitl/agent.mermaid ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ %% AUTO-GENERATED by `uipath init`. Do not edit manually.
2
+ %% Regenerated on every `uipath init`.
3
+ flowchart TB
4
+ __start__(__start__)
5
+ triage(triage)
6
+ __end__(__end__)
7
+ __start__ --> triage
8
+ triage --> __end__
agents/agent_1_triage_hitl/bindings.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "version": "2.0",
3
+ "resources": []
4
+ }
agents/agent_1_triage_hitl/entry-points.json ADDED
@@ -0,0 +1,87 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "$schema": "https://cloud.uipath.com/draft/2024-12/entry-point",
3
+ "$id": "entry-points.json",
4
+ "entryPoints": [
5
+ {
6
+ "filePath": "agent",
7
+ "uniqueId": "458f06d3-9709-4a94-a776-85c8edcd30c4",
8
+ "type": "agent",
9
+ "input": {
10
+ "type": "object",
11
+ "properties": {
12
+ "case_id": {
13
+ "description": "The unique case ID from Maestro.",
14
+ "title": "Case Id",
15
+ "type": "string"
16
+ },
17
+ "risk_score": {
18
+ "description": "The calculated risk score (0-100).",
19
+ "title": "Risk Score",
20
+ "type": "integer"
21
+ },
22
+ "context_data": {
23
+ "additionalProperties": true,
24
+ "description": "The transaction context and entity data.",
25
+ "title": "Context Data",
26
+ "type": "object"
27
+ }
28
+ },
29
+ "required": [
30
+ "case_id",
31
+ "risk_score",
32
+ "context_data"
33
+ ]
34
+ },
35
+ "output": {
36
+ "type": "object",
37
+ "properties": {
38
+ "approval_status": {
39
+ "description": "The decision from the human reviewer: 'approved', 'rejected', or 'escalated'.",
40
+ "title": "Approval Status",
41
+ "type": "string"
42
+ }
43
+ },
44
+ "required": [
45
+ "approval_status"
46
+ ]
47
+ },
48
+ "graph": {
49
+ "nodes": [
50
+ {
51
+ "id": "__start__",
52
+ "name": "__start__",
53
+ "type": "__start__",
54
+ "subgraph": null,
55
+ "metadata": {}
56
+ },
57
+ {
58
+ "id": "triage",
59
+ "name": "triage",
60
+ "type": "node",
61
+ "subgraph": null,
62
+ "metadata": {}
63
+ },
64
+ {
65
+ "id": "__end__",
66
+ "name": "__end__",
67
+ "type": "__end__",
68
+ "subgraph": null,
69
+ "metadata": {}
70
+ }
71
+ ],
72
+ "edges": [
73
+ {
74
+ "source": "__start__",
75
+ "target": "triage",
76
+ "label": null
77
+ },
78
+ {
79
+ "source": "triage",
80
+ "target": "__end__",
81
+ "label": null
82
+ }
83
+ ]
84
+ }
85
+ }
86
+ ]
87
+ }
agents/agent_1_triage_hitl/langgraph.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "graphs": {
3
+ "agent": "./main.py:compiled_graph"
4
+ }
5
+ }
agents/agent_1_triage_hitl/main.mermaid ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ %% AUTO-GENERATED by `uipath init`. Do not edit manually.
2
+ %% Regenerated on every `uipath init`.
3
+ flowchart TB
4
+ main.py:55(main)
agents/agent_1_triage_hitl/main.py ADDED
@@ -0,0 +1,75 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ from typing import TypedDict
2
+ from langgraph.graph import StateGraph, START, END
3
+ from langgraph.types import Command, interrupt
4
+ from pydantic import BaseModel, Field
5
+ import datetime
6
+
7
+
8
+ class InvestigationState(TypedDict):
9
+ case_id: str
10
+ risk_score: int
11
+ context_data: dict
12
+ approval_status: str
13
+
14
+
15
+ class Input(BaseModel):
16
+ case_id: str = Field(description="The unique case ID from Maestro.")
17
+ risk_score: int = Field(description="The calculated risk score (0-100).")
18
+ context_data: dict = Field(description="The transaction context and entity data.")
19
+
20
+
21
+ class Output(BaseModel):
22
+ approval_status: str = Field(
23
+ description="The decision from the human reviewer: 'approved', 'rejected', or 'escalated'."
24
+ )
25
+
26
+
27
+ def triage_node(state: InvestigationState) -> Command:
28
+ """
29
+ Gate 1: AML Analyst Triage Review.
30
+
31
+ Uses LangGraph interrupt() to pause execution and suspend the Orchestrator job.
32
+ The analyst sees the full case context in the Orchestrator UI and resumes the
33
+ job with their decision. This is the API Trigger HITL pattern.
34
+
35
+ Resume the job with: {'status': 'approved'} | {'status': 'rejected'} | {'status': 'escalated'}
36
+ """
37
+ risk = state["risk_score"]
38
+ severity = "HIGH" if risk >= 75 else "MEDIUM" if risk >= 40 else "LOW"
39
+
40
+ resume_payload = interrupt({
41
+ "gate": "Gate 1 — AML Analyst Triage Review",
42
+ "case_id": state["case_id"],
43
+ "risk_score": risk,
44
+ "risk_severity": severity,
45
+ "context_summary": state.get("context_data", {}),
46
+ "timestamp_utc": str(datetime.datetime.utcnow().isoformat()),
47
+ "instructions": (
48
+ f"Case {state['case_id']} has been flagged with risk score {risk}/100 ({severity}). "
49
+ "Review the context data above. Resume this job with "
50
+ "{'status': 'approved'} to proceed to full investigation, "
51
+ "{'status': 'rejected'} to close the case, or "
52
+ "{'status': 'escalated'} to escalate to senior analyst."
53
+ )
54
+ })
55
+
56
+ import json
57
+ if isinstance(resume_payload, str):
58
+ try:
59
+ resume_payload = json.loads(resume_payload)
60
+ except Exception:
61
+ resume_payload = {"status": resume_payload}
62
+
63
+ if isinstance(resume_payload, dict):
64
+ decision = resume_payload.get("status", "approved")
65
+ else:
66
+ decision = "approved"
67
+
68
+ return {"approval_status": decision}
69
+
70
+
71
+ workflow = StateGraph(InvestigationState, input_schema=Input, output_schema=Output)
72
+ workflow.add_node("triage", triage_node)
73
+ workflow.add_edge(START, "triage")
74
+ workflow.add_edge("triage", END)
75
+ compiled_graph = workflow.compile()
agents/agent_1_triage_hitl/project.uiproj ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "ProjectType": "Agent",
3
+ "Name": "agent_1_triage",
4
+ "Description": "agent_1_triage_hitl",
5
+ "MainFile": null
6
+ }
agents/agent_1_triage_hitl/pyproject.toml ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [project]
2
+ name = "agent_1_triage"
3
+ version = "0.0.2"
4
+ description = "agent_1_triage_hitl"
5
+ authors = [{ name = "John Doe", email = "john.doe@myemail.com" }]
6
+ dependencies = [
7
+ "langgraph>=1.2.6",
8
+ "uipath>=2.10.0, <2.11.0",
9
+ "uipath-core>=0.5.19",
10
+ "uipath-langchain>=0.12.2",
11
+ ]
12
+ requires-python = ">=3.11"
agents/agent_1_triage_hitl/uipath.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "functions": {
3
+ "compiled_graph": "main.py:compiled_graph"
4
+ },
5
+ "id": "dc030ac9-5926-49f9-9f96-bd93277e44be"
6
+ }
agents/agent_1_triage_hitl/uv.lock ADDED
The diff for this file is too large to render. See raw diff
 
agents/agent_2_investigation_api/.agent/CLI_REFERENCE.md ADDED
@@ -0,0 +1,949 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## CLI Commands Reference
2
+
3
+ The UiPath Python SDK provides a comprehensive CLI for managing coded agents and automation projects. All commands should be executed with `uv run uipath <command>`.
4
+
5
+ ### Command Overview
6
+
7
+ | Command | Purpose | When to Use |
8
+ |---------|---------|-------------|
9
+ | `init` | Initialize agent project | Creating a new agent or updating schema |
10
+ | `run` | Execute agent | Running agent locally or testing |
11
+ | `eval` | Evaluate agent | Testing agent performance with evaluation sets |
12
+
13
+ ---
14
+
15
+ ### `uipath init`
16
+
17
+ **Description:** Initialize the project.
18
+
19
+ **Options:**
20
+
21
+ | Option | Type | Default | Description |
22
+ |--------|------|---------|-------------|
23
+ | `--no-agents-md-override` | flag | false | Won't override existing .agent files and AGENTS.md file. |
24
+
25
+ **Usage Examples:**
26
+
27
+ ```bash
28
+ # Initialize a new agent project
29
+ uv run uipath init
30
+
31
+ # Initialize with specific entrypoint
32
+ uv run uipath init main.py
33
+
34
+ # Initialize and infer bindings from code
35
+ uv run uipath init --infer-bindings
36
+ ```
37
+
38
+ **When to use:** Run this command when you've modified the Input/Output models and need to regenerate the `uipath.json` schema file.
39
+
40
+ ---
41
+
42
+ ### `uipath run`
43
+
44
+ **Description:** Execute the project.
45
+
46
+ **Arguments:**
47
+
48
+ | Argument | Required | Description |
49
+ |----------|----------|-------------|
50
+ | `entrypoint` | No | N/A |
51
+ | `input` | No | N/A |
52
+
53
+ **Options:**
54
+
55
+ | Option | Type | Default | Description |
56
+ |--------|------|---------|-------------|
57
+ | `--resume` | flag | false | Resume execution from a previous state |
58
+ | `-f`, `--file` | value | `Sentinel.UNSET` | File path for the .json input |
59
+ | `--input-file` | value | `Sentinel.UNSET` | Alias for '-f/--file' arguments |
60
+ | `--output-file` | value | `Sentinel.UNSET` | File path where the output will be written |
61
+ | `--trace-file` | value | `Sentinel.UNSET` | File path where the trace spans will be written (JSON Lines format) |
62
+ | `--state-file` | value | `Sentinel.UNSET` | File path where the state file is stored for persisting execution state. If not provided, a temporary file will be used. |
63
+ | `--debug` | flag | false | Enable debugging with debugpy. The process will wait for a debugger to attach. |
64
+ | `--debug-port` | value | `5678` | Port for the debug server (default: 5678) |
65
+ | `--keep-state-file` | flag | false | Keep the temporary state file even when not resuming and no job id is provided |
66
+ | `--simulation` | value | none | Simulation config as a JSON object (same schema as simulation.json) |
67
+
68
+ **Usage Examples:**
69
+
70
+ ```bash
71
+ # Run agent with inline JSON input
72
+ uv run uipath run main.py '{"query": "What is the weather?"}'
73
+
74
+ # Run agent with input from file
75
+ uv run uipath run main.py --file input.json
76
+
77
+ # Run agent and save output to file
78
+ uv run uipath run agent '{"task": "Process data"}' --output-file result.json
79
+
80
+ # Run agent with debugging enabled
81
+ uv run uipath run main.py '{"input": "test"}' --debug --debug-port 5678
82
+
83
+ # Resume agent execution from previous state
84
+ uv run uipath run --resume
85
+ ```
86
+
87
+ **When to use:** Run this command to execute your agent locally for development, testing, or debugging. Use `--debug` flag to attach a debugger for step-by-step debugging.
88
+
89
+ ---
90
+
91
+ ### `uipath eval`
92
+
93
+ **Description:** Run an evaluation set against the agent.
94
+
95
+ Args:
96
+ entrypoint: Path to the agent script to evaluate (optional, will auto-discover if not specified)
97
+ eval_set: Path to the evaluation set JSON file (optional, will auto-discover if not specified)
98
+ eval_ids: Optional list of evaluation IDs
99
+ eval_set_run_id: Custom evaluation set run ID (optional, will generate UUID if not specified)
100
+ workers: Number of parallel workers for running evaluations
101
+ no_report: Do not report the evaluation results
102
+ enable_mocker_cache: Enable caching for LLM mocker responses
103
+ report_coverage: Report evaluation coverage
104
+ model_settings_id: Model settings ID to override agent settings
105
+ trace_file: File path where traces will be written in JSONL format
106
+ max_llm_concurrency: Maximum concurrent LLM requests
107
+ input_overrides: Input field overrides mapping (direct field override with deep merge)
108
+ resume: Resume execution from a previous suspended state
109
+
110
+
111
+ **Arguments:**
112
+
113
+ | Argument | Required | Description |
114
+ |----------|----------|-------------|
115
+ | `entrypoint` | No | N/A |
116
+ | `eval_set` | No | N/A |
117
+
118
+ **Options:**
119
+
120
+ | Option | Type | Default | Description |
121
+ |--------|------|---------|-------------|
122
+ | `--eval-set-run-id` | value | `Sentinel.UNSET` | Custom evaluation set run ID (if not provided, a UUID will be generated) |
123
+ | `--no-report` | flag | false | Do not report the evaluation results |
124
+ | `--workers` | value | `1` | Number of parallel workers for running evaluations (default: 1) |
125
+ | `--output-file` | value | `Sentinel.UNSET` | File path where the output will be written |
126
+ | `--enable-mocker-cache` | flag | false | Enable caching for LLM mocker responses |
127
+ | `--report-coverage` | flag | false | Report evaluation coverage |
128
+ | `--model-settings-id` | value | `"default"` | Model settings ID from evaluation set to override agent settings (default: 'default') |
129
+ | `--trace-file` | value | `Sentinel.UNSET` | File path where traces will be written in JSONL format |
130
+ | `--max-llm-concurrency` | value | `20` | Maximum concurrent LLM requests (default: 20) |
131
+ | `--resume` | flag | false | Resume execution from a previous suspended state |
132
+ | `--verbose` | flag | false | Include agent execution output (trace, result) in the output file |
133
+
134
+ **Usage Examples:**
135
+
136
+ ```bash
137
+ # Run evaluation with auto-discovered files
138
+ uv run uipath eval
139
+
140
+ # Run evaluation with specific entrypoint and eval set
141
+ uv run uipath eval main.py eval_set.json
142
+
143
+ # Run evaluation without reporting results
144
+ uv run uipath eval --no-report
145
+
146
+ # Run evaluation with custom number of workers
147
+ uv run uipath eval --workers 4
148
+
149
+ # Save evaluation output to file
150
+ uv run uipath eval --output-file eval_results.json
151
+ ```
152
+
153
+ **When to use:** Run this command to test your agent's performance against a predefined evaluation set. This helps validate agent behavior and measure quality metrics.
154
+
155
+ ---
156
+
157
+ ### Common Workflows
158
+
159
+ **1. Creating a New Agent:**
160
+ ```bash
161
+ # Step 1: Initialize project
162
+ uv run uipath init
163
+
164
+ # Step 2: Run agent to test
165
+ uv run uipath run main.py '{"input": "test"}'
166
+
167
+ # Step 3: Evaluate agent performance
168
+ uv run uipath eval
169
+ ```
170
+
171
+ **2. Development & Testing:**
172
+ ```bash
173
+ # Run with debugging
174
+ uv run uipath run main.py '{"input": "test"}' --debug
175
+
176
+ # Test with input file
177
+ uv run uipath run main.py --file test_input.json --output-file test_output.json
178
+ ```
179
+
180
+ **3. Schema Updates:**
181
+ ```bash
182
+ # After modifying Input/Output models, regenerate schema
183
+ uv run uipath init --infer-bindings
184
+ ```
185
+
186
+ ### Configuration File (uipath.json)
187
+
188
+ The `uipath.json` file is automatically generated by `uipath init` and defines your agent's schema and bindings.
189
+
190
+ **Structure:**
191
+
192
+ ```json
193
+ {
194
+ "entryPoints": [
195
+ {
196
+ "filePath": "agent",
197
+ "uniqueId": "uuid-here",
198
+ "type": "agent",
199
+ "input": {
200
+ "type": "object",
201
+ "properties": { ... },
202
+ "description": "Input schema",
203
+ "required": [ ... ]
204
+ },
205
+ "output": {
206
+ "type": "object",
207
+ "properties": { ... },
208
+ "description": "Output schema",
209
+ "required": [ ... ]
210
+ }
211
+ }
212
+ ],
213
+ "bindings": {
214
+ "version": "2.0",
215
+ "resources": []
216
+ }
217
+ }
218
+ ```
219
+
220
+ **When to Update:**
221
+
222
+ 1. **After Modifying Input/Output Models**: Run `uv run uipath init --infer-bindings` to regenerate schemas
223
+ 2. **Changing Entry Point**: Update `filePath` if you rename or move your main file
224
+ 3. **Manual Schema Adjustments**: Edit `input.jsonSchema` or `output.jsonSchema` directly if needed
225
+ 4. **Bindings Updates**: The `bindings` section maps the exported graph variable - update if you rename your graph
226
+
227
+ **Important Notes:**
228
+
229
+ - The `uniqueId` should remain constant for the same agent
230
+ - Always use `type: "agent"` for LangGraph agents
231
+ - The `jsonSchema` must match your Pydantic models exactly
232
+ - Re-run `uipath init --infer-bindings` instead of manual edits when possible
233
+
234
+
235
+ ## Service Commands Reference
236
+
237
+ The UiPath CLI provides commands for interacting with UiPath platform services. These commands allow you to manage buckets, assets, jobs, and other resources.
238
+
239
+ ### `uipath assets`
240
+
241
+ Manage UiPath assets.
242
+
243
+ Assets are key-value pairs that store configuration data, credentials,
244
+ and settings used by automation processes.
245
+
246
+ \b
247
+ Examples:
248
+ # List all assets in a folder
249
+ uipath assets list --folder-path "Shared"
250
+
251
+ # List with filter
252
+ uipath assets list --filter "ValueType eq 'Text'"
253
+
254
+ # List with ordering
255
+ uipath assets list --orderby "Name asc"
256
+
257
+
258
+ **Subcommands:**
259
+
260
+ **`uipath assets list`**
261
+
262
+ List assets in a folder.
263
+
264
+ \b
265
+ Examples:
266
+ uipath assets list
267
+ uipath assets list --folder-path "Shared"
268
+ uipath assets list --filter "ValueType eq 'Text'"
269
+ uipath assets list --filter "Name eq 'MyAsset'"
270
+ uipath assets list --orderby "Name asc"
271
+ uipath assets list --top 50 --skip 100
272
+
273
+
274
+ Options:
275
+ - `--filter`: OData $filter expression (default: `Sentinel.UNSET`)
276
+ - `--orderby`: OData $orderby expression (default: `Sentinel.UNSET`)
277
+ - `--top`: Maximum number of items to return (default: 100, max: 1000) (default: `100`)
278
+ - `--skip`: Number of items to skip (default: `0`)
279
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
280
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
281
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
282
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
283
+
284
+ ---
285
+
286
+ ### `uipath buckets`
287
+
288
+ Manage UiPath storage buckets and files.
289
+
290
+ Buckets are cloud storage containers for files used by automation processes.
291
+
292
+ 
293
+ Bucket Operations:
294
+ list - List all buckets
295
+ create - Create a new bucket
296
+ delete - Delete a bucket
297
+ retrieve - Get bucket details
298
+ exists - Check if bucket exists
299
+
300
+ 
301
+ File Operations (use 'buckets files' subcommand):
302
+ files list - List files in a bucket
303
+ files search - Search files using glob patterns
304
+ files upload - Upload a file to a bucket
305
+ files download - Download a file from a bucket
306
+ files delete - Delete a file from a bucket
307
+ files exists - Check if a file exists
308
+
309
+ 
310
+ Examples:
311
+ 
312
+ # Bucket operations with explicit folder
313
+ uipath buckets list --folder-path "Shared"
314
+ uipath buckets create my-bucket --description "Data storage"
315
+ uipath buckets exists my-bucket
316
+ uipath buckets delete my-bucket --confirm
317
+ 
318
+ # Using environment variable for folder context
319
+ export UIPATH_FOLDER_PATH="Shared"
320
+ uipath buckets list
321
+ uipath buckets create my-bucket --description "Data storage"
322
+ 
323
+ # File operations
324
+ uipath buckets files list my-bucket
325
+ uipath buckets files search my-bucket "*.pdf"
326
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
327
+ uipath buckets files download my-bucket data.csv ./local.csv
328
+ uipath buckets files delete my-bucket old-data.csv --confirm
329
+ uipath buckets files exists my-bucket data.csv
330
+
331
+
332
+ **Subcommands:**
333
+
334
+ **`uipath buckets create`**
335
+
336
+ Create a new Bucket.
337
+
338
+ Examples:
339
+ uipath buckets create my-resource
340
+ uipath buckets create my-resource --folder-path Shared
341
+
342
+
343
+ Arguments:
344
+ - `name` (required): N/A
345
+
346
+ Options:
347
+ - `--description`: Bucket description
348
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
349
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
350
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
351
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
352
+
353
+ **`uipath buckets delete`**
354
+
355
+ Delete a bucket.
356
+
357
+ 
358
+ Examples:
359
+ uipath buckets delete my-bucket --confirm
360
+ uipath buckets delete my-bucket --dry-run
361
+
362
+
363
+ Arguments:
364
+ - `name` (required): N/A
365
+
366
+ Options:
367
+ - `--confirm`: Skip confirmation prompt
368
+ - `--dry-run`: Show what would be deleted without deleting
369
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
370
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
371
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
372
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
373
+
374
+ **`uipath buckets exists`**
375
+
376
+ Check if a Bucket exists.
377
+
378
+ Examples:
379
+ uipath buckets exists my-resource
380
+ uipath buckets exists my-resource --folder-path Shared
381
+
382
+
383
+ Arguments:
384
+ - `name` (required): N/A
385
+
386
+ Options:
387
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
388
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
389
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
390
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
391
+
392
+ #### `uipath buckets files`
393
+
394
+ Manage files within buckets.
395
+
396
+ 
397
+ Examples:
398
+ 
399
+ # List files in a bucket
400
+ uipath buckets files list my-bucket
401
+ 
402
+ # Search for files with glob pattern
403
+ uipath buckets files search my-bucket "*.pdf"
404
+ 
405
+ # Upload a file
406
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
407
+ 
408
+ # Download a file
409
+ uipath buckets files download my-bucket data.csv ./local.csv
410
+ 
411
+ # Delete a file
412
+ uipath buckets files delete my-bucket old-data.csv --confirm
413
+ 
414
+ # Check if file exists
415
+ uipath buckets files exists my-bucket data.csv
416
+
417
+
418
+ **`uipath buckets files delete`**
419
+
420
+ Delete a file from a bucket.
421
+
422
+ 
423
+ Arguments:
424
+ BUCKET_NAME: Name of the bucket
425
+ FILE_PATH: Path to file in bucket
426
+
427
+ 
428
+ Examples:
429
+ uipath buckets files delete my-bucket old-data.csv --confirm
430
+ uipath buckets files delete reports archive/old.pdf --dry-run
431
+
432
+
433
+ Arguments:
434
+ - `bucket_name` (required): N/A
435
+ - `file_path` (required): N/A
436
+
437
+ Options:
438
+ - `--confirm`: Skip confirmation prompt
439
+ - `--dry-run`: Show what would be deleted
440
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
441
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
442
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
443
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
444
+
445
+ **`uipath buckets files download`**
446
+
447
+ Download a file from a bucket.
448
+
449
+ 
450
+ Arguments:
451
+ BUCKET_NAME: Name of the bucket
452
+ REMOTE_PATH: Path to file in bucket
453
+ LOCAL_PATH: Local destination path
454
+
455
+ 
456
+ Examples:
457
+ uipath buckets files download my-bucket data.csv ./downloads/data.csv
458
+ uipath buckets files download reports monthly/report.pdf ./report.pdf
459
+
460
+
461
+ Arguments:
462
+ - `bucket_name` (required): N/A
463
+ - `remote_path` (required): N/A
464
+ - `local_path` (required): N/A
465
+
466
+ Options:
467
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
468
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
469
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
470
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
471
+
472
+ **`uipath buckets files exists`**
473
+
474
+ Check if a file exists in a bucket.
475
+
476
+ 
477
+ Arguments:
478
+ BUCKET_NAME: Name of the bucket
479
+ FILE_PATH: Path to file in bucket
480
+
481
+ 
482
+ Examples:
483
+ uipath buckets files exists my-bucket data.csv
484
+ uipath buckets files exists reports monthly/report.pdf
485
+
486
+
487
+ Arguments:
488
+ - `bucket_name` (required): N/A
489
+ - `file_path` (required): N/A
490
+
491
+ Options:
492
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
493
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
494
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
495
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
496
+
497
+ **`uipath buckets files list`**
498
+
499
+ List files in a bucket.
500
+
501
+ 
502
+ Arguments:
503
+ BUCKET_NAME: Name of the bucket
504
+
505
+ 
506
+ Examples:
507
+ uipath buckets files list my-bucket
508
+ uipath buckets files list my-bucket --prefix "data/"
509
+ uipath buckets files list reports --limit 10 --format json
510
+ uipath buckets files list my-bucket --all
511
+
512
+
513
+ Arguments:
514
+ - `bucket_name` (required): N/A
515
+
516
+ Options:
517
+ - `--prefix`: Filter files by prefix (default: ``)
518
+ - `--limit`: Maximum number of files to return (default: `Sentinel.UNSET`)
519
+ - `--offset`: Number of files to skip (default: `0`)
520
+ - `--all`: Fetch all files (auto-paginate)
521
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
522
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
523
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
524
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
525
+
526
+ **`uipath buckets files search`**
527
+
528
+ Search for files using glob patterns.
529
+
530
+ Uses the GetFiles API which supports glob patterns like *.pdf or data_*.csv.
531
+
532
+ 
533
+ Arguments:
534
+ BUCKET_NAME: Name of the bucket
535
+ PATTERN: Glob pattern to match files (e.g., "*.pdf", "data_*.csv")
536
+
537
+ 
538
+ Examples:
539
+ uipath buckets files search my-bucket "*.pdf"
540
+ uipath buckets files search reports "*.csv" --recursive
541
+ uipath buckets files search my-bucket "data_*.json" --prefix "archive/"
542
+
543
+
544
+ Arguments:
545
+ - `bucket_name` (required): N/A
546
+ - `pattern` (required): N/A
547
+
548
+ Options:
549
+ - `--prefix`: Directory path to search in (default: ``)
550
+ - `--recursive`: Search subdirectories recursively
551
+ - `--limit`: Maximum number of files to return (default: `Sentinel.UNSET`)
552
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
553
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
554
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
555
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
556
+
557
+ **`uipath buckets files upload`**
558
+
559
+ Upload a file to a bucket.
560
+
561
+ 
562
+ Arguments:
563
+ BUCKET_NAME: Name of the bucket
564
+ LOCAL_PATH: Local file to upload
565
+ REMOTE_PATH: Destination path in bucket
566
+
567
+ 
568
+ Examples:
569
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
570
+ uipath buckets files upload reports ./report.pdf monthly/report.pdf
571
+
572
+
573
+ Arguments:
574
+ - `bucket_name` (required): N/A
575
+ - `local_path` (required): N/A
576
+ - `remote_path` (required): N/A
577
+
578
+ Options:
579
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
580
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
581
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
582
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
583
+
584
+ **`uipath buckets list`**
585
+
586
+ List all Buckets.
587
+
588
+ Examples:
589
+ uipath buckets list
590
+ uipath buckets list --folder-path Shared
591
+
592
+
593
+ Options:
594
+ - `--limit`: Maximum number of items to return (default: `Sentinel.UNSET`)
595
+ - `--offset`: Number of items to skip (default: `0`)
596
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
597
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
598
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
599
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
600
+
601
+ **`uipath buckets retrieve`**
602
+
603
+ Retrieve a bucket by name or key.
604
+
605
+ 
606
+ Examples:
607
+ uipath buckets retrieve --name "my-bucket"
608
+ uipath buckets retrieve --key "abc-123-def-456" --format json
609
+
610
+
611
+ Options:
612
+ - `--name`: Bucket name (default: `Sentinel.UNSET`)
613
+ - `--key`: Bucket key (UUID) (default: `Sentinel.UNSET`)
614
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
615
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
616
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
617
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
618
+
619
+ ---
620
+
621
+ ### `uipath context-grounding`
622
+
623
+ Manage UiPath Context Grounding indexes.
624
+
625
+ Context Grounding indexes store and search contextual information
626
+ used to enhance AI-enabled automation processes.
627
+
628
+ 
629
+ Two index types:
630
+ Regular - Persistent, backed by bucket or connection, created via 'create'
631
+ Ephemeral - Temporary, no Orchestrator folder, created from local files via 'create-ephemeral'
632
+
633
+ 
634
+ Examples:
635
+ uipath context-grounding list --folder-path "Shared"
636
+
637
+
638
+ **Subcommands:**
639
+
640
+ #### `uipath context-grounding batch-transform`
641
+
642
+ Manage Batch Transform tasks.
643
+
644
+ Batch Transform processes and transforms CSV files from context
645
+ grounding indexes.
646
+
647
+ 
648
+ Examples:
649
+ uipath context-grounding batch-transform start --help
650
+
651
+
652
+ **`uipath context-grounding batch-transform download`**
653
+
654
+ Download a Batch Transform result file.
655
+
656
+ 
657
+ Examples:
658
+ uipath context-grounding batch-transform download --task-id abc-123 --output-file result.csv
659
+
660
+
661
+ Options:
662
+ - `--task-id`: ID of the Batch Transform task (default: `Sentinel.UNSET`)
663
+ - `--output-file`: Local destination path for the result file (default: `Sentinel.UNSET`)
664
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
665
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
666
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
667
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
668
+
669
+ **`uipath context-grounding batch-transform retrieve`**
670
+
671
+ Retrieve a Batch Transform task status.
672
+
673
+ 
674
+ Examples:
675
+ uipath context-grounding batch-transform retrieve --task-id abc-123-def-456
676
+
677
+
678
+ Options:
679
+ - `--task-id`: ID of the Batch Transform task (default: `Sentinel.UNSET`)
680
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
681
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
682
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
683
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
684
+
685
+ **`uipath context-grounding batch-transform start`**
686
+
687
+ Start a Batch Transform task on an index.
688
+
689
+ The index must contain CSV files. Only one file is processed per task.
690
+
691
+ 
692
+ Two ways to specify the index:
693
+ Regular index: --index-name + --folder-path
694
+ Ephemeral index: --index-id
695
+
696
+ 
697
+ --columns-file is a JSON array defining output columns:
698
+ [
699
+ {"name": "entity", "description": "Extracted entity name"},
700
+ {"name": "category", "description": "Entity category"}
701
+ ]
702
+
703
+ 
704
+ Examples:
705
+ uipath context-grounding batch-transform start --index-name my-index --task-name my-task --prompt "Extract" --columns-file cols.json
706
+ uipath context-grounding batch-transform start --index-id abc-123 --task-name my-task --prompt "Extract" --columns-file cols.json
707
+
708
+
709
+ Options:
710
+ - `--index-name`: Name of the context grounding index (default: `Sentinel.UNSET`)
711
+ - `--index-id`: ID of the context grounding index (ephemeral indexes only) (default: `Sentinel.UNSET`)
712
+ - `--task-name`: Name for the Batch Transform task (default: `Sentinel.UNSET`)
713
+ - `--prompt`: Task prompt describing what to process (default: `Sentinel.UNSET`)
714
+ - `--columns-file`: JSON file defining output columns (see format above) (default: `Sentinel.UNSET`)
715
+ - `--target-file`: Specific file name to target in the index (default: `Sentinel.UNSET`)
716
+ - `--prefix`: Storage bucket folder path prefix for filtering files (default: `Sentinel.UNSET`)
717
+ - `--web-search`: Enable web search grounding
718
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
719
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
720
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
721
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
722
+
723
+ **`uipath context-grounding create`**
724
+
725
+ Create a new context grounding index (persistent).
726
+
727
+ The created index lives in an Orchestrator folder. Ingestion must be
728
+ triggered separately after creation.
729
+
730
+ 
731
+ Two ways to specify the data source:
732
+ --bucket-source Bucket name for bucket-backed indexes
733
+ --source-file JSON file for connections (use 'source-schema' to see formats)
734
+
735
+ 
736
+ Examples:
737
+ uipath context-grounding create --index-name my-index --bucket-source my-bucket
738
+ uipath context-grounding create --index-name my-index --source-file config.json
739
+
740
+
741
+ Options:
742
+ - `--index-name`: Name of the index to create (default: `Sentinel.UNSET`)
743
+ - `--source-file`: JSON file with connection source configuration (Google Drive, OneDrive, Dropbox, Confluence) (default: `Sentinel.UNSET`)
744
+ - `--bucket-source`: Bucket name for bucket-backed indexes (default: `Sentinel.UNSET`)
745
+ - `--description`: Description of the index (default: ``)
746
+ - `--extraction-strategy`: Extraction strategy (default: LLMV4) (default: `LLMV4`)
747
+ - `--file-type`: File type filter (e.g., 'pdf', 'txt') (default: `Sentinel.UNSET`)
748
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
749
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
750
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
751
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
752
+
753
+ **`uipath context-grounding create-ephemeral`**
754
+
755
+ Create an ephemeral index from local files (temporary).
756
+
757
+ Uploads files as attachments and creates a temporary index. Reference it
758
+ in other commands with --index-id (no folder, no name). Ingestion starts
759
+ automatically. Poll with 'retrieve --index-id <id>' until
760
+ lastIngestionStatus is Successful before starting a task.
761
+
762
+ 
763
+ Supported file types:
764
+ DeepRAG: PDF, TXT
765
+ BatchRAG: CSV
766
+
767
+ 
768
+ Examples:
769
+ uipath context-grounding create-ephemeral --usage DeepRAG --files doc1.pdf --files doc2.pdf
770
+ uipath context-grounding create-ephemeral --usage BatchRAG --files data.csv
771
+
772
+
773
+ Options:
774
+ - `--usage`: Task type for the ephemeral index (default: `Sentinel.UNSET`)
775
+ - `--files`: Local file paths to upload as attachments (repeatable) (default: `Sentinel.UNSET`)
776
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
777
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
778
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
779
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
780
+
781
+ #### `uipath context-grounding deep-rag`
782
+
783
+ Manage Deep RAG tasks.
784
+
785
+ Deep RAG performs multi-document research and synthesis on context
786
+ grounding indexes.
787
+
788
+ 
789
+ Examples:
790
+ uipath context-grounding deep-rag start --help
791
+
792
+
793
+ **`uipath context-grounding deep-rag retrieve`**
794
+
795
+ Retrieve a Deep RAG task result (status, summary, citations).
796
+
797
+ 
798
+ Examples:
799
+ uipath context-grounding deep-rag retrieve --task-id abc-123-def-456
800
+
801
+
802
+ Options:
803
+ - `--task-id`: ID of the Deep RAG task (default: `Sentinel.UNSET`)
804
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
805
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
806
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
807
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
808
+
809
+ **`uipath context-grounding deep-rag start`**
810
+
811
+ Start a Deep RAG task on an index.
812
+
813
+ 
814
+ Two ways to specify the index:
815
+ Regular index: --index-name + --folder-path
816
+ Ephemeral index: --index-id
817
+
818
+ 
819
+ Examples:
820
+ uipath context-grounding deep-rag start --index-name my-index --folder-path Shared --task-name my-task --prompt "Summarize"
821
+ uipath context-grounding deep-rag start --index-id abc-123 --task-name my-task --prompt "Summarize"
822
+
823
+
824
+ Options:
825
+ - `--index-name`: Name of the context grounding index (default: `Sentinel.UNSET`)
826
+ - `--index-id`: ID of the context grounding index (ephemeral indexes only) (default: `Sentinel.UNSET`)
827
+ - `--task-name`: Name for the Deep RAG task (default: `Sentinel.UNSET`)
828
+ - `--prompt`: Task prompt describing what to research (default: `Sentinel.UNSET`)
829
+ - `--glob-pattern`: Glob pattern to filter files in the index (default: **) (default: `**`)
830
+ - `--citation-mode`: Citation mode (default: Skip) (default: `Skip`)
831
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
832
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
833
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
834
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
835
+
836
+ **`uipath context-grounding delete`**
837
+
838
+ Delete a context grounding index.
839
+
840
+ 
841
+ Examples:
842
+ uipath context-grounding delete --index-name my-index --confirm
843
+ uipath context-grounding delete --index-name my-index --dry-run
844
+
845
+
846
+ Options:
847
+ - `--index-name`: Name of the index to delete (default: `Sentinel.UNSET`)
848
+ - `--confirm`: Skip confirmation prompt
849
+ - `--dry-run`: Show what would be deleted without deleting
850
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
851
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
852
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
853
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
854
+
855
+ **`uipath context-grounding ingest`**
856
+
857
+ Trigger ingestion on a context grounding index.
858
+
859
+ Ingestion runs asynchronously. Use 'retrieve' to poll lastIngestionStatus
860
+ until it reaches Successful or Failed.
861
+
862
+ 
863
+ Examples:
864
+ uipath context-grounding ingest --index-name my-index --folder-path "Shared"
865
+
866
+
867
+ Options:
868
+ - `--index-name`: Name of the index to ingest (default: `Sentinel.UNSET`)
869
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
870
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
871
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
872
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
873
+
874
+ **`uipath context-grounding list`**
875
+
876
+ List all context grounding indexes.
877
+
878
+ 
879
+ Examples:
880
+ uipath context-grounding list --folder-path "Shared"
881
+
882
+
883
+ Options:
884
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
885
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
886
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
887
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
888
+
889
+ **`uipath context-grounding retrieve`**
890
+
891
+ Retrieve a context grounding index.
892
+
893
+ 
894
+ Two ways to specify the index:
895
+ Regular index: --index-name + --folder-path
896
+ Ephemeral index: --index-id
897
+
898
+ 
899
+ Examples:
900
+ uipath context-grounding retrieve --index-name my-index --folder-path "Shared"
901
+ uipath context-grounding retrieve --index-id abc-123-def-456 --format json
902
+
903
+
904
+ Options:
905
+ - `--index-name`: Name of the index to retrieve (default: `Sentinel.UNSET`)
906
+ - `--index-id`: ID of the index to retrieve (ephemeral indexes only) (default: `Sentinel.UNSET`)
907
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
908
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
909
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
910
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
911
+
912
+ **`uipath context-grounding search`**
913
+
914
+ Search a context grounding index (regular indexes only).
915
+
916
+ 
917
+ Examples:
918
+ uipath context-grounding search --index-name my-index --query "What is the revenue?"
919
+ uipath context-grounding search --index-name my-index --query "results" --limit 5
920
+
921
+
922
+ Options:
923
+ - `--index-name`: Name of the index to search (default: `Sentinel.UNSET`)
924
+ - `--query`: Search query in natural language (default: `Sentinel.UNSET`)
925
+ - `--limit`: Maximum number of results (default: 10) (default: `10`)
926
+ - `--threshold`: Minimum similarity threshold (default: 0.0) (default: `0.0`)
927
+ - `--search-mode`: Search mode (default: Semantic) (default: `Semantic`)
928
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
929
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
930
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
931
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
932
+
933
+ **`uipath context-grounding source-schema`**
934
+
935
+ Show JSON source file formats for connection-backed indexes.
936
+
937
+ Use this to see the required fields for --source-file when creating
938
+ an index backed by Google Drive, OneDrive, Dropbox, or Confluence.
939
+
940
+ 
941
+ Examples:
942
+ uipath context-grounding source-schema --type google_drive
943
+
944
+
945
+ Options:
946
+ - `--type`: Show schema for a specific source type (omit to show all) (default: `Sentinel.UNSET`)
947
+
948
+ ---
949
+
agents/agent_2_investigation_api/.agent/REQUIRED_STRUCTURE.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Required Agent Structure
2
+
3
+ **IMPORTANT**: All UiPath coded agents MUST follow this standard structure unless explicitly specified otherwise by the user.
4
+
5
+ ### Required Components
6
+
7
+ Every agent implementation MUST include these two Pydantic models:
8
+
9
+ ```python
10
+ from pydantic import BaseModel
11
+
12
+ class Input(BaseModel):
13
+ """Define input fields that the agent accepts"""
14
+ # Add your input fields here
15
+ pass
16
+
17
+ class Output(BaseModel):
18
+ """Define output fields that the agent returns"""
19
+ # Add your output fields here
20
+ pass
21
+ ```
22
+
23
+ ### SDK Initialization
24
+
25
+ ```python
26
+ from uipath.platform import UiPath
27
+
28
+ # Initialize with environment variables
29
+ uipath = UiPath()
30
+
31
+ # With explicit credentials
32
+ uipath = UiPath(base_url="https://cloud.uipath.com/...", secret="your_token")
33
+
34
+ # Or with client_id and client_secret
35
+ uipath = UiPath(
36
+ client_id=UIPATH_CLIENT_ID,
37
+ client_secret=UIPATH_CLIENT_SECRET,
38
+ scope=UIPATH_SCOPE,
39
+ base_url=UIPATH_URL
40
+ )
41
+ ```
42
+
43
+ ### Standard Agent Template
44
+
45
+ Every agent should follow this basic structure:
46
+
47
+ ```python
48
+ from uipath.platform import UiPath
49
+ from pydantic import BaseModel
50
+
51
+ # 1. Define Input, and Output models
52
+ class Input(BaseModel):
53
+ field: str
54
+
55
+ class Output(BaseModel):
56
+ result: str
57
+
58
+ # 2. Initialize with environment variables
59
+ uipath = UiPath()
60
+
61
+ # 3. Define the main function (the main function can be named "main", "run" or "execute")
62
+ def main(input_data: Input) -> Output:
63
+ pass
64
+ ```
agents/agent_2_investigation_api/.agent/SDK_REFERENCE.md ADDED
@@ -0,0 +1,971 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## API Reference
2
+
3
+ This section provides a comprehensive reference for all UiPath SDK services and methods. Each service is documented with complete method signatures, including parameter types and return types.
4
+
5
+ ### SDK Initialization
6
+
7
+ Initialize the UiPath SDK client
8
+
9
+ ```python
10
+ from uipath.platform import UiPath
11
+
12
+ # Initialize with environment variables
13
+ sdk = UiPath()
14
+
15
+ # Or with explicit credentials
16
+ sdk = UiPath(base_url="https://cloud.uipath.com/...", secret="your_token")
17
+ ```
18
+
19
+ ### Agenthub
20
+
21
+ Agenthub service
22
+
23
+ ```python
24
+ # Fetch available models from LLM Gateway discovery endpoint.
25
+ sdk.agenthub.get_available_llm_models(headers: dict[str, Any] | None=None) -> list[uipath.platform.agenthub.agenthub.LlmModel]
26
+
27
+ # Asynchronously fetch available models from LLM Gateway discovery endpoint.
28
+ sdk.agenthub.get_available_llm_models_async(headers: dict[str, Any] | None=None) -> list[uipath.platform.agenthub.agenthub.LlmModel]
29
+
30
+ # Start a system agent job.
31
+ sdk.agenthub.invoke_system_agent(agent_name: str, entrypoint: str, input_arguments: dict[str, Any] | None=None, folder_key: str | None=None, folder_path: str | None=None, headers: dict[str, Any] | None=None) -> str
32
+
33
+ # Asynchronously start a system agent and return the job.
34
+ sdk.agenthub.invoke_system_agent_async(agent_name: str, entrypoint: str, input_arguments: dict[str, Any] | None=None, folder_key: str | None=None, folder_path: str | None=None, headers: dict[str, Any] | None=None) -> str
35
+
36
+ ```
37
+
38
+ ### Api Client
39
+
40
+ Api Client service
41
+
42
+ ```python
43
+ # Access api_client service methods
44
+ service = sdk.api_client
45
+
46
+ ```
47
+
48
+ ### Assets
49
+
50
+ Assets service
51
+
52
+ ```python
53
+ # List assets using OData API with offset-based pagination.
54
+ sdk.assets.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.assets.Asset]
55
+
56
+ # Asynchronously list assets using OData API with offset-based pagination.
57
+ sdk.assets.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.assets.Asset]
58
+
59
+ # Retrieve an asset by its name.
60
+ sdk.assets.retrieve(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.assets.UserAsset | uipath.platform.orchestrator.assets.Asset
61
+
62
+ # Asynchronously retrieve an asset by its name.
63
+ sdk.assets.retrieve_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.assets.UserAsset | uipath.platform.orchestrator.assets.Asset
64
+
65
+ # Gets a specified Orchestrator credential.
66
+ sdk.assets.retrieve_credential(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Optional[str]
67
+
68
+ # Asynchronously gets a specified Orchestrator credential.
69
+ sdk.assets.retrieve_credential_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Optional[str]
70
+
71
+ # Update an asset's value.
72
+ sdk.assets.update(robot_asset: uipath.platform.orchestrator.assets.UserAsset, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
73
+
74
+ # Asynchronously update an asset's value.
75
+ sdk.assets.update_async(robot_asset: uipath.platform.orchestrator.assets.UserAsset, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
76
+
77
+ ```
78
+
79
+ ### Attachments
80
+
81
+ Attachments service
82
+
83
+ ```python
84
+ # Delete an attachment.
85
+ sdk.attachments.delete(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> None
86
+
87
+ # Delete an attachment asynchronously.
88
+ sdk.attachments.delete_async(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> None
89
+
90
+ # Download an attachment.
91
+ sdk.attachments.download(key: uuid.UUID, destination_path: str, folder_key: str | None=None, folder_path: str | None=None) -> str
92
+
93
+ # Download an attachment asynchronously.
94
+ sdk.attachments.download_async(key: uuid.UUID, destination_path: str, folder_key: str | None=None, folder_path: str | None=None) -> str
95
+
96
+ # Get the BlobFileAccess information for an attachment.
97
+ sdk.attachments.get_blob_file_access_uri(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.attachments.attachments.BlobFileAccessInfo
98
+
99
+ # Get the BlobFileAccess information for an attachment asynchronously.
100
+ sdk.attachments.get_blob_file_access_uri_async(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.attachments.attachments.BlobFileAccessInfo
101
+
102
+ # Open an attachment.
103
+ sdk.attachments.open(attachment: uipath.platform.attachments.attachments.Attachment, mode: <enum 'AttachmentMode="AttachmentMode.READ", content: Union[str, bytes, Iterable[bytes], AsyncIterable[bytes], NoneType]=None, folder_key: str | None=None, folder_path: str | None=None) -> typing.Iterator[typing.Tuple[uipath.platform.attachments.attachments.Attachment, httpx.Response]]
104
+
105
+ # Open an attachment asynchronously.
106
+ sdk.attachments.open_async(attachment: uipath.platform.attachments.attachments.Attachment, mode: <enum 'AttachmentMode="AttachmentMode.READ", content: Union[str, bytes, Iterable[bytes], AsyncIterable[bytes], NoneType]=None, folder_key: str | None=None, folder_path: str | None=None) -> typing.AsyncIterator[typing.Tuple[uipath.platform.attachments.attachments.Attachment, httpx.Response]]
107
+
108
+ # Upload a file or content to UiPath as an attachment.
109
+ sdk.attachments.upload(name: str, content: str | bytes | None=None, source_path: str | None=None, folder_key: str | None=None, folder_path: str | None=None) -> uuid.UUID
110
+
111
+ # Upload a file or content to UiPath as an attachment asynchronously.
112
+ sdk.attachments.upload_async(name: str, content: str | bytes | None=None, source_path: str | None=None, folder_key: str | None=None, folder_path: str | None=None) -> uuid.UUID
113
+
114
+ ```
115
+
116
+ ### Automation Ops
117
+
118
+ Automation Ops service
119
+
120
+ ```python
121
+ # Retrieve the deployed policy.
122
+ sdk.automation_ops.get_deployed_policy() -> dict[str, typing.Any]
123
+
124
+ # Retrieve the deployed policy (async).
125
+ sdk.automation_ops.get_deployed_policy_async() -> dict[str, typing.Any]
126
+
127
+ ```
128
+
129
+ ### Automation Tracker
130
+
131
+ Automation Tracker service
132
+
133
+ ```python
134
+ # End tracking an operation within a transaction.
135
+ sdk.automation_tracker.end_operation(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
136
+
137
+ # End tracking an operation within a transaction (async).
138
+ sdk.automation_tracker.end_operation_async(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
139
+
140
+ # End tracking a business transaction.
141
+ sdk.automation_tracker.end_transaction(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
142
+
143
+ # End tracking a business transaction (async).
144
+ sdk.automation_tracker.end_transaction_async(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
145
+
146
+ # Start tracking an operation within a transaction.
147
+ sdk.automation_tracker.start_operation(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
148
+
149
+ # Start tracking an operation within a transaction (async).
150
+ sdk.automation_tracker.start_operation_async(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
151
+
152
+ # Start tracking a business transaction.
153
+ sdk.automation_tracker.start_transaction(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
154
+
155
+ # Start tracking a business transaction (async).
156
+ sdk.automation_tracker.start_transaction_async(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
157
+
158
+ ```
159
+
160
+ ### Buckets
161
+
162
+ Buckets service
163
+
164
+ ```python
165
+ # Create a new bucket.
166
+ sdk.buckets.create(name: str, description: Optional[str]=None, identifier: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
167
+
168
+ # Async version of create().
169
+ sdk.buckets.create_async(name: str, description: Optional[str]=None, identifier: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
170
+
171
+ # Delete a bucket.
172
+ sdk.buckets.delete(name: Optional[str]=None, key: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
173
+
174
+ # Async version of delete().
175
+ sdk.buckets.delete_async(name: Optional[str]=None, key: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
176
+
177
+ # Delete a file from a bucket.
178
+ sdk.buckets.delete_file(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
179
+
180
+ # Delete a file from a bucket asynchronously.
181
+ sdk.buckets.delete_file_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
182
+
183
+ # Download a file from a bucket.
184
+ sdk.buckets.download(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, destination_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
185
+
186
+ # Download a file from a bucket asynchronously.
187
+ sdk.buckets.download_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, destination_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
188
+
189
+ # Check if bucket exists.
190
+ sdk.buckets.exists(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
191
+
192
+ # Async version of exists().
193
+ sdk.buckets.exists_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
194
+
195
+ # Check if a file exists in a bucket.
196
+ sdk.buckets.exists_file(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
197
+
198
+ # Async version of exists_file().
199
+ sdk.buckets.exists_file_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
200
+
201
+ # Get files using OData GetFiles API with offset-based pagination.
202
+ sdk.buckets.get_files(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", recursive: bool=False, file_name_glob: Optional[str]=None, skip: int=0, top: int=500, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
203
+
204
+ # Async version of get_files() with offset-based pagination.
205
+ sdk.buckets.get_files_async(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", recursive: bool=False, file_name_glob: Optional[str]=None, skip: int=0, top: int=500, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
206
+
207
+ # List buckets using OData API with offset-based pagination.
208
+ sdk.buckets.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, name: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.Bucket]
209
+
210
+ # Async version of list() with offset-based pagination.
211
+ sdk.buckets.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, name: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.Bucket]
212
+
213
+ # List files in a bucket using cursor-based pagination.
214
+ sdk.buckets.list_files(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", take_hint: int=500, continuation_token: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
215
+
216
+ # Async version of list_files() with cursor-based pagination.
217
+ sdk.buckets.list_files_async(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", take_hint: int=500, continuation_token: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
218
+
219
+ # Retrieve bucket information by its name.
220
+ sdk.buckets.retrieve(name: Optional[str]=None, key: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
221
+
222
+ # Asynchronously retrieve bucket information by its name.
223
+ sdk.buckets.retrieve_async(name: Optional[str]=None, key: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
224
+
225
+ # Upload a file to a bucket.
226
+ sdk.buckets.upload(key: Optional[str]=None, name: Optional[str]=None, blob_file_path: str, content_type: Optional[str]=None, source_path: Optional[str]=None, content: Union[str, bytes, NoneType]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
227
+
228
+ # Upload a file to a bucket asynchronously.
229
+ sdk.buckets.upload_async(key: Optional[str]=None, name: Optional[str]=None, blob_file_path: str, content_type: Optional[str]=None, source_path: Optional[str]=None, content: Union[str, bytes, NoneType]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
230
+
231
+ ```
232
+
233
+ ### Connections
234
+
235
+ Connections service
236
+
237
+ ```python
238
+ # Invoke an activity synchronously.
239
+ sdk.connections.invoke_activity(activity_metadata: uipath.platform.connections.connections.ActivityMetadata, connection_id: str, activity_input: Dict[str, Any]) -> typing.Any
240
+
241
+ # Invoke an activity asynchronously.
242
+ sdk.connections.invoke_activity_async(activity_metadata: uipath.platform.connections.connections.ActivityMetadata, connection_id: str, activity_input: Dict[str, Any]) -> typing.Any
243
+
244
+ # Lists all connections with optional filtering.
245
+ sdk.connections.list(name: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, connector_key: Optional[str]=None, skip: Optional[int]=None, top: Optional[int]=None) -> typing.List[uipath.platform.connections.connections.Connection]
246
+
247
+ # Asynchronously lists all connections with optional filtering.
248
+ sdk.connections.list_async(name: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, connector_key: Optional[str]=None, skip: Optional[int]=None, top: Optional[int]=None) -> typing.List[uipath.platform.connections.connections.Connection]
249
+
250
+ # Synchronously retrieve connection API metadata.
251
+ sdk.connections.metadata(element_instance_id: int, connector_key: str, tool_path: str, parameters: Optional[Dict[str, str]]=None, schema_mode: bool=True, max_jit_depth: int=5) -> uipath.platform.connections.connections.ConnectionMetadata
252
+
253
+ # Asynchronously retrieve connection API metadata.
254
+ sdk.connections.metadata_async(element_instance_id: int, connector_key: str, tool_path: str, parameters: Optional[Dict[str, str]]=None, schema_mode: bool=True, max_jit_depth: int=5) -> uipath.platform.connections.connections.ConnectionMetadata
255
+
256
+ # Retrieve connection details by its key.
257
+ sdk.connections.retrieve(key: str) -> uipath.platform.connections.connections.Connection
258
+
259
+ # Asynchronously retrieve connection details by its key.
260
+ sdk.connections.retrieve_async(key: str) -> uipath.platform.connections.connections.Connection
261
+
262
+ # Retrieve event payload from UiPath Integration Service.
263
+ sdk.connections.retrieve_event_payload(event_args: uipath.platform.connections.connections.EventArguments) -> typing.Dict[str, typing.Any]
264
+
265
+ # Retrieve event payload from UiPath Integration Service.
266
+ sdk.connections.retrieve_event_payload_async(event_args: uipath.platform.connections.connections.EventArguments) -> typing.Dict[str, typing.Any]
267
+
268
+ # Retrieve an authentication token for a connection.
269
+ sdk.connections.retrieve_token(key: str, token_type: <enum 'ConnectionTokenType="ConnectionTokenType.DIRECT") -> uipath.platform.connections.connections.ConnectionToken
270
+
271
+ # Asynchronously retrieve an authentication token for a connection.
272
+ sdk.connections.retrieve_token_async(key: str, token_type: <enum 'ConnectionTokenType="ConnectionTokenType.DIRECT") -> uipath.platform.connections.connections.ConnectionToken
273
+
274
+ ```
275
+
276
+ ### Context Grounding
277
+
278
+ Context Grounding service
279
+
280
+ ```python
281
+ # Add content to the index.
282
+ sdk.context_grounding.add_to_index(name: str, blob_file_path: str, content_type: Optional[str]=None, content: Union[str, bytes, NoneType]=None, source_path: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, ingest_data: bool=True) -> None
283
+
284
+ # Asynchronously add content to the index.
285
+ sdk.context_grounding.add_to_index_async(name: str, blob_file_path: str, content_type: Optional[str]=None, content: Union[str, bytes, NoneType]=None, source_path: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, ingest_data: bool=True) -> None
286
+
287
+ # Create a new ephemeral context grounding index.
288
+ sdk.context_grounding.create_ephemeral_index(usage: <enum 'EphemeralIndexUsage, attachments: List[str], folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
289
+
290
+ # Create a new ephemeral context grounding index.
291
+ sdk.context_grounding.create_ephemeral_index_async(usage: <enum 'EphemeralIndexUsage, attachments: List[str], folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
292
+
293
+ # Create a new context grounding index.
294
+ sdk.context_grounding.create_index(name: str, source: Union[uipath.platform.context_grounding.context_grounding_payloads.BucketSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.GoogleDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.DropboxSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.OneDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.ConfluenceSourceConfig], description: Optional[str]=None, extraction_strategy: Optional[str]=None, embeddings_enabled: Optional[bool]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
295
+
296
+ # Create a new context grounding index.
297
+ sdk.context_grounding.create_index_async(name: str, source: Union[uipath.platform.context_grounding.context_grounding_payloads.BucketSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.GoogleDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.DropboxSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.OneDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.ConfluenceSourceConfig], description: Optional[str]=None, extraction_strategy: Optional[str]=None, embeddings_enabled: Optional[bool]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
298
+
299
+ # Delete a context grounding index by its name.
300
+ sdk.context_grounding.delete_by_name(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
301
+
302
+ # Asynchronously delete a context grounding index by its name.
303
+ sdk.context_grounding.delete_by_name_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
304
+
305
+ # Delete a context grounding index.
306
+ sdk.context_grounding.delete_index(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
307
+
308
+ # Asynchronously delete a context grounding index.
309
+ sdk.context_grounding.delete_index_async(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
310
+
311
+ # Downloads the Batch Transform result file to the specified path.
312
+ sdk.context_grounding.download_batch_transform_result(id: str, destination_path: str, validate_status: bool=True, index_name: str | None=None) -> None
313
+
314
+ # Asynchronously downloads the Batch Transform result file to the specified path.
315
+ sdk.context_grounding.download_batch_transform_result_async(id: str, destination_path: str, validate_status: bool=True, index_name: str | None=None) -> None
316
+
317
+ # Trigger ingestion on a context grounding index by its name.
318
+ sdk.context_grounding.ingest_by_name(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
319
+
320
+ # Asynchronously trigger ingestion on a context grounding index by its name.
321
+ sdk.context_grounding.ingest_by_name_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
322
+
323
+ # Ingest data into the context grounding index.
324
+ sdk.context_grounding.ingest_data(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
325
+
326
+ # Asynchronously ingest data into the context grounding index.
327
+ sdk.context_grounding.ingest_data_async(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
328
+
329
+ # List all context grounding indexes in a folder.
330
+ sdk.context_grounding.list(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
331
+
332
+ # Asynchronously list all context grounding indexes in a folder.
333
+ sdk.context_grounding.list_async(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
334
+
335
+ # List all context grounding indexes in a folder.
336
+ sdk.context_grounding.list_indexes(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
337
+
338
+ # Asynchronously list all context grounding indexes in a folder.
339
+ sdk.context_grounding.list_indexes_async(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
340
+
341
+ # Retrieve context grounding index information by its name.
342
+ sdk.context_grounding.retrieve(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
343
+
344
+ # Retrieve all context grounding indexes across all folders.
345
+ sdk.context_grounding.retrieve_across_folders(name: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
346
+
347
+ # Asynchronously retrieve all context grounding indexes across all folders.
348
+ sdk.context_grounding.retrieve_across_folders_async(name: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
349
+
350
+ # Asynchronously retrieve context grounding index information by its name.
351
+ sdk.context_grounding.retrieve_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
352
+
353
+ # Retrieves a Batch Transform task status.
354
+ sdk.context_grounding.retrieve_batch_transform(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformResponse
355
+
356
+ # Asynchronously retrieves a Batch Transform task status.
357
+ sdk.context_grounding.retrieve_batch_transform_async(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformResponse
358
+
359
+ # Retrieve context grounding index information by its ID.
360
+ sdk.context_grounding.retrieve_by_id(id: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Any
361
+
362
+ # Retrieve asynchronously context grounding index information by its ID.
363
+ sdk.context_grounding.retrieve_by_id_async(id: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Any
364
+
365
+ # Retrieves a Deep RAG task.
366
+ sdk.context_grounding.retrieve_deep_rag(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagResponse
367
+
368
+ # Asynchronously retrieves a Deep RAG task.
369
+ sdk.context_grounding.retrieve_deep_rag_async(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagResponse
370
+
371
+ # Search for contextual information within a specific index.
372
+ sdk.context_grounding.search(name: str, query: str, number_of_results: int=10, threshold: Optional[float]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding.ContextGroundingQueryResponse]
373
+
374
+ # Search asynchronously for contextual information within a specific index.
375
+ sdk.context_grounding.search_async(name: str, query: str, number_of_results: int=10, threshold: Optional[float]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding.ContextGroundingQueryResponse]
376
+
377
+ # Starts a Batch Transform, task on the targeted index.
378
+ sdk.context_grounding.start_batch_transform(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, target_file_name: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_name: str | None=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
379
+
380
+ # Asynchronously starts a Batch Transform, task on the targeted index.
381
+ sdk.context_grounding.start_batch_transform_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, target_file_name: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_name: str | None=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
382
+
383
+ # Asynchronously starts a Batch Transform, task on the targeted index.
384
+ sdk.context_grounding.start_batch_transform_ephemeral(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
385
+
386
+ # Asynchronously starts a Batch Transform, task on the targeted index.
387
+ sdk.context_grounding.start_batch_transform_ephemeral_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
388
+
389
+ # Starts a Deep RAG task on the targeted index.
390
+ sdk.context_grounding.start_deep_rag(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_name: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
391
+
392
+ # Asynchronously starts a Deep RAG task on the targeted index.
393
+ sdk.context_grounding.start_deep_rag_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_name: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
394
+
395
+ # Asynchronously starts a Deep RAG task on the targeted index.
396
+ sdk.context_grounding.start_deep_rag_ephemeral(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
397
+
398
+ # Asynchronously starts a Deep RAG task on the targeted index.
399
+ sdk.context_grounding.start_deep_rag_ephemeral_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
400
+
401
+ # Perform a unified search on a context grounding index.
402
+ sdk.context_grounding.unified_search(name: str, query: str, search_mode: <enum 'SearchMode="SearchMode.SEMANTIC", number_of_results: int=10, threshold: float=0.0, scope: Optional[uipath.platform.context_grounding.context_grounding.UnifiedSearchScope]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding.UnifiedQueryResult
403
+
404
+ # Asynchronously perform a unified search on a context grounding index.
405
+ sdk.context_grounding.unified_search_async(name: str, query: str, search_mode: <enum 'SearchMode="SearchMode.SEMANTIC", number_of_results: int=10, threshold: float=0.0, scope: Optional[uipath.platform.context_grounding.context_grounding.UnifiedSearchScope]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding.UnifiedQueryResult
406
+
407
+ ```
408
+
409
+ ### Conversational
410
+
411
+ Conversational service
412
+
413
+ ```python
414
+ # Access conversational service methods
415
+ service = sdk.conversational
416
+
417
+ ```
418
+
419
+ ### Documents
420
+
421
+ Documents service
422
+
423
+ ```python
424
+ # Classify a document using a DU Modern project.
425
+ sdk.documents.classify(project_type: <enum 'ProjectType, tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
426
+
427
+ # Asynchronously version of the [`classify`][uipath.platform.documents._documents_service.DocumentsService.classify] method.
428
+ sdk.documents.classify_async(project_type: <enum 'ProjectType, tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
429
+
430
+ # Create a validate classification action for a document based on the classification results. More details about validation actions can be found in the [official documentation](https://docs.uipath.com/ixp/automation-cloud/latest/user-guide/validating-classifications).
431
+ sdk.documents.create_validate_classification_action(classification_results: List[uipath.platform.documents.documents.ClassificationResult], action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateClassificationAction
432
+
433
+ # Asynchronous version of the [`create_validation_action`][uipath.platform.documents._documents_service.DocumentsService.create_validate_classification_action] method.
434
+ sdk.documents.create_validate_classification_action_async(classification_results: List[uipath.platform.documents.documents.ClassificationResult], action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateClassificationAction
435
+
436
+ # Create a validate extraction action for a document based on the extraction response. More details about validation actions can be found in the [official documentation](https://docs.uipath.com/ixp/automation-cloud/latest/user-guide/validating-extractions).
437
+ sdk.documents.create_validate_extraction_action(extraction_response: uipath.platform.documents.documents.ExtractionResponse, action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateExtractionAction
438
+
439
+ # Asynchronous version of the [`create_validation_action`][uipath.platform.documents._documents_service.DocumentsService.create_validate_extraction_action] method.
440
+ sdk.documents.create_validate_extraction_action_async(extraction_response: uipath.platform.documents.documents.ExtractionResponse, action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateExtractionAction
441
+
442
+ # Extract predicted data from a document using an DU Modern/IXP project.
443
+ sdk.documents.extract(tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None, classification_result: Optional[uipath.platform.documents.documents.ClassificationResult]=None, project_type: Optional[uipath.platform.documents.documents.ProjectType]=None, document_type_name: Optional[str]=None) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
444
+
445
+ # Asynchronously version of the [`extract`][uipath.platform.documents._documents_service.DocumentsService.extract] method.
446
+ sdk.documents.extract_async(tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None, classification_result: Optional[uipath.platform.documents.documents.ClassificationResult]=None, project_type: Optional[uipath.platform.documents.documents.ProjectType]=None, document_type_name: Optional[str]=None) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
447
+
448
+ # Get the result of a validate classification action.
449
+ sdk.documents.get_validate_classification_result(validation_action: uipath.platform.documents.documents.ValidateClassificationAction) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
450
+
451
+ # Asynchronous version of the [`get_validation_result`][uipath.platform.documents._documents_service.DocumentsService.get_validate_classification_result] method.
452
+ sdk.documents.get_validate_classification_result_async(validation_action: uipath.platform.documents.documents.ValidateClassificationAction) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
453
+
454
+ # Get the result of a validate extraction action.
455
+ sdk.documents.get_validate_extraction_result(validation_action: uipath.platform.documents.documents.ValidateExtractionAction) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
456
+
457
+ # Asynchronous version of the [`get_validation_result`][uipath.platform.documents._documents_service.DocumentsService.get_validate_extraction_result] method.
458
+ sdk.documents.get_validate_extraction_result_async(validation_action: uipath.platform.documents.documents.ValidateExtractionAction) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
459
+
460
+ # Retrieve the result of an IXP extraction operation (single-shot, non-blocking).
461
+ sdk.documents.retrieve_ixp_extraction_result(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ExtractionResponseIXP
462
+
463
+ # Asynchronous version of the [`retrieve_ixp_extraction_result`][uipath.platform.documents._documents_service.DocumentsService.retrieve_ixp_extraction_result] method.
464
+ sdk.documents.retrieve_ixp_extraction_result_async(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ExtractionResponseIXP
465
+
466
+ # Retrieve the result of an IXP create validate extraction action operation (single-shot, non-blocking).
467
+ sdk.documents.retrieve_ixp_extraction_validation_result(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ValidateExtractionAction
468
+
469
+ # Asynchronous version of the [`retrieve_ixp_extraction_validation_result`][uipath.platform.documents._documents_service.DocumentsService.retrieve_ixp_extraction_validation_result] method.
470
+ sdk.documents.retrieve_ixp_extraction_validation_result_async(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ValidateExtractionAction
471
+
472
+ # Start an IXP extraction process without waiting for results (non-blocking).
473
+ sdk.documents.start_ixp_extraction(project_name: str, tag: str, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionResponse
474
+
475
+ # Asynchronous version of the [`start_ixp_extraction`][uipath.platform.documents._documents_service.DocumentsService.start_ixp_extraction] method.
476
+ sdk.documents.start_ixp_extraction_async(project_name: str, tag: str, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionResponse
477
+
478
+ # Start an IXP extraction validation action without waiting for results (non-blocking).
479
+ sdk.documents.start_ixp_extraction_validation(extraction_response: uipath.platform.documents.documents.ExtractionResponseIXP, action_title: str, action_catalog: Optional[str]=None, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionValidationResponse
480
+
481
+ # Asynchronous version of the [`start_ixp_extraction_validation`][uipath.platform.documents._documents_service.DocumentsService.start_ixp_extraction_validation] method.
482
+ sdk.documents.start_ixp_extraction_validation_async(extraction_response: uipath.platform.documents.documents.ExtractionResponseIXP, action_title: str, action_catalog: Optional[str]=None, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionValidationResponse
483
+
484
+ ```
485
+
486
+ ### Entities
487
+
488
+ Entities service
489
+
490
+ ```python
491
+ # Create a new entity with the given schema and return its id.
492
+ sdk.entities.create_entity(name: str, fields: List[uipath.platform.entities.entities.EntityCreateFieldOptions], options: Optional[uipath.platform.entities.entities.EntityCreateOptions]=None) -> str
493
+
494
+ # Asynchronously create a new entity with the given schema.
495
+ sdk.entities.create_entity_async(name: str, fields: List[uipath.platform.entities.entities.EntityCreateFieldOptions], options: Optional[uipath.platform.entities.entities.EntityCreateOptions]=None) -> str
496
+
497
+ # Remove the file attached to a File-type field on a record.
498
+ sdk.entities.delete_attachment(entity_id: str, record_id: str, field_name: str, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
499
+
500
+ # Asynchronously remove the file attached to a File-type field.
501
+ sdk.entities.delete_attachment_async(entity_id: str, record_id: str, field_name: str, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
502
+
503
+ # Delete an entity and all of its records.
504
+ sdk.entities.delete_entity(entity_id: str) -> None
505
+
506
+ # Asynchronously delete an entity and all of its records.
507
+ sdk.entities.delete_entity_async(entity_id: str) -> None
508
+
509
+ # Delete a single record by id.
510
+ sdk.entities.delete_record(entity_key: str, record_id: str) -> None
511
+
512
+ # Asynchronously delete a single record by id.
513
+ sdk.entities.delete_record_async(entity_key: str, record_id: str) -> None
514
+
515
+ # Delete multiple records from an entity in a single batch operation.
516
+ sdk.entities.delete_records(entity_key: str, record_ids: List[str], fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
517
+
518
+ # Asynchronously delete multiple records from an entity in a single batch operation.
519
+ sdk.entities.delete_records_async(entity_key: str, record_ids: List[str], fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
520
+
521
+ # Download a file attached to a record and return its raw bytes.
522
+ sdk.entities.download_attachment(entity_id: str, record_id: str, field_name: str) -> bytes
523
+
524
+ # Asynchronously download a file attached to a record.
525
+ sdk.entities.download_attachment_async(entity_id: str, record_id: str, field_name: str) -> bytes
526
+
527
+ # Get the values of a choice set by its ID.
528
+ sdk.entities.get_choiceset_values(choiceset_id: str, start: Optional[int]=None, limit: Optional[int]=None) -> typing.List[uipath.platform.entities.entities.ChoiceSetValue]
529
+
530
+ # Asynchronously get the values of a choice set by its ID.
531
+ sdk.entities.get_choiceset_values_async(choiceset_id: str, start: Optional[int]=None, limit: Optional[int]=None) -> typing.List[uipath.platform.entities.entities.ChoiceSetValue]
532
+
533
+ # Fetch a single entity record by its id.
534
+ sdk.entities.get_record(entity_key: str, record_id: str, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
535
+
536
+ # Asynchronously fetch a single entity record by its id.
537
+ sdk.entities.get_record_async(entity_key: str, record_id: str, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
538
+
539
+ # Bulk-import records into an entity from a CSV file.
540
+ sdk.entities.import_records(entity_id: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.entities.entities.EntityImportRecordsResponse
541
+
542
+ # Asynchronously bulk-import records into an entity from a CSV file.
543
+ sdk.entities.import_records_async(entity_id: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.entities.entities.EntityImportRecordsResponse
544
+
545
+ # Insert a single record into an entity and return the inserted row.
546
+ sdk.entities.insert_record(entity_key: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
547
+
548
+ # Asynchronously insert a single record into an entity.
549
+ sdk.entities.insert_record_async(entity_key: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
550
+
551
+ # Insert multiple records into an entity in a single batch operation.
552
+ sdk.entities.insert_records(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
553
+
554
+ # Asynchronously insert multiple records into an entity in a single batch operation.
555
+ sdk.entities.insert_records_async(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
556
+
557
+ # List all choice sets in Data Service.
558
+ sdk.entities.list_choicesets() -> typing.List[uipath.platform.entities.entities.Entity]
559
+
560
+ # Asynchronously list all choice sets in Data Service.
561
+ sdk.entities.list_choicesets_async() -> typing.List[uipath.platform.entities.entities.Entity]
562
+
563
+ # List all entities in Data Service.
564
+ sdk.entities.list_entities() -> typing.List[uipath.platform.entities.entities.Entity]
565
+
566
+ # Asynchronously list all entities in the Data Service.
567
+ sdk.entities.list_entities_async() -> typing.List[uipath.platform.entities.entities.Entity]
568
+
569
+ # List records from an entity with optional pagination and schema validation.
570
+ sdk.entities.list_records(entity_key: str, schema: Optional[Type[Any]]=None, start: Optional[int]=None, limit: Optional[int]=None, expansion_level: Optional[int]=None, filter: Optional[str]=None, orderby: Optional[str]=None, select: Optional[List[str]]=None, expand: Optional[List[str]]=None) -> uipath.platform.entities.entities.EntityRecordsListResponse
571
+
572
+ # Asynchronously list records from an entity with optional pagination and schema validation.
573
+ sdk.entities.list_records_async(entity_key: str, schema: Optional[Type[Any]]=None, start: Optional[int]=None, limit: Optional[int]=None, expansion_level: Optional[int]=None, filter: Optional[str]=None, orderby: Optional[str]=None, select: Optional[List[str]]=None, expand: Optional[List[str]]=None) -> uipath.platform.entities.entities.EntityRecordsListResponse
574
+
575
+ # Query entity records using a validated SQL query.
576
+ sdk.entities.query_entity_records(sql_query: str) -> typing.List[typing.Dict[str, typing.Any]]
577
+
578
+ # Asynchronously query entity records using a validated SQL query.
579
+ sdk.entities.query_entity_records_async(sql_query: str) -> typing.List[typing.Dict[str, typing.Any]]
580
+
581
+ # Resolve an agent entity set, applying resource overwrites.
582
+ sdk.entities.resolve_entity_set(items: List[uipath.platform.entities.entities.DataFabricEntityItem]) -> uipath.platform.entities.entities.EntitySetResolution
583
+
584
+ # Resolve an agent entity set, applying resource overwrites.
585
+ sdk.entities.resolve_entity_set_async(items: List[uipath.platform.entities.entities.DataFabricEntityItem]) -> uipath.platform.entities.entities.EntitySetResolution
586
+
587
+ # Retrieve an entity by its key.
588
+ sdk.entities.retrieve(entity_key: str) -> uipath.platform.entities.entities.Entity
589
+
590
+ # Asynchronously retrieve an entity by its key.
591
+ sdk.entities.retrieve_async(entity_key: str) -> uipath.platform.entities.entities.Entity
592
+
593
+ # Retrieve an entity by its name.
594
+ sdk.entities.retrieve_by_name(entity_name: str, folder_key: Optional[str]=None) -> uipath.platform.entities.entities.Entity
595
+
596
+ # Asynchronously retrieve an entity by its name.
597
+ sdk.entities.retrieve_by_name_async(entity_name: str, folder_key: Optional[str]=None) -> uipath.platform.entities.entities.Entity
598
+
599
+ # Retrieve records with structured filters, sorting, expansion, joins, and aggregates.
600
+ sdk.entities.retrieve_records(entity_key: str, filter_group: Optional[uipath.platform.entities.entities.EntityQueryFilterGroup]=None, sort_options: Optional[List[uipath.platform.entities.entities.EntityQuerySortOption]]=None, selected_fields: Optional[List[str]]=None, expansions: Optional[List[Any]]=None, expansion_level: Optional[int]=None, aggregates: Optional[List[uipath.platform.entities.entities.EntityAggregate]]=None, group_by: Optional[List[str]]=None, joins: Optional[List[uipath.platform.entities.entities.EntityJoin]]=None, binnings: Optional[List[uipath.platform.entities.entities.EntityBinning]]=None, start: Optional[int]=None, limit: Optional[int]=None) -> uipath.platform.entities.entities.RetrieveEntityRecordsResponse
601
+
602
+ # Asynchronously retrieve records with structured filters, sorting, expansion, joins, and aggregates.
603
+ sdk.entities.retrieve_records_async(entity_key: str, filter_group: Optional[uipath.platform.entities.entities.EntityQueryFilterGroup]=None, sort_options: Optional[List[uipath.platform.entities.entities.EntityQuerySortOption]]=None, selected_fields: Optional[List[str]]=None, expansions: Optional[List[Any]]=None, expansion_level: Optional[int]=None, aggregates: Optional[List[uipath.platform.entities.entities.EntityAggregate]]=None, group_by: Optional[List[str]]=None, joins: Optional[List[uipath.platform.entities.entities.EntityJoin]]=None, binnings: Optional[List[uipath.platform.entities.entities.EntityBinning]]=None, start: Optional[int]=None, limit: Optional[int]=None) -> uipath.platform.entities.entities.RetrieveEntityRecordsResponse
604
+
605
+ # Update an entity's display name, description, and/or RBAC flag.
606
+ sdk.entities.update_entity_metadata(entity_id: str, metadata: Union[uipath.platform.entities.entities.EntityMetadataUpdateOptions, Dict[str, Any]]) -> None
607
+
608
+ # Asynchronously update an entity's display name, description, and/or RBAC flag.
609
+ sdk.entities.update_entity_metadata_async(entity_id: str, metadata: Union[uipath.platform.entities.entities.EntityMetadataUpdateOptions, Dict[str, Any]]) -> None
610
+
611
+ # Update a single record by id and return the updated row.
612
+ sdk.entities.update_record(entity_key: str, record_id: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
613
+
614
+ # Asynchronously update a single record by id.
615
+ sdk.entities.update_record_async(entity_key: str, record_id: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
616
+
617
+ # Update multiple records in an entity in a single batch operation.
618
+ sdk.entities.update_records(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
619
+
620
+ # Asynchronously update multiple records in an entity in a single batch operation.
621
+ sdk.entities.update_records_async(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
622
+
623
+ # Upload a file attachment to a File-type field on a record.
624
+ sdk.entities.upload_attachment(entity_id: str, record_id: str, field_name: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
625
+
626
+ # Asynchronously upload a file attachment to a File-type field on a record.
627
+ sdk.entities.upload_attachment_async(entity_id: str, record_id: str, field_name: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
628
+
629
+ # Parse a batch response, optionally validating success records against ``schema``.
630
+ sdk.entities.validate_entity_batch(batch_response: httpx.Response, schema: Optional[Type[Any]]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
631
+
632
+ ```
633
+
634
+ ### Folders
635
+
636
+ Folders service
637
+
638
+ ```python
639
+ # Retrieve the personal workspace folder for the current user.
640
+ sdk.folders.get_personal_workspace() -> uipath.platform.orchestrator.folder.PersonalWorkspace
641
+
642
+ # Asynchronously retrieve the personal workspace folder for the current user.
643
+ sdk.folders.get_personal_workspace_async() -> uipath.platform.orchestrator.folder.PersonalWorkspace
644
+
645
+ # Resolve a folder path to its corresponding folder key.
646
+ sdk.folders.retrieve_folder_key(folder_path: str | None) -> str | None
647
+
648
+ # Asynchronously resolve a folder path to its corresponding folder key.
649
+ sdk.folders.retrieve_folder_key_async(folder_path: str | None) -> str | None
650
+
651
+ # Retrieve the folder key by folder path with pagination support.
652
+ sdk.folders.retrieve_key(folder_path: str) -> typing.Optional[str]
653
+
654
+ # Retrieve the folder key by folder path with pagination support.
655
+ sdk.folders.retrieve_key_async(folder_path: str) -> typing.Optional[str]
656
+
657
+ ```
658
+
659
+ ### Guardrails
660
+
661
+ Guardrails service
662
+
663
+ ```python
664
+ # Validate input text using the provided guardrail.
665
+ sdk.guardrails.evaluate_guardrail(input_data: str | dict[str, Any], guardrail: uipath.platform.guardrails.guardrails.BuiltInValidatorGuardrail) -> uipath.core.guardrails.guardrails.GuardrailValidationResult
666
+
667
+ ```
668
+
669
+ ### Jobs
670
+
671
+ Jobs service
672
+
673
+ ```python
674
+ # Create and upload an attachment, optionally linking it to a job.
675
+ sdk.jobs.create_attachment(name: str, content: Union[str, bytes, NoneType]=None, source_path: Union[str, pathlib.Path, NoneType]=None, job_key: Union[str, uuid.UUID, NoneType]=None, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uuid.UUID
676
+
677
+ # Create and upload an attachment asynchronously, optionally linking it to a job.
678
+ sdk.jobs.create_attachment_async(name: str, content: Union[str, bytes, NoneType]=None, source_path: Union[str, pathlib.Path, NoneType]=None, job_key: Union[str, uuid.UUID, NoneType]=None, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uuid.UUID
679
+
680
+ # Check if job exists.
681
+ sdk.jobs.exists(job_key: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
682
+
683
+ # Async version of exists().
684
+ sdk.jobs.exists_async(job_key: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
685
+
686
+ # Get the actual output data, downloading from attachment if necessary.
687
+ sdk.jobs.extract_output(job: uipath.platform.orchestrator.job.Job) -> typing.Optional[str]
688
+
689
+ # Asynchronously fetch the actual output data, downloading from attachment if necessary.
690
+ sdk.jobs.extract_output_async(job: uipath.platform.orchestrator.job.Job) -> typing.Optional[str]
691
+
692
+ # Link an attachment to a job.
693
+ sdk.jobs.link_attachment(attachment_key: uuid.UUID, job_key: uuid.UUID, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None)
694
+
695
+ # Link an attachment to a job asynchronously.
696
+ sdk.jobs.link_attachment_async(attachment_key: uuid.UUID, job_key: uuid.UUID, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None)
697
+
698
+ # List jobs using OData API with offset-based pagination.
699
+ sdk.jobs.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.job.Job]
700
+
701
+ # Async version of list() with offset-based pagination.
702
+ sdk.jobs.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.job.Job]
703
+
704
+ # List attachments associated with a specific job.
705
+ sdk.jobs.list_attachments(job_key: uuid.UUID, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[str]
706
+
707
+ # List attachments associated with a specific job asynchronously.
708
+ sdk.jobs.list_attachments_async(job_key: uuid.UUID, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[str]
709
+
710
+ # Restart a completed or failed job.
711
+ sdk.jobs.restart(job_key: str, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.job.Job
712
+
713
+ # Async version of restart().
714
+ sdk.jobs.restart_async(job_key: str, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.job.Job
715
+
716
+ # Sends a payload to resume a paused job waiting for input, identified by its inbox ID.
717
+ sdk.jobs.resume(inbox_id: Optional[str]=None, job_id: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, payload: Any) -> None
718
+
719
+ # Asynchronously sends a payload to resume a paused job waiting for input, identified by its inbox ID.
720
+ sdk.jobs.resume_async(inbox_id: Optional[str]=None, job_id: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, payload: Any) -> None
721
+
722
+ # Retrieve a job identified by its key.
723
+ sdk.jobs.retrieve(job_key: str, folder_key: str | None=None, folder_path: str | None=None, process_name: str | None=None) -> uipath.platform.orchestrator.job.Job
724
+
725
+ # Fetch payload data for API triggers.
726
+ sdk.jobs.retrieve_api_payload(inbox_id: str) -> typing.Any
727
+
728
+ # Asynchronously fetch payload data for API triggers.
729
+ sdk.jobs.retrieve_api_payload_async(inbox_id: str) -> typing.Any
730
+
731
+ # Asynchronously retrieve a job identified by its key.
732
+ sdk.jobs.retrieve_async(job_key: str, folder_key: str | None=None, folder_path: str | None=None, process_name: str | None=None) -> uipath.platform.orchestrator.job.Job
733
+
734
+ # Fetch payload data for Integration Services (Inbox) triggers.
735
+ sdk.jobs.retrieve_inbox_payload(inbox_id: str) -> typing.Any
736
+
737
+ # Asynchronously fetch payload data for Integration Services (Inbox) triggers.
738
+ sdk.jobs.retrieve_inbox_payload_async(inbox_id: str) -> typing.Any
739
+
740
+ # Stop one or more jobs with specified strategy.
741
+ sdk.jobs.stop(job_keys: List[str], strategy: str="SoftStop", folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
742
+
743
+ # Async version of stop().
744
+ sdk.jobs.stop_async(job_keys: List[str], strategy: str="SoftStop", folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
745
+
746
+ ```
747
+
748
+ ### Llm
749
+
750
+ Llm service
751
+
752
+ ```python
753
+ # Generate chat completions using UiPath's normalized LLM Gateway API.
754
+ sdk.llm.chat_completions(messages: list[dict[str, str]] | list[tuple[str, str]], model: str="gpt-4.1-mini-2025-04-14", max_tokens: int=4096, temperature: float=0, n: int=1, frequency_penalty: float=0, presence_penalty: float=0, top_p: float | None=1, top_k: int | None=None, tools: list[uipath.platform.chat.llm_gateway.ToolDefinition] | None=None, tool_choice: Union[uipath.platform.chat.llm_gateway.AutoToolChoice, uipath.platform.chat.llm_gateway.RequiredToolChoice, uipath.platform.chat.llm_gateway.SpecificToolChoice, Literal['auto', 'none'], NoneType]=None, response_format: dict[str, Any] | type[pydantic.main.BaseModel] | None=None, api_version: str="2024-08-01-preview")
755
+
756
+ ```
757
+
758
+ ### Llm Openai
759
+
760
+ Llm Openai service
761
+
762
+ ```python
763
+ # Generate chat completions using UiPath's LLM Gateway service.
764
+ sdk.llm_openai.chat_completions(messages: list[dict[str, str]], model: str="gpt-4.1-mini-2025-04-14", max_tokens: int=4096, temperature: float=0, response_format: dict[str, Any] | type[pydantic.main.BaseModel] | None=None, api_version: str="2024-10-21")
765
+
766
+ # Generate text embeddings using UiPath's LLM Gateway service.
767
+ sdk.llm_openai.embeddings(input: str, embedding_model: str="text-embedding-ada-002", openai_api_version: str="2024-10-21")
768
+
769
+ ```
770
+
771
+ ### Mcp
772
+
773
+ Mcp service
774
+
775
+ ```python
776
+ # List all MCP servers.
777
+ sdk.mcp.list(folder_path: str | None=None) -> typing.List[uipath.platform.orchestrator.mcp.McpServer]
778
+
779
+ # Asynchronously list all MCP servers.
780
+ sdk.mcp.list_async(folder_path: str | None=None) -> typing.List[uipath.platform.orchestrator.mcp.McpServer]
781
+
782
+ # Retrieve a specific MCP server by its slug.
783
+ sdk.mcp.retrieve(slug: str, folder_path: str | None=None) -> uipath.platform.orchestrator.mcp.McpServer
784
+
785
+ # Asynchronously retrieve a specific MCP server by its slug.
786
+ sdk.mcp.retrieve_async(slug: str, folder_path: str | None=None) -> uipath.platform.orchestrator.mcp.McpServer
787
+
788
+ ```
789
+
790
+ ### Memory
791
+
792
+ Memory service
793
+
794
+ ```python
795
+ # Create a new memory space.
796
+ sdk.memory.create(name: str, description: Optional[str]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpace
797
+
798
+ # Asynchronously create a new memory space.
799
+ sdk.memory.create_async(name: str, description: Optional[str]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpace
800
+
801
+ # Ingest a resolved escalation outcome into memory.
802
+ sdk.memory.escalation_ingest(memory_space_id: str, request: uipath.platform.memory.memory.EscalationMemoryIngestRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
803
+
804
+ # Asynchronously ingest a resolved escalation outcome into memory.
805
+ sdk.memory.escalation_ingest_async(memory_space_id: str, request: uipath.platform.memory.memory.EscalationMemoryIngestRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
806
+
807
+ # Search escalation memory for previously resolved outcomes.
808
+ sdk.memory.escalation_search(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.EscalationMemorySearchResponse
809
+
810
+ # Asynchronously search escalation memory for previously resolved outcomes.
811
+ sdk.memory.escalation_search_async(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.EscalationMemorySearchResponse
812
+
813
+ # List memory spaces with optional OData query parameters.
814
+ sdk.memory.list(filter: Optional[str]=None, orderby: Optional[str]=None, top: Optional[int]=None, skip: Optional[int]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpaceListResponse
815
+
816
+ # Asynchronously list memory spaces.
817
+ sdk.memory.list_async(filter: Optional[str]=None, orderby: Optional[str]=None, top: Optional[int]=None, skip: Optional[int]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpaceListResponse
818
+
819
+ # Search a memory space via LLMOps.
820
+ sdk.memory.search(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySearchResponse
821
+
822
+ # Asynchronously search a memory space via LLMOps.
823
+ sdk.memory.search_async(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySearchResponse
824
+
825
+ ```
826
+
827
+ ### Orchestrator Setup
828
+
829
+ Orchestrator Setup service
830
+
831
+ ```python
832
+ # Fire-and-forget POST requests to enable first run for StudioWeb.
833
+ sdk.orchestrator_setup.enable_first_run() -> None
834
+
835
+ # Fire-and-forget POST requests to enable first run for StudioWeb.
836
+ sdk.orchestrator_setup.enable_first_run_async() -> None
837
+
838
+ ```
839
+
840
+ ### Processes
841
+
842
+ Processes service
843
+
844
+ ```python
845
+ # Start execution of a process by its name.
846
+ sdk.processes.invoke(name: str, input_arguments: Optional[Dict[str, Any]]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, attachments: Optional[list[uipath.platform.attachments.attachments.Attachment]]=None, parent_operation_id: Optional[str]=None, run_as_me: Optional[bool]=None, **kwargs) -> uipath.platform.orchestrator.job.Job
847
+
848
+ # Asynchronously start execution of a process by its name.
849
+ sdk.processes.invoke_async(name: str, input_arguments: Optional[Dict[str, Any]]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, attachments: Optional[list[uipath.platform.attachments.attachments.Attachment]]=None, parent_operation_id: Optional[str]=None, run_as_me: Optional[bool]=None, **kwargs) -> uipath.platform.orchestrator.job.Job
850
+
851
+ ```
852
+
853
+ ### Queues
854
+
855
+ Queues service
856
+
857
+ ```python
858
+ # Completes a transaction item with the specified result.
859
+ sdk.queues.complete_transaction_item(transaction_key: str, result: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItemResult], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
860
+
861
+ # Asynchronously completes a transaction item with the specified result.
862
+ sdk.queues.complete_transaction_item_async(transaction_key: str, result: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItemResult], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
863
+
864
+ # Creates a new queue item in the Orchestrator.
865
+ sdk.queues.create_item(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
866
+
867
+ # Asynchronously creates a new queue item in the Orchestrator.
868
+ sdk.queues.create_item_async(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
869
+
870
+ # Creates multiple queue items in bulk.
871
+ sdk.queues.create_items(items: List[Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem]], queue_name: str, commit_type: <enum 'CommitType, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
872
+
873
+ # Asynchronously creates multiple queue items in bulk.
874
+ sdk.queues.create_items_async(items: List[Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem]], queue_name: str, commit_type: <enum 'CommitType, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
875
+
876
+ # Creates a new transaction item in a queue.
877
+ sdk.queues.create_transaction_item(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItem], queue_name: Optional[str]=None, no_robot: bool=False, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
878
+
879
+ # Asynchronously creates a new transaction item in a queue.
880
+ sdk.queues.create_transaction_item_async(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItem], queue_name: Optional[str]=None, no_robot: bool=False, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
881
+
882
+ # Retrieves a list of queue items from the Orchestrator.
883
+ sdk.queues.list_items(queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
884
+
885
+ # Asynchronously retrieves a list of queue items from the Orchestrator.
886
+ sdk.queues.list_items_async(queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
887
+
888
+ # Updates the progress of a transaction item.
889
+ sdk.queues.update_progress_of_transaction_item(transaction_key: str, progress: str, queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
890
+
891
+ # Asynchronously updates the progress of a transaction item.
892
+ sdk.queues.update_progress_of_transaction_item_async(transaction_key: str, progress: str, queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
893
+
894
+ ```
895
+
896
+ ### Remote A2A
897
+
898
+ Remote A2A service
899
+
900
+ ```python
901
+ # List Remote A2A agents.
902
+ sdk.remote_a2a.list(top: int | None=None, skip: int | None=None, search: str | None=None, folder_path: str | None=None) -> typing.List[uipath.platform.agenthub.remote_a2a.RemoteA2aAgent]
903
+
904
+ # Asynchronously list Remote A2A agents.
905
+ sdk.remote_a2a.list_async(top: int | None=None, skip: int | None=None, search: str | None=None, folder_path: str | None=None) -> typing.List[uipath.platform.agenthub.remote_a2a.RemoteA2aAgent]
906
+
907
+ # Retrieve a specific Remote A2A agent by slug.
908
+ sdk.remote_a2a.retrieve(slug: str, folder_path: str | None=None) -> uipath.platform.agenthub.remote_a2a.RemoteA2aAgent
909
+
910
+ # Asynchronously retrieve a specific Remote A2A agent by slug.
911
+ sdk.remote_a2a.retrieve_async(slug: str, folder_path: str | None=None) -> uipath.platform.agenthub.remote_a2a.RemoteA2aAgent
912
+
913
+ ```
914
+
915
+ ### Resource Catalog
916
+
917
+ Resource Catalog service
918
+
919
+ ```python
920
+ # Get tenant scoped resources and folder scoped resources (accessible to the user).
921
+ sdk.resource_catalog.list(resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
922
+
923
+ # Asynchronously get tenant scoped resources and folder scoped resources (accessible to the user).
924
+ sdk.resource_catalog.list_async(resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
925
+
926
+ # Get resources of a specific type (tenant scoped or folder scoped).
927
+ sdk.resource_catalog.list_by_type(resource_type: <enum 'ResourceType, name: Optional[str]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
928
+
929
+ # Asynchronously get resources of a specific type (tenant scoped or folder scoped).
930
+ sdk.resource_catalog.list_by_type_async(resource_type: <enum 'ResourceType, name: Optional[str]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
931
+
932
+ # Search for tenant scoped resources and folder scoped resources (accessible to the user).
933
+ sdk.resource_catalog.search(name: Optional[str]=None, resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
934
+
935
+ # Asynchronously search for tenant scoped resources and folder scoped resources (accessible to the user).
936
+ sdk.resource_catalog.search_async(name: Optional[str]=None, resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
937
+
938
+ ```
939
+
940
+ ### Semantic Proxy
941
+
942
+ Semantic Proxy service
943
+
944
+ ```python
945
+ # Detect PII in the provided documents and/or files.
946
+ sdk.semantic_proxy.detect_pii(request: uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionRequest) -> uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionResponse
947
+
948
+ # Detect PII in the provided documents and/or files (async).
949
+ sdk.semantic_proxy.detect_pii_async(request: uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionRequest) -> uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionResponse
950
+
951
+ ```
952
+
953
+ ### Tasks
954
+
955
+ Tasks service
956
+
957
+ ```python
958
+ # Creates a new task synchronously.
959
+ sdk.tasks.create(title: str, data: Optional[Dict[str, Any]]=None, app_name: Optional[str]=None, app_key: Optional[str]=None, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, assignee: Optional[str]=None, recipient: Optional[uipath.platform.action_center.tasks.TaskRecipient]=None, priority: Optional[str]=None, labels: Optional[List[str]]=None, is_actionable_message_enabled: Optional[bool]=None, actionable_message_metadata: Optional[Dict[str, Any]]=None, source_name: str="Agent") -> uipath.platform.action_center.tasks.Task
960
+
961
+ # Creates a new action asynchronously.
962
+ sdk.tasks.create_async(title: str, data: Optional[Dict[str, Any]]=None, app_name: Optional[str]=None, app_key: Optional[str]=None, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, assignee: Optional[str]=None, recipient: Optional[uipath.platform.action_center.tasks.TaskRecipient]=None, priority: Optional[str]=None, labels: Optional[List[str]]=None, is_actionable_message_enabled: Optional[bool]=None, actionable_message_metadata: Optional[Dict[str, Any]]=None, source_name: str="Agent") -> uipath.platform.action_center.tasks.Task
963
+
964
+ # Retrieves a task by its key synchronously.
965
+ sdk.tasks.retrieve(action_key: str, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, app_name: str | None=None) -> uipath.platform.action_center.tasks.Task
966
+
967
+ # Retrieves a task by its key asynchronously.
968
+ sdk.tasks.retrieve_async(action_key: str, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, app_name: str | None=None) -> uipath.platform.action_center.tasks.Task
969
+
970
+ ```
971
+
agents/agent_2_investigation_api/.claude/commands/eval.md ADDED
@@ -0,0 +1,287 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ allowed-tools: Bash, Read, Write, Edit, Glob
3
+ description: Create and run agent evaluations
4
+ ---
5
+
6
+ I'll help you create and run evaluations for your UiPath agent.
7
+
8
+ ## Step 1: Check project setup
9
+
10
+ Let me check your project structure:
11
+
12
+ !ls -la evaluations/ entry-points.json 2>/dev/null || echo "NEEDS_SETUP"
13
+
14
+ # Check if schemas might be stale (main.py newer than entry-points.json)
15
+ !if [ -f main.py ] && [ -f entry-points.json ] && [ main.py -nt entry-points.json ]; then echo "SCHEMAS_MAY_BE_STALE"; fi
16
+
17
+ ### If NEEDS_SETUP
18
+
19
+ If `entry-points.json` doesn't exist, initialize the project first:
20
+
21
+ !uv run uipath init
22
+
23
+ Then re-run this skill.
24
+
25
+ ### If SCHEMAS_MAY_BE_STALE
26
+
27
+ Your `main.py` is newer than `entry-points.json`. Refresh schemas:
28
+
29
+ !uv run uipath init --no-agents-md-override
30
+
31
+ ## Step 2: What would you like to do?
32
+
33
+ 1. **Create new eval set** - Set up evaluations from scratch
34
+ 2. **Add test case** - Add a test to existing eval set
35
+ 3. **Run evaluations** - Execute tests and see results
36
+ 4. **Analyze failures** - Debug failing tests
37
+
38
+ ---
39
+
40
+ ## Creating an Eval Set
41
+
42
+ First, create the directory structure:
43
+
44
+ !mkdir -p evaluations/eval-sets evaluations/evaluators
45
+
46
+ Read the agent's Input/Output schema from entry-points.json to understand the data types.
47
+
48
+ ### Evaluator Selection Guide
49
+
50
+ | If your output is... | Use this evaluator | evaluatorTypeId |
51
+ |---------------------|-------------------|-----------------|
52
+ | Exact string/number | `ExactMatchEvaluator` | `uipath-exact-match` |
53
+ | Contains key phrases | `ContainsEvaluator` | `uipath-contains` |
54
+ | Semantically correct | `LLMJudgeOutputEvaluator` | `uipath-llm-judge-output-semantic-similarity` |
55
+ | JSON with numbers | `JsonSimilarityEvaluator` | `uipath-json-similarity` |
56
+
57
+ ### Step 1: Create Evaluator Config Files
58
+
59
+ **Each evaluator needs a JSON config file** in `evaluations/evaluators/`.
60
+
61
+ **ExactMatchEvaluator** (`evaluations/evaluators/exact-match.json`):
62
+ ```json
63
+ {
64
+ "version": "1.0",
65
+ "id": "ExactMatchEvaluator",
66
+ "name": "ExactMatchEvaluator",
67
+ "description": "Checks for exact output match",
68
+ "evaluatorTypeId": "uipath-exact-match",
69
+ "evaluatorConfig": {
70
+ "name": "ExactMatchEvaluator",
71
+ "targetOutputKey": "*"
72
+ }
73
+ }
74
+ ```
75
+
76
+ **LLMJudgeOutputEvaluator** (`evaluations/evaluators/llm-judge-output.json`):
77
+ ```json
78
+ {
79
+ "version": "1.0",
80
+ "id": "LLMJudgeOutputEvaluator",
81
+ "name": "LLMJudgeOutputEvaluator",
82
+ "description": "Uses LLM to judge semantic similarity",
83
+ "evaluatorTypeId": "uipath-llm-judge-output-semantic-similarity",
84
+ "evaluatorConfig": {
85
+ "name": "LLMJudgeOutputEvaluator",
86
+ "model": "gpt-4o-mini-2024-07-18"
87
+ }
88
+ }
89
+ ```
90
+
91
+ **JsonSimilarityEvaluator** (`evaluations/evaluators/json-similarity.json`):
92
+ ```json
93
+ {
94
+ "version": "1.0",
95
+ "id": "JsonSimilarityEvaluator",
96
+ "name": "JsonSimilarityEvaluator",
97
+ "description": "Compares JSON structures",
98
+ "evaluatorTypeId": "uipath-json-similarity",
99
+ "evaluatorConfig": {
100
+ "name": "JsonSimilarityEvaluator",
101
+ "targetOutputKey": "*"
102
+ }
103
+ }
104
+ ```
105
+
106
+ **ContainsEvaluator** (`evaluations/evaluators/contains.json`):
107
+ ```json
108
+ {
109
+ "version": "1.0",
110
+ "id": "ContainsEvaluator",
111
+ "name": "ContainsEvaluator",
112
+ "description": "Checks if output contains text",
113
+ "evaluatorTypeId": "uipath-contains",
114
+ "evaluatorConfig": {
115
+ "name": "ContainsEvaluator"
116
+ }
117
+ }
118
+ ```
119
+
120
+ ### Step 2: Create Eval Set
121
+
122
+ **Eval Set Template** (`evaluations/eval-sets/default.json`):
123
+ ```json
124
+ {
125
+ "version": "1.0",
126
+ "id": "default-eval-set",
127
+ "name": "Default Evaluation Set",
128
+ "evaluatorRefs": ["ExactMatchEvaluator"],
129
+ "evaluations": [
130
+ {
131
+ "id": "test-1",
132
+ "name": "Test description",
133
+ "inputs": {
134
+ "field": "value"
135
+ },
136
+ "evaluationCriterias": {
137
+ "ExactMatchEvaluator": {
138
+ "expectedOutput": {
139
+ "result": "expected value"
140
+ }
141
+ }
142
+ }
143
+ }
144
+ ]
145
+ }
146
+ ```
147
+
148
+ **Important notes:**
149
+ - `evaluatorRefs` must list ALL evaluators used in any test case
150
+ - Each evaluator in `evaluatorRefs` needs a matching JSON config in `evaluations/evaluators/`
151
+ - `evaluationCriterias` keys must match entries in `evaluatorRefs`
152
+ - Use `expectedOutput` for most evaluators
153
+ - LLM evaluators need `model` in their config. Available models are defined in the SDK's `ChatModels` class (`uipath.platform.chat.ChatModels`):
154
+ - `gpt-4o-mini-2024-07-18` (recommended for cost-efficiency)
155
+ - `gpt-4o-2024-08-06` (higher quality, higher cost)
156
+ - `o3-mini-2025-01-31` (latest reasoning model)
157
+ - Model availability varies by region and tenant configuration
158
+ - Check your UiPath Automation Cloud portal under AI Trust Layer for available models in your region
159
+
160
+ ---
161
+
162
+ ## Adding a Test Case
163
+
164
+ When adding a test to an existing eval set:
165
+
166
+ 1. Read the existing eval set
167
+ 2. Check which evaluators are in `evaluatorRefs`
168
+ 3. Add the new test to `evaluations` array
169
+ 4. If using a new evaluator, add it to `evaluatorRefs`
170
+
171
+ ### Test Case Template
172
+
173
+ ```json
174
+ {
175
+ "id": "test-{n}",
176
+ "name": "Description of what this tests",
177
+ "inputs": { },
178
+ "evaluationCriterias": {
179
+ "EvaluatorName": {
180
+ "expectedOutput": { }
181
+ }
182
+ }
183
+ }
184
+ ```
185
+
186
+ ---
187
+
188
+ ## Running Evaluations
189
+
190
+ First, read entry-points.json to get the entrypoint name (e.g., `main`):
191
+
192
+ !uv run uipath eval main evaluations/eval-sets/default.json --output-file eval-results.json
193
+
194
+ **Note:** Replace `main` with your actual entrypoint from entry-points.json.
195
+
196
+ ### Analyze Results
197
+
198
+ After running, read `eval-results.json` and show:
199
+ - Pass/fail summary table
200
+ - For failures: expected vs actual output
201
+ - Suggestions for fixing or changing evaluators
202
+
203
+ ### Results Format
204
+
205
+ ```json
206
+ {
207
+ "evaluationSetResults": [{
208
+ "evaluationRunResults": [
209
+ {
210
+ "evaluationId": "test-1",
211
+ "evaluatorId": "ExactMatchEvaluator",
212
+ "result": { "score": 1.0 },
213
+ "errorMessage": null
214
+ }
215
+ ]
216
+ }]
217
+ }
218
+ ```
219
+
220
+ - Score 1.0 = PASS
221
+ - Score < 1.0 = FAIL (show expected vs actual)
222
+ - errorMessage present = ERROR (show message)
223
+
224
+ ---
225
+
226
+ ## Evaluator Reference
227
+
228
+ ### Deterministic Evaluators
229
+
230
+ **ExactMatchEvaluator** - Exact output matching
231
+ ```json
232
+ "ExactMatchEvaluator": {
233
+ "expectedOutput": { "result": "exact value" }
234
+ }
235
+ ```
236
+
237
+ **ContainsEvaluator** - Output contains substring
238
+ ```json
239
+ "ContainsEvaluator": {
240
+ "searchText": "must contain this"
241
+ }
242
+ ```
243
+
244
+ **JsonSimilarityEvaluator** - JSON comparison with tolerance
245
+ ```json
246
+ "JsonSimilarityEvaluator": {
247
+ "expectedOutput": { "value": 10.0 }
248
+ }
249
+ ```
250
+
251
+ ### LLM-Based Evaluators
252
+
253
+ **LLMJudgeOutputEvaluator** - Semantic correctness
254
+ ```json
255
+ "LLMJudgeOutputEvaluator": {
256
+ "expectedOutput": { "summary": "Expected semantic meaning" }
257
+ }
258
+ ```
259
+
260
+ **LLMJudgeTrajectoryEvaluator** - Validate agent reasoning
261
+ ```json
262
+ "LLMJudgeTrajectoryEvaluator": {
263
+ "expectedAgentBehavior": "The agent should first fetch data, then process it"
264
+ }
265
+ ```
266
+
267
+ ---
268
+
269
+ ## Common Issues
270
+
271
+ ### "No evaluations found"
272
+ - Check `evaluations/eval-sets/` directory exists
273
+ - Verify JSON file is valid
274
+
275
+ ### Evaluator not found
276
+ - Each evaluator needs a JSON config file in `evaluations/evaluators/`
277
+ - Config file must have correct `evaluatorTypeId` (see templates above)
278
+ - Config file must have `name` field at root level
279
+ - LLM evaluators need `model` in `evaluatorConfig`
280
+
281
+ ### Evaluator skipped
282
+ - Ensure evaluator is listed in root `evaluatorRefs` array
283
+ - Check evaluator config file exists in `evaluations/evaluators/`
284
+
285
+ ### Schema mismatch
286
+ - Run `uv run uipath init --no-agents-md-override` to refresh schemas
287
+ - Check `entry-points.json` matches your Input/Output models
agents/agent_2_investigation_api/.claude/commands/new-agent.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ allowed-tools: Bash, Read, Write, Edit, Glob
3
+ description: Create a new UiPath coded agent from a description
4
+ ---
5
+
6
+ I'll help you create a new UiPath coded agent.
7
+
8
+ ## Step 1: Check existing project
9
+
10
+ Let me check if this is an existing UiPath project:
11
+
12
+ !ls uipath.json main.py 2>/dev/null || echo "NEW_PROJECT"
13
+
14
+ ## Step 2: Gather requirements
15
+
16
+ **What should this agent do?**
17
+
18
+ Please describe:
19
+
20
+ - What inputs it needs (e.g., "a file path and bucket name")
21
+ - What it should accomplish (e.g., "process CSV data")
22
+ - What outputs it should return (e.g., "total count and status")
23
+
24
+ I'll generate the agent structure based on your description.
25
+
26
+ ## Step 3: Generate agent
27
+
28
+ After you describe the agent, I will:
29
+
30
+ 1. Create `main.py` with Input/Output Pydantic models and `async def main()`
31
+ 2. Add entrypoint to `uipath.json` under `"functions": {"agent_name": "main.py:main"}`
32
+ 3. Run `uv run uipath init --no-agents-md-override` to generate schemas
33
+
34
+ **Template structure** (from .agent/REQUIRED_STRUCTURE.md):
35
+
36
+ ```python
37
+ from pydantic import BaseModel
38
+ from uipath.platform import UiPath
39
+
40
+ class Input(BaseModel):
41
+ """Input fields for the agent."""
42
+ # Fields based on your description
43
+ pass
44
+
45
+
46
+ class Output(BaseModel):
47
+ """Output fields returned by the agent."""
48
+ # Fields based on your description
49
+ pass
50
+
51
+
52
+ async def main(input: Input) -> Output:
53
+ """Main entry point for the agent.
54
+
55
+ Args:
56
+ input: The input data for the agent.
57
+
58
+ Returns:
59
+ The output data from the agent.
60
+ """
61
+
62
+ uipath = UiPath()
63
+
64
+ # TODO: Implement agent logic
65
+ return Output()
66
+ ```
67
+
68
+ **Important notes:**
69
+
70
+ - Use `async def main` - many SDK methods are async
71
+ - Initialize `UiPath()` inside the function, not at module level
72
+ - After creating main.py, add entrypoint to `uipath.json` under `"functions"`
73
+
74
+ ## Step 4: Update entry-point schemas
75
+
76
+ After creating main.py, regenerate the schemas:
77
+
78
+ !uv run uipath init --no-agents-md-override
79
+
80
+ ## Step 5: Verify
81
+
82
+ Quick test to verify the setup:
83
+
84
+ !uv run uipath run main '{}' 2>&1 | head -30
85
+
86
+ ## Summary
87
+
88
+ Once complete, you'll have:
89
+
90
+ | File | Purpose |
91
+ | ------------------- | ----------------------------------- |
92
+ | `main.py` | Agent code with Input/Output models |
93
+ | `uipath.json` | Project configuration |
94
+ | `entry-points.json` | Entry point schemas |
95
+ | `bindings.json` | Resource bindings |
96
+ | `.agent/` | SDK and CLI reference docs |
97
+
98
+ **Next steps:**
99
+
100
+ 1. Implement your logic in `main()`
101
+ 2. Test: `uv run uipath run main '{"field": "value"}'`
102
+ 3. Create `eval_set.json` for evaluations
103
+ 4. Evaluate: `uv run uipath eval`
agents/agent_2_investigation_api/.env ADDED
File without changes
agents/agent_2_investigation_api/.uipath/.telemetry.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "ProjectKey": "71315e07-2daa-4f0e-b80e-d5aad6444002"
3
+ }
agents/agent_2_investigation_api/.uipath/studio_metadata.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "schemaVersion": 1,
3
+ "codeVersion": "1.0.0"
4
+ }
agents/agent_2_investigation_api/AGENTS.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ # Agent Code Patterns Reference
2
+
3
+ This document provides practical code patterns for building UiPath coded agents using the UiPath Python SDK.
4
+
5
+ ---
6
+
7
+ ## Documentation Structure
8
+
9
+ This documentation is split into multiple files for efficient context loading. Load only the files you need:
10
+
11
+ 1. **@.agent/REQUIRED_STRUCTURE.md** - Agent structure patterns and templates
12
+ - **When to load:** Creating a new agent or understanding required patterns
13
+ - **Contains:** Required Pydantic models (Input, Output), SDK initialization patterns, standard agent template
14
+
15
+ 2. **@.agent/SDK_REFERENCE.md** - Complete SDK API reference
16
+ - **When to load:** Calling UiPath SDK methods, working with services (actions, assets, jobs, etc.)
17
+ - **Contains:** All SDK services and methods with full signatures and type annotations
18
+
19
+ 3. **@.agent/CLI_REFERENCE.md** - CLI commands documentation
20
+ - **When to load:** Working with `uipath init`, `uipath run`, or `uipath eval` commands
21
+ - **Contains:** Command syntax, options, usage examples, and workflows
agents/agent_2_investigation_api/__pycache__/main.cpython-313.pyc ADDED
Binary file (3.19 kB). View file
 
agents/agent_2_investigation_api/agent_2_investigation_api.mermaid ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ %% AUTO-GENERATED by `uipath init`. Do not edit manually.
2
+ %% Regenerated on every `uipath init`.
3
+ flowchart TB
4
+ main.py:56(main)
agents/agent_2_investigation_api/bindings.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "version": "2.0",
3
+ "resources": []
4
+ }
agents/agent_2_investigation_api/entry-points.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "$schema": "https://cloud.uipath.com/draft/2024-12/entry-point",
3
+ "$id": "entry-points.json",
4
+ "entryPoints": [
5
+ {
6
+ "filePath": "agent_2_investigation_api",
7
+ "uniqueId": "1e9a65bb-24e1-4fa3-af9d-8cef2d6b7b9b",
8
+ "type": "agent",
9
+ "input": {
10
+ "type": "object"
11
+ },
12
+ "output": {
13
+ "type": "object"
14
+ },
15
+ "graph": {
16
+ "nodes": [
17
+ {
18
+ "id": "main.py:56",
19
+ "name": "main",
20
+ "type": "function",
21
+ "metadata": {
22
+ "file": "main.py"
23
+ }
24
+ }
25
+ ],
26
+ "edges": []
27
+ }
28
+ }
29
+ ]
30
+ }
agents/agent_2_investigation_api/main.py ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ import json
2
+ import requests
3
+ from typing import TypedDict
4
+ from langgraph.graph import StateGraph, START, END
5
+
6
+ class AgentState(TypedDict):
7
+ case_id: str
8
+ risk_score: int
9
+ sar_narrative: str
10
+
11
+ def call_api(state: AgentState):
12
+ case_id = state.get("case_id", "CASE-123")
13
+
14
+ # Payload for the backend investigation pipeline
15
+ payload = {
16
+ "case_id": case_id,
17
+ "alert_type": "SUSPECTED_LAYERING",
18
+ "transactions": [
19
+ {"txn_id":"TXN-201","date":"2024-05-10T09:00:00Z","amount":250000,"type":"WIRE_IN","originator":{"name":"Unknown Entity A","country":"Cayman Islands","account":"CY-999123"},"beneficiary":{"account":"ACC-554433"}},
20
+ {"txn_id":"TXN-202","date":"2024-05-11T11:30:00Z","amount":120000,"type":"WIRE_OUT","originator":{"account":"ACC-554433"},"beneficiary":{"name":"Shell Corp B","country":"Panama","account":"PA-888456"}},
21
+ {"txn_id":"TXN-203","date":"2024-05-11T14:45:00Z","amount":125000,"type":"WIRE_OUT","originator":{"account":"ACC-554433"},"beneficiary":{"name":"Holdings C","country":"Cyprus","account":"CP-777789"}}
22
+ ],
23
+ "force_api_failure": False
24
+ }
25
+
26
+ import os
27
+ url = os.getenv("API_BASE_URL", "http://localhost:8000/api/investigate")
28
+ headers = {
29
+ "Content-Type": "application/json",
30
+ "ngrok-skip-browser-warning": "true"
31
+ }
32
+
33
+ try:
34
+ response = requests.post(url, json=payload, headers=headers)
35
+ response.raise_for_status()
36
+ data = response.json()
37
+
38
+ return {
39
+ "risk_score": data.get("final_risk_score", 85),
40
+ "sar_narrative": data.get("sar_narrative", "API connection succeeded but narrative missing.")
41
+ }
42
+ except Exception as e:
43
+ return {
44
+ "risk_score": 99,
45
+ "sar_narrative": f"API Error: {str(e)}"
46
+ }
47
+
48
+ workflow = StateGraph(AgentState)
49
+ workflow.add_node("call_api", call_api)
50
+ workflow.add_edge(START, "call_api")
51
+ workflow.add_edge("call_api", END)
52
+ graph = workflow.compile()
53
+
54
+ def main(args: dict):
55
+ initial_state = {"case_id": args.get("case_id", "CASE-DEFAULT")}
56
+ final_state = graph.invoke(initial_state)
57
+ return {
58
+ "case_id": final_state.get("case_id"),
59
+ "risk_score": final_state.get("risk_score"),
60
+ "sar_narrative": final_state.get("sar_narrative")
61
+ }
agents/agent_2_investigation_api/project.uiproj ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "ProjectType": "Agent",
3
+ "Name": "agent_2_investigation_api",
4
+ "Description": "Calls the local FastAPI investigation endpoint",
5
+ "MainFile": null
6
+ }
agents/agent_2_investigation_api/pyproject.toml ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [project]
2
+ name = "agent_2_investigation_api"
3
+ version = "0.0.1"
4
+ authors = [{ name = "SentinelFin Team" }]
5
+ description = "Calls the local FastAPI investigation endpoint"
6
+ requires-python = ">=3.11"
7
+ dependencies = [
8
+ "requests",
9
+ "langgraph",
10
+ "typing_extensions"
11
+ ]
12
+
13
+ [build-system]
14
+ requires = ["hatchling"]
15
+ build-backend = "hatchling.build"
agents/agent_2_investigation_api/uipath.json ADDED
@@ -0,0 +1,8 @@
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "project_id": "agent_2_investigation_api",
3
+ "project_name": "agent_2_investigation_api",
4
+ "project_type": "Agent",
5
+ "agents": {
6
+ "agent_2_investigation_api": "main.py:main"
7
+ }
8
+ }
agents/agent_2_sanctions_screener/.agent/CLI_REFERENCE.md ADDED
@@ -0,0 +1,949 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## CLI Commands Reference
2
+
3
+ The UiPath Python SDK provides a comprehensive CLI for managing coded agents and automation projects. All commands should be executed with `uv run uipath <command>`.
4
+
5
+ ### Command Overview
6
+
7
+ | Command | Purpose | When to Use |
8
+ |---------|---------|-------------|
9
+ | `init` | Initialize agent project | Creating a new agent or updating schema |
10
+ | `run` | Execute agent | Running agent locally or testing |
11
+ | `eval` | Evaluate agent | Testing agent performance with evaluation sets |
12
+
13
+ ---
14
+
15
+ ### `uipath init`
16
+
17
+ **Description:** Initialize the project.
18
+
19
+ **Options:**
20
+
21
+ | Option | Type | Default | Description |
22
+ |--------|------|---------|-------------|
23
+ | `--no-agents-md-override` | flag | false | Won't override existing .agent files and AGENTS.md file. |
24
+
25
+ **Usage Examples:**
26
+
27
+ ```bash
28
+ # Initialize a new agent project
29
+ uv run uipath init
30
+
31
+ # Initialize with specific entrypoint
32
+ uv run uipath init main.py
33
+
34
+ # Initialize and infer bindings from code
35
+ uv run uipath init --infer-bindings
36
+ ```
37
+
38
+ **When to use:** Run this command when you've modified the Input/Output models and need to regenerate the `uipath.json` schema file.
39
+
40
+ ---
41
+
42
+ ### `uipath run`
43
+
44
+ **Description:** Execute the project.
45
+
46
+ **Arguments:**
47
+
48
+ | Argument | Required | Description |
49
+ |----------|----------|-------------|
50
+ | `entrypoint` | No | N/A |
51
+ | `input` | No | N/A |
52
+
53
+ **Options:**
54
+
55
+ | Option | Type | Default | Description |
56
+ |--------|------|---------|-------------|
57
+ | `--resume` | flag | false | Resume execution from a previous state |
58
+ | `-f`, `--file` | value | `Sentinel.UNSET` | File path for the .json input |
59
+ | `--input-file` | value | `Sentinel.UNSET` | Alias for '-f/--file' arguments |
60
+ | `--output-file` | value | `Sentinel.UNSET` | File path where the output will be written |
61
+ | `--trace-file` | value | `Sentinel.UNSET` | File path where the trace spans will be written (JSON Lines format) |
62
+ | `--state-file` | value | `Sentinel.UNSET` | File path where the state file is stored for persisting execution state. If not provided, a temporary file will be used. |
63
+ | `--debug` | flag | false | Enable debugging with debugpy. The process will wait for a debugger to attach. |
64
+ | `--debug-port` | value | `5678` | Port for the debug server (default: 5678) |
65
+ | `--keep-state-file` | flag | false | Keep the temporary state file even when not resuming and no job id is provided |
66
+ | `--simulation` | value | none | Simulation config as a JSON object (same schema as simulation.json) |
67
+
68
+ **Usage Examples:**
69
+
70
+ ```bash
71
+ # Run agent with inline JSON input
72
+ uv run uipath run main.py '{"query": "What is the weather?"}'
73
+
74
+ # Run agent with input from file
75
+ uv run uipath run main.py --file input.json
76
+
77
+ # Run agent and save output to file
78
+ uv run uipath run agent '{"task": "Process data"}' --output-file result.json
79
+
80
+ # Run agent with debugging enabled
81
+ uv run uipath run main.py '{"input": "test"}' --debug --debug-port 5678
82
+
83
+ # Resume agent execution from previous state
84
+ uv run uipath run --resume
85
+ ```
86
+
87
+ **When to use:** Run this command to execute your agent locally for development, testing, or debugging. Use `--debug` flag to attach a debugger for step-by-step debugging.
88
+
89
+ ---
90
+
91
+ ### `uipath eval`
92
+
93
+ **Description:** Run an evaluation set against the agent.
94
+
95
+ Args:
96
+ entrypoint: Path to the agent script to evaluate (optional, will auto-discover if not specified)
97
+ eval_set: Path to the evaluation set JSON file (optional, will auto-discover if not specified)
98
+ eval_ids: Optional list of evaluation IDs
99
+ eval_set_run_id: Custom evaluation set run ID (optional, will generate UUID if not specified)
100
+ workers: Number of parallel workers for running evaluations
101
+ no_report: Do not report the evaluation results
102
+ enable_mocker_cache: Enable caching for LLM mocker responses
103
+ report_coverage: Report evaluation coverage
104
+ model_settings_id: Model settings ID to override agent settings
105
+ trace_file: File path where traces will be written in JSONL format
106
+ max_llm_concurrency: Maximum concurrent LLM requests
107
+ input_overrides: Input field overrides mapping (direct field override with deep merge)
108
+ resume: Resume execution from a previous suspended state
109
+
110
+
111
+ **Arguments:**
112
+
113
+ | Argument | Required | Description |
114
+ |----------|----------|-------------|
115
+ | `entrypoint` | No | N/A |
116
+ | `eval_set` | No | N/A |
117
+
118
+ **Options:**
119
+
120
+ | Option | Type | Default | Description |
121
+ |--------|------|---------|-------------|
122
+ | `--eval-set-run-id` | value | `Sentinel.UNSET` | Custom evaluation set run ID (if not provided, a UUID will be generated) |
123
+ | `--no-report` | flag | false | Do not report the evaluation results |
124
+ | `--workers` | value | `1` | Number of parallel workers for running evaluations (default: 1) |
125
+ | `--output-file` | value | `Sentinel.UNSET` | File path where the output will be written |
126
+ | `--enable-mocker-cache` | flag | false | Enable caching for LLM mocker responses |
127
+ | `--report-coverage` | flag | false | Report evaluation coverage |
128
+ | `--model-settings-id` | value | `"default"` | Model settings ID from evaluation set to override agent settings (default: 'default') |
129
+ | `--trace-file` | value | `Sentinel.UNSET` | File path where traces will be written in JSONL format |
130
+ | `--max-llm-concurrency` | value | `20` | Maximum concurrent LLM requests (default: 20) |
131
+ | `--resume` | flag | false | Resume execution from a previous suspended state |
132
+ | `--verbose` | flag | false | Include agent execution output (trace, result) in the output file |
133
+
134
+ **Usage Examples:**
135
+
136
+ ```bash
137
+ # Run evaluation with auto-discovered files
138
+ uv run uipath eval
139
+
140
+ # Run evaluation with specific entrypoint and eval set
141
+ uv run uipath eval main.py eval_set.json
142
+
143
+ # Run evaluation without reporting results
144
+ uv run uipath eval --no-report
145
+
146
+ # Run evaluation with custom number of workers
147
+ uv run uipath eval --workers 4
148
+
149
+ # Save evaluation output to file
150
+ uv run uipath eval --output-file eval_results.json
151
+ ```
152
+
153
+ **When to use:** Run this command to test your agent's performance against a predefined evaluation set. This helps validate agent behavior and measure quality metrics.
154
+
155
+ ---
156
+
157
+ ### Common Workflows
158
+
159
+ **1. Creating a New Agent:**
160
+ ```bash
161
+ # Step 1: Initialize project
162
+ uv run uipath init
163
+
164
+ # Step 2: Run agent to test
165
+ uv run uipath run main.py '{"input": "test"}'
166
+
167
+ # Step 3: Evaluate agent performance
168
+ uv run uipath eval
169
+ ```
170
+
171
+ **2. Development & Testing:**
172
+ ```bash
173
+ # Run with debugging
174
+ uv run uipath run main.py '{"input": "test"}' --debug
175
+
176
+ # Test with input file
177
+ uv run uipath run main.py --file test_input.json --output-file test_output.json
178
+ ```
179
+
180
+ **3. Schema Updates:**
181
+ ```bash
182
+ # After modifying Input/Output models, regenerate schema
183
+ uv run uipath init --infer-bindings
184
+ ```
185
+
186
+ ### Configuration File (uipath.json)
187
+
188
+ The `uipath.json` file is automatically generated by `uipath init` and defines your agent's schema and bindings.
189
+
190
+ **Structure:**
191
+
192
+ ```json
193
+ {
194
+ "entryPoints": [
195
+ {
196
+ "filePath": "agent",
197
+ "uniqueId": "uuid-here",
198
+ "type": "agent",
199
+ "input": {
200
+ "type": "object",
201
+ "properties": { ... },
202
+ "description": "Input schema",
203
+ "required": [ ... ]
204
+ },
205
+ "output": {
206
+ "type": "object",
207
+ "properties": { ... },
208
+ "description": "Output schema",
209
+ "required": [ ... ]
210
+ }
211
+ }
212
+ ],
213
+ "bindings": {
214
+ "version": "2.0",
215
+ "resources": []
216
+ }
217
+ }
218
+ ```
219
+
220
+ **When to Update:**
221
+
222
+ 1. **After Modifying Input/Output Models**: Run `uv run uipath init --infer-bindings` to regenerate schemas
223
+ 2. **Changing Entry Point**: Update `filePath` if you rename or move your main file
224
+ 3. **Manual Schema Adjustments**: Edit `input.jsonSchema` or `output.jsonSchema` directly if needed
225
+ 4. **Bindings Updates**: The `bindings` section maps the exported graph variable - update if you rename your graph
226
+
227
+ **Important Notes:**
228
+
229
+ - The `uniqueId` should remain constant for the same agent
230
+ - Always use `type: "agent"` for LangGraph agents
231
+ - The `jsonSchema` must match your Pydantic models exactly
232
+ - Re-run `uipath init --infer-bindings` instead of manual edits when possible
233
+
234
+
235
+ ## Service Commands Reference
236
+
237
+ The UiPath CLI provides commands for interacting with UiPath platform services. These commands allow you to manage buckets, assets, jobs, and other resources.
238
+
239
+ ### `uipath assets`
240
+
241
+ Manage UiPath assets.
242
+
243
+ Assets are key-value pairs that store configuration data, credentials,
244
+ and settings used by automation processes.
245
+
246
+ \b
247
+ Examples:
248
+ # List all assets in a folder
249
+ uipath assets list --folder-path "Shared"
250
+
251
+ # List with filter
252
+ uipath assets list --filter "ValueType eq 'Text'"
253
+
254
+ # List with ordering
255
+ uipath assets list --orderby "Name asc"
256
+
257
+
258
+ **Subcommands:**
259
+
260
+ **`uipath assets list`**
261
+
262
+ List assets in a folder.
263
+
264
+ \b
265
+ Examples:
266
+ uipath assets list
267
+ uipath assets list --folder-path "Shared"
268
+ uipath assets list --filter "ValueType eq 'Text'"
269
+ uipath assets list --filter "Name eq 'MyAsset'"
270
+ uipath assets list --orderby "Name asc"
271
+ uipath assets list --top 50 --skip 100
272
+
273
+
274
+ Options:
275
+ - `--filter`: OData $filter expression (default: `Sentinel.UNSET`)
276
+ - `--orderby`: OData $orderby expression (default: `Sentinel.UNSET`)
277
+ - `--top`: Maximum number of items to return (default: 100, max: 1000) (default: `100`)
278
+ - `--skip`: Number of items to skip (default: `0`)
279
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
280
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
281
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
282
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
283
+
284
+ ---
285
+
286
+ ### `uipath buckets`
287
+
288
+ Manage UiPath storage buckets and files.
289
+
290
+ Buckets are cloud storage containers for files used by automation processes.
291
+
292
+ 
293
+ Bucket Operations:
294
+ list - List all buckets
295
+ create - Create a new bucket
296
+ delete - Delete a bucket
297
+ retrieve - Get bucket details
298
+ exists - Check if bucket exists
299
+
300
+ 
301
+ File Operations (use 'buckets files' subcommand):
302
+ files list - List files in a bucket
303
+ files search - Search files using glob patterns
304
+ files upload - Upload a file to a bucket
305
+ files download - Download a file from a bucket
306
+ files delete - Delete a file from a bucket
307
+ files exists - Check if a file exists
308
+
309
+ 
310
+ Examples:
311
+ 
312
+ # Bucket operations with explicit folder
313
+ uipath buckets list --folder-path "Shared"
314
+ uipath buckets create my-bucket --description "Data storage"
315
+ uipath buckets exists my-bucket
316
+ uipath buckets delete my-bucket --confirm
317
+ 
318
+ # Using environment variable for folder context
319
+ export UIPATH_FOLDER_PATH="Shared"
320
+ uipath buckets list
321
+ uipath buckets create my-bucket --description "Data storage"
322
+ 
323
+ # File operations
324
+ uipath buckets files list my-bucket
325
+ uipath buckets files search my-bucket "*.pdf"
326
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
327
+ uipath buckets files download my-bucket data.csv ./local.csv
328
+ uipath buckets files delete my-bucket old-data.csv --confirm
329
+ uipath buckets files exists my-bucket data.csv
330
+
331
+
332
+ **Subcommands:**
333
+
334
+ **`uipath buckets create`**
335
+
336
+ Create a new Bucket.
337
+
338
+ Examples:
339
+ uipath buckets create my-resource
340
+ uipath buckets create my-resource --folder-path Shared
341
+
342
+
343
+ Arguments:
344
+ - `name` (required): N/A
345
+
346
+ Options:
347
+ - `--description`: Bucket description
348
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
349
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
350
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
351
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
352
+
353
+ **`uipath buckets delete`**
354
+
355
+ Delete a bucket.
356
+
357
+ 
358
+ Examples:
359
+ uipath buckets delete my-bucket --confirm
360
+ uipath buckets delete my-bucket --dry-run
361
+
362
+
363
+ Arguments:
364
+ - `name` (required): N/A
365
+
366
+ Options:
367
+ - `--confirm`: Skip confirmation prompt
368
+ - `--dry-run`: Show what would be deleted without deleting
369
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
370
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
371
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
372
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
373
+
374
+ **`uipath buckets exists`**
375
+
376
+ Check if a Bucket exists.
377
+
378
+ Examples:
379
+ uipath buckets exists my-resource
380
+ uipath buckets exists my-resource --folder-path Shared
381
+
382
+
383
+ Arguments:
384
+ - `name` (required): N/A
385
+
386
+ Options:
387
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
388
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
389
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
390
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
391
+
392
+ #### `uipath buckets files`
393
+
394
+ Manage files within buckets.
395
+
396
+ 
397
+ Examples:
398
+ 
399
+ # List files in a bucket
400
+ uipath buckets files list my-bucket
401
+ 
402
+ # Search for files with glob pattern
403
+ uipath buckets files search my-bucket "*.pdf"
404
+ 
405
+ # Upload a file
406
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
407
+ 
408
+ # Download a file
409
+ uipath buckets files download my-bucket data.csv ./local.csv
410
+ 
411
+ # Delete a file
412
+ uipath buckets files delete my-bucket old-data.csv --confirm
413
+ 
414
+ # Check if file exists
415
+ uipath buckets files exists my-bucket data.csv
416
+
417
+
418
+ **`uipath buckets files delete`**
419
+
420
+ Delete a file from a bucket.
421
+
422
+ 
423
+ Arguments:
424
+ BUCKET_NAME: Name of the bucket
425
+ FILE_PATH: Path to file in bucket
426
+
427
+ 
428
+ Examples:
429
+ uipath buckets files delete my-bucket old-data.csv --confirm
430
+ uipath buckets files delete reports archive/old.pdf --dry-run
431
+
432
+
433
+ Arguments:
434
+ - `bucket_name` (required): N/A
435
+ - `file_path` (required): N/A
436
+
437
+ Options:
438
+ - `--confirm`: Skip confirmation prompt
439
+ - `--dry-run`: Show what would be deleted
440
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
441
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
442
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
443
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
444
+
445
+ **`uipath buckets files download`**
446
+
447
+ Download a file from a bucket.
448
+
449
+ 
450
+ Arguments:
451
+ BUCKET_NAME: Name of the bucket
452
+ REMOTE_PATH: Path to file in bucket
453
+ LOCAL_PATH: Local destination path
454
+
455
+ 
456
+ Examples:
457
+ uipath buckets files download my-bucket data.csv ./downloads/data.csv
458
+ uipath buckets files download reports monthly/report.pdf ./report.pdf
459
+
460
+
461
+ Arguments:
462
+ - `bucket_name` (required): N/A
463
+ - `remote_path` (required): N/A
464
+ - `local_path` (required): N/A
465
+
466
+ Options:
467
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
468
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
469
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
470
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
471
+
472
+ **`uipath buckets files exists`**
473
+
474
+ Check if a file exists in a bucket.
475
+
476
+ 
477
+ Arguments:
478
+ BUCKET_NAME: Name of the bucket
479
+ FILE_PATH: Path to file in bucket
480
+
481
+ 
482
+ Examples:
483
+ uipath buckets files exists my-bucket data.csv
484
+ uipath buckets files exists reports monthly/report.pdf
485
+
486
+
487
+ Arguments:
488
+ - `bucket_name` (required): N/A
489
+ - `file_path` (required): N/A
490
+
491
+ Options:
492
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
493
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
494
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
495
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
496
+
497
+ **`uipath buckets files list`**
498
+
499
+ List files in a bucket.
500
+
501
+ 
502
+ Arguments:
503
+ BUCKET_NAME: Name of the bucket
504
+
505
+ 
506
+ Examples:
507
+ uipath buckets files list my-bucket
508
+ uipath buckets files list my-bucket --prefix "data/"
509
+ uipath buckets files list reports --limit 10 --format json
510
+ uipath buckets files list my-bucket --all
511
+
512
+
513
+ Arguments:
514
+ - `bucket_name` (required): N/A
515
+
516
+ Options:
517
+ - `--prefix`: Filter files by prefix (default: ``)
518
+ - `--limit`: Maximum number of files to return (default: `Sentinel.UNSET`)
519
+ - `--offset`: Number of files to skip (default: `0`)
520
+ - `--all`: Fetch all files (auto-paginate)
521
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
522
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
523
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
524
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
525
+
526
+ **`uipath buckets files search`**
527
+
528
+ Search for files using glob patterns.
529
+
530
+ Uses the GetFiles API which supports glob patterns like *.pdf or data_*.csv.
531
+
532
+ 
533
+ Arguments:
534
+ BUCKET_NAME: Name of the bucket
535
+ PATTERN: Glob pattern to match files (e.g., "*.pdf", "data_*.csv")
536
+
537
+ 
538
+ Examples:
539
+ uipath buckets files search my-bucket "*.pdf"
540
+ uipath buckets files search reports "*.csv" --recursive
541
+ uipath buckets files search my-bucket "data_*.json" --prefix "archive/"
542
+
543
+
544
+ Arguments:
545
+ - `bucket_name` (required): N/A
546
+ - `pattern` (required): N/A
547
+
548
+ Options:
549
+ - `--prefix`: Directory path to search in (default: ``)
550
+ - `--recursive`: Search subdirectories recursively
551
+ - `--limit`: Maximum number of files to return (default: `Sentinel.UNSET`)
552
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
553
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
554
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
555
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
556
+
557
+ **`uipath buckets files upload`**
558
+
559
+ Upload a file to a bucket.
560
+
561
+ 
562
+ Arguments:
563
+ BUCKET_NAME: Name of the bucket
564
+ LOCAL_PATH: Local file to upload
565
+ REMOTE_PATH: Destination path in bucket
566
+
567
+ 
568
+ Examples:
569
+ uipath buckets files upload my-bucket ./data.csv remote/data.csv
570
+ uipath buckets files upload reports ./report.pdf monthly/report.pdf
571
+
572
+
573
+ Arguments:
574
+ - `bucket_name` (required): N/A
575
+ - `local_path` (required): N/A
576
+ - `remote_path` (required): N/A
577
+
578
+ Options:
579
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
580
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
581
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
582
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
583
+
584
+ **`uipath buckets list`**
585
+
586
+ List all Buckets.
587
+
588
+ Examples:
589
+ uipath buckets list
590
+ uipath buckets list --folder-path Shared
591
+
592
+
593
+ Options:
594
+ - `--limit`: Maximum number of items to return (default: `Sentinel.UNSET`)
595
+ - `--offset`: Number of items to skip (default: `0`)
596
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
597
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
598
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
599
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
600
+
601
+ **`uipath buckets retrieve`**
602
+
603
+ Retrieve a bucket by name or key.
604
+
605
+ 
606
+ Examples:
607
+ uipath buckets retrieve --name "my-bucket"
608
+ uipath buckets retrieve --key "abc-123-def-456" --format json
609
+
610
+
611
+ Options:
612
+ - `--name`: Bucket name (default: `Sentinel.UNSET`)
613
+ - `--key`: Bucket key (UUID) (default: `Sentinel.UNSET`)
614
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
615
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
616
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
617
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
618
+
619
+ ---
620
+
621
+ ### `uipath context-grounding`
622
+
623
+ Manage UiPath Context Grounding indexes.
624
+
625
+ Context Grounding indexes store and search contextual information
626
+ used to enhance AI-enabled automation processes.
627
+
628
+ 
629
+ Two index types:
630
+ Regular - Persistent, backed by bucket or connection, created via 'create'
631
+ Ephemeral - Temporary, no Orchestrator folder, created from local files via 'create-ephemeral'
632
+
633
+ 
634
+ Examples:
635
+ uipath context-grounding list --folder-path "Shared"
636
+
637
+
638
+ **Subcommands:**
639
+
640
+ #### `uipath context-grounding batch-transform`
641
+
642
+ Manage Batch Transform tasks.
643
+
644
+ Batch Transform processes and transforms CSV files from context
645
+ grounding indexes.
646
+
647
+ 
648
+ Examples:
649
+ uipath context-grounding batch-transform start --help
650
+
651
+
652
+ **`uipath context-grounding batch-transform download`**
653
+
654
+ Download a Batch Transform result file.
655
+
656
+ 
657
+ Examples:
658
+ uipath context-grounding batch-transform download --task-id abc-123 --output-file result.csv
659
+
660
+
661
+ Options:
662
+ - `--task-id`: ID of the Batch Transform task (default: `Sentinel.UNSET`)
663
+ - `--output-file`: Local destination path for the result file (default: `Sentinel.UNSET`)
664
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
665
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
666
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
667
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
668
+
669
+ **`uipath context-grounding batch-transform retrieve`**
670
+
671
+ Retrieve a Batch Transform task status.
672
+
673
+ 
674
+ Examples:
675
+ uipath context-grounding batch-transform retrieve --task-id abc-123-def-456
676
+
677
+
678
+ Options:
679
+ - `--task-id`: ID of the Batch Transform task (default: `Sentinel.UNSET`)
680
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
681
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
682
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
683
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
684
+
685
+ **`uipath context-grounding batch-transform start`**
686
+
687
+ Start a Batch Transform task on an index.
688
+
689
+ The index must contain CSV files. Only one file is processed per task.
690
+
691
+ 
692
+ Two ways to specify the index:
693
+ Regular index: --index-name + --folder-path
694
+ Ephemeral index: --index-id
695
+
696
+ 
697
+ --columns-file is a JSON array defining output columns:
698
+ [
699
+ {"name": "entity", "description": "Extracted entity name"},
700
+ {"name": "category", "description": "Entity category"}
701
+ ]
702
+
703
+ 
704
+ Examples:
705
+ uipath context-grounding batch-transform start --index-name my-index --task-name my-task --prompt "Extract" --columns-file cols.json
706
+ uipath context-grounding batch-transform start --index-id abc-123 --task-name my-task --prompt "Extract" --columns-file cols.json
707
+
708
+
709
+ Options:
710
+ - `--index-name`: Name of the context grounding index (default: `Sentinel.UNSET`)
711
+ - `--index-id`: ID of the context grounding index (ephemeral indexes only) (default: `Sentinel.UNSET`)
712
+ - `--task-name`: Name for the Batch Transform task (default: `Sentinel.UNSET`)
713
+ - `--prompt`: Task prompt describing what to process (default: `Sentinel.UNSET`)
714
+ - `--columns-file`: JSON file defining output columns (see format above) (default: `Sentinel.UNSET`)
715
+ - `--target-file`: Specific file name to target in the index (default: `Sentinel.UNSET`)
716
+ - `--prefix`: Storage bucket folder path prefix for filtering files (default: `Sentinel.UNSET`)
717
+ - `--web-search`: Enable web search grounding
718
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
719
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
720
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
721
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
722
+
723
+ **`uipath context-grounding create`**
724
+
725
+ Create a new context grounding index (persistent).
726
+
727
+ The created index lives in an Orchestrator folder. Ingestion must be
728
+ triggered separately after creation.
729
+
730
+ 
731
+ Two ways to specify the data source:
732
+ --bucket-source Bucket name for bucket-backed indexes
733
+ --source-file JSON file for connections (use 'source-schema' to see formats)
734
+
735
+ 
736
+ Examples:
737
+ uipath context-grounding create --index-name my-index --bucket-source my-bucket
738
+ uipath context-grounding create --index-name my-index --source-file config.json
739
+
740
+
741
+ Options:
742
+ - `--index-name`: Name of the index to create (default: `Sentinel.UNSET`)
743
+ - `--source-file`: JSON file with connection source configuration (Google Drive, OneDrive, Dropbox, Confluence) (default: `Sentinel.UNSET`)
744
+ - `--bucket-source`: Bucket name for bucket-backed indexes (default: `Sentinel.UNSET`)
745
+ - `--description`: Description of the index (default: ``)
746
+ - `--extraction-strategy`: Extraction strategy (default: LLMV4) (default: `LLMV4`)
747
+ - `--file-type`: File type filter (e.g., 'pdf', 'txt') (default: `Sentinel.UNSET`)
748
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
749
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
750
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
751
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
752
+
753
+ **`uipath context-grounding create-ephemeral`**
754
+
755
+ Create an ephemeral index from local files (temporary).
756
+
757
+ Uploads files as attachments and creates a temporary index. Reference it
758
+ in other commands with --index-id (no folder, no name). Ingestion starts
759
+ automatically. Poll with 'retrieve --index-id <id>' until
760
+ lastIngestionStatus is Successful before starting a task.
761
+
762
+ 
763
+ Supported file types:
764
+ DeepRAG: PDF, TXT
765
+ BatchRAG: CSV
766
+
767
+ 
768
+ Examples:
769
+ uipath context-grounding create-ephemeral --usage DeepRAG --files doc1.pdf --files doc2.pdf
770
+ uipath context-grounding create-ephemeral --usage BatchRAG --files data.csv
771
+
772
+
773
+ Options:
774
+ - `--usage`: Task type for the ephemeral index (default: `Sentinel.UNSET`)
775
+ - `--files`: Local file paths to upload as attachments (repeatable) (default: `Sentinel.UNSET`)
776
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
777
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
778
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
779
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
780
+
781
+ #### `uipath context-grounding deep-rag`
782
+
783
+ Manage Deep RAG tasks.
784
+
785
+ Deep RAG performs multi-document research and synthesis on context
786
+ grounding indexes.
787
+
788
+ 
789
+ Examples:
790
+ uipath context-grounding deep-rag start --help
791
+
792
+
793
+ **`uipath context-grounding deep-rag retrieve`**
794
+
795
+ Retrieve a Deep RAG task result (status, summary, citations).
796
+
797
+ 
798
+ Examples:
799
+ uipath context-grounding deep-rag retrieve --task-id abc-123-def-456
800
+
801
+
802
+ Options:
803
+ - `--task-id`: ID of the Deep RAG task (default: `Sentinel.UNSET`)
804
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
805
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
806
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
807
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
808
+
809
+ **`uipath context-grounding deep-rag start`**
810
+
811
+ Start a Deep RAG task on an index.
812
+
813
+ 
814
+ Two ways to specify the index:
815
+ Regular index: --index-name + --folder-path
816
+ Ephemeral index: --index-id
817
+
818
+ 
819
+ Examples:
820
+ uipath context-grounding deep-rag start --index-name my-index --folder-path Shared --task-name my-task --prompt "Summarize"
821
+ uipath context-grounding deep-rag start --index-id abc-123 --task-name my-task --prompt "Summarize"
822
+
823
+
824
+ Options:
825
+ - `--index-name`: Name of the context grounding index (default: `Sentinel.UNSET`)
826
+ - `--index-id`: ID of the context grounding index (ephemeral indexes only) (default: `Sentinel.UNSET`)
827
+ - `--task-name`: Name for the Deep RAG task (default: `Sentinel.UNSET`)
828
+ - `--prompt`: Task prompt describing what to research (default: `Sentinel.UNSET`)
829
+ - `--glob-pattern`: Glob pattern to filter files in the index (default: **) (default: `**`)
830
+ - `--citation-mode`: Citation mode (default: Skip) (default: `Skip`)
831
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
832
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
833
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
834
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
835
+
836
+ **`uipath context-grounding delete`**
837
+
838
+ Delete a context grounding index.
839
+
840
+ 
841
+ Examples:
842
+ uipath context-grounding delete --index-name my-index --confirm
843
+ uipath context-grounding delete --index-name my-index --dry-run
844
+
845
+
846
+ Options:
847
+ - `--index-name`: Name of the index to delete (default: `Sentinel.UNSET`)
848
+ - `--confirm`: Skip confirmation prompt
849
+ - `--dry-run`: Show what would be deleted without deleting
850
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
851
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
852
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
853
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
854
+
855
+ **`uipath context-grounding ingest`**
856
+
857
+ Trigger ingestion on a context grounding index.
858
+
859
+ Ingestion runs asynchronously. Use 'retrieve' to poll lastIngestionStatus
860
+ until it reaches Successful or Failed.
861
+
862
+ 
863
+ Examples:
864
+ uipath context-grounding ingest --index-name my-index --folder-path "Shared"
865
+
866
+
867
+ Options:
868
+ - `--index-name`: Name of the index to ingest (default: `Sentinel.UNSET`)
869
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
870
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
871
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
872
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
873
+
874
+ **`uipath context-grounding list`**
875
+
876
+ List all context grounding indexes.
877
+
878
+ 
879
+ Examples:
880
+ uipath context-grounding list --folder-path "Shared"
881
+
882
+
883
+ Options:
884
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
885
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
886
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
887
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
888
+
889
+ **`uipath context-grounding retrieve`**
890
+
891
+ Retrieve a context grounding index.
892
+
893
+ 
894
+ Two ways to specify the index:
895
+ Regular index: --index-name + --folder-path
896
+ Ephemeral index: --index-id
897
+
898
+ 
899
+ Examples:
900
+ uipath context-grounding retrieve --index-name my-index --folder-path "Shared"
901
+ uipath context-grounding retrieve --index-id abc-123-def-456 --format json
902
+
903
+
904
+ Options:
905
+ - `--index-name`: Name of the index to retrieve (default: `Sentinel.UNSET`)
906
+ - `--index-id`: ID of the index to retrieve (ephemeral indexes only) (default: `Sentinel.UNSET`)
907
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
908
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
909
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
910
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
911
+
912
+ **`uipath context-grounding search`**
913
+
914
+ Search a context grounding index (regular indexes only).
915
+
916
+ 
917
+ Examples:
918
+ uipath context-grounding search --index-name my-index --query "What is the revenue?"
919
+ uipath context-grounding search --index-name my-index --query "results" --limit 5
920
+
921
+
922
+ Options:
923
+ - `--index-name`: Name of the index to search (default: `Sentinel.UNSET`)
924
+ - `--query`: Search query in natural language (default: `Sentinel.UNSET`)
925
+ - `--limit`: Maximum number of results (default: 10) (default: `10`)
926
+ - `--threshold`: Minimum similarity threshold (default: 0.0) (default: `0.0`)
927
+ - `--search-mode`: Search mode (default: Semantic) (default: `Semantic`)
928
+ - `--folder-path`: Folder path (e.g., "Shared"). Can also be set via UIPATH_FOLDER_PATH environment variable. (default: `Sentinel.UNSET`)
929
+ - `--folder-key`: Folder key (UUID) (default: `Sentinel.UNSET`)
930
+ - `--format`: Output format (overrides global) (default: `Sentinel.UNSET`)
931
+ - `--output`, `-o`: Output file (overrides global) (default: `Sentinel.UNSET`)
932
+
933
+ **`uipath context-grounding source-schema`**
934
+
935
+ Show JSON source file formats for connection-backed indexes.
936
+
937
+ Use this to see the required fields for --source-file when creating
938
+ an index backed by Google Drive, OneDrive, Dropbox, or Confluence.
939
+
940
+ 
941
+ Examples:
942
+ uipath context-grounding source-schema --type google_drive
943
+
944
+
945
+ Options:
946
+ - `--type`: Show schema for a specific source type (omit to show all) (default: `Sentinel.UNSET`)
947
+
948
+ ---
949
+
agents/agent_2_sanctions_screener/.agent/REQUIRED_STRUCTURE.md ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## Required Agent Structure
2
+
3
+ **IMPORTANT**: All UiPath coded agents MUST follow this standard structure unless explicitly specified otherwise by the user.
4
+
5
+ ### Required Components
6
+
7
+ Every agent implementation MUST include these two Pydantic models:
8
+
9
+ ```python
10
+ from pydantic import BaseModel
11
+
12
+ class Input(BaseModel):
13
+ """Define input fields that the agent accepts"""
14
+ # Add your input fields here
15
+ pass
16
+
17
+ class Output(BaseModel):
18
+ """Define output fields that the agent returns"""
19
+ # Add your output fields here
20
+ pass
21
+ ```
22
+
23
+ ### SDK Initialization
24
+
25
+ ```python
26
+ from uipath.platform import UiPath
27
+
28
+ # Initialize with environment variables
29
+ uipath = UiPath()
30
+
31
+ # With explicit credentials
32
+ uipath = UiPath(base_url="https://cloud.uipath.com/...", secret="your_token")
33
+
34
+ # Or with client_id and client_secret
35
+ uipath = UiPath(
36
+ client_id=UIPATH_CLIENT_ID,
37
+ client_secret=UIPATH_CLIENT_SECRET,
38
+ scope=UIPATH_SCOPE,
39
+ base_url=UIPATH_URL
40
+ )
41
+ ```
42
+
43
+ ### Standard Agent Template
44
+
45
+ Every agent should follow this basic structure:
46
+
47
+ ```python
48
+ from uipath.platform import UiPath
49
+ from pydantic import BaseModel
50
+
51
+ # 1. Define Input, and Output models
52
+ class Input(BaseModel):
53
+ field: str
54
+
55
+ class Output(BaseModel):
56
+ result: str
57
+
58
+ # 2. Initialize with environment variables
59
+ uipath = UiPath()
60
+
61
+ # 3. Define the main function (the main function can be named "main", "run" or "execute")
62
+ def main(input_data: Input) -> Output:
63
+ pass
64
+ ```
agents/agent_2_sanctions_screener/.agent/SDK_REFERENCE.md ADDED
@@ -0,0 +1,971 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ## API Reference
2
+
3
+ This section provides a comprehensive reference for all UiPath SDK services and methods. Each service is documented with complete method signatures, including parameter types and return types.
4
+
5
+ ### SDK Initialization
6
+
7
+ Initialize the UiPath SDK client
8
+
9
+ ```python
10
+ from uipath.platform import UiPath
11
+
12
+ # Initialize with environment variables
13
+ sdk = UiPath()
14
+
15
+ # Or with explicit credentials
16
+ sdk = UiPath(base_url="https://cloud.uipath.com/...", secret="your_token")
17
+ ```
18
+
19
+ ### Agenthub
20
+
21
+ Agenthub service
22
+
23
+ ```python
24
+ # Fetch available models from LLM Gateway discovery endpoint.
25
+ sdk.agenthub.get_available_llm_models(headers: dict[str, Any] | None=None) -> list[uipath.platform.agenthub.agenthub.LlmModel]
26
+
27
+ # Asynchronously fetch available models from LLM Gateway discovery endpoint.
28
+ sdk.agenthub.get_available_llm_models_async(headers: dict[str, Any] | None=None) -> list[uipath.platform.agenthub.agenthub.LlmModel]
29
+
30
+ # Start a system agent job.
31
+ sdk.agenthub.invoke_system_agent(agent_name: str, entrypoint: str, input_arguments: dict[str, Any] | None=None, folder_key: str | None=None, folder_path: str | None=None, headers: dict[str, Any] | None=None) -> str
32
+
33
+ # Asynchronously start a system agent and return the job.
34
+ sdk.agenthub.invoke_system_agent_async(agent_name: str, entrypoint: str, input_arguments: dict[str, Any] | None=None, folder_key: str | None=None, folder_path: str | None=None, headers: dict[str, Any] | None=None) -> str
35
+
36
+ ```
37
+
38
+ ### Api Client
39
+
40
+ Api Client service
41
+
42
+ ```python
43
+ # Access api_client service methods
44
+ service = sdk.api_client
45
+
46
+ ```
47
+
48
+ ### Assets
49
+
50
+ Assets service
51
+
52
+ ```python
53
+ # List assets using OData API with offset-based pagination.
54
+ sdk.assets.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.assets.Asset]
55
+
56
+ # Asynchronously list assets using OData API with offset-based pagination.
57
+ sdk.assets.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.assets.Asset]
58
+
59
+ # Retrieve an asset by its name.
60
+ sdk.assets.retrieve(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.assets.UserAsset | uipath.platform.orchestrator.assets.Asset
61
+
62
+ # Asynchronously retrieve an asset by its name.
63
+ sdk.assets.retrieve_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.assets.UserAsset | uipath.platform.orchestrator.assets.Asset
64
+
65
+ # Gets a specified Orchestrator credential.
66
+ sdk.assets.retrieve_credential(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Optional[str]
67
+
68
+ # Asynchronously gets a specified Orchestrator credential.
69
+ sdk.assets.retrieve_credential_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Optional[str]
70
+
71
+ # Update an asset's value.
72
+ sdk.assets.update(robot_asset: uipath.platform.orchestrator.assets.UserAsset, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
73
+
74
+ # Asynchronously update an asset's value.
75
+ sdk.assets.update_async(robot_asset: uipath.platform.orchestrator.assets.UserAsset, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
76
+
77
+ ```
78
+
79
+ ### Attachments
80
+
81
+ Attachments service
82
+
83
+ ```python
84
+ # Delete an attachment.
85
+ sdk.attachments.delete(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> None
86
+
87
+ # Delete an attachment asynchronously.
88
+ sdk.attachments.delete_async(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> None
89
+
90
+ # Download an attachment.
91
+ sdk.attachments.download(key: uuid.UUID, destination_path: str, folder_key: str | None=None, folder_path: str | None=None) -> str
92
+
93
+ # Download an attachment asynchronously.
94
+ sdk.attachments.download_async(key: uuid.UUID, destination_path: str, folder_key: str | None=None, folder_path: str | None=None) -> str
95
+
96
+ # Get the BlobFileAccess information for an attachment.
97
+ sdk.attachments.get_blob_file_access_uri(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.attachments.attachments.BlobFileAccessInfo
98
+
99
+ # Get the BlobFileAccess information for an attachment asynchronously.
100
+ sdk.attachments.get_blob_file_access_uri_async(key: uuid.UUID, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.attachments.attachments.BlobFileAccessInfo
101
+
102
+ # Open an attachment.
103
+ sdk.attachments.open(attachment: uipath.platform.attachments.attachments.Attachment, mode: <enum 'AttachmentMode="AttachmentMode.READ", content: Union[str, bytes, Iterable[bytes], AsyncIterable[bytes], NoneType]=None, folder_key: str | None=None, folder_path: str | None=None) -> typing.Iterator[typing.Tuple[uipath.platform.attachments.attachments.Attachment, httpx.Response]]
104
+
105
+ # Open an attachment asynchronously.
106
+ sdk.attachments.open_async(attachment: uipath.platform.attachments.attachments.Attachment, mode: <enum 'AttachmentMode="AttachmentMode.READ", content: Union[str, bytes, Iterable[bytes], AsyncIterable[bytes], NoneType]=None, folder_key: str | None=None, folder_path: str | None=None) -> typing.AsyncIterator[typing.Tuple[uipath.platform.attachments.attachments.Attachment, httpx.Response]]
107
+
108
+ # Upload a file or content to UiPath as an attachment.
109
+ sdk.attachments.upload(name: str, content: str | bytes | None=None, source_path: str | None=None, folder_key: str | None=None, folder_path: str | None=None) -> uuid.UUID
110
+
111
+ # Upload a file or content to UiPath as an attachment asynchronously.
112
+ sdk.attachments.upload_async(name: str, content: str | bytes | None=None, source_path: str | None=None, folder_key: str | None=None, folder_path: str | None=None) -> uuid.UUID
113
+
114
+ ```
115
+
116
+ ### Automation Ops
117
+
118
+ Automation Ops service
119
+
120
+ ```python
121
+ # Retrieve the deployed policy.
122
+ sdk.automation_ops.get_deployed_policy() -> dict[str, typing.Any]
123
+
124
+ # Retrieve the deployed policy (async).
125
+ sdk.automation_ops.get_deployed_policy_async() -> dict[str, typing.Any]
126
+
127
+ ```
128
+
129
+ ### Automation Tracker
130
+
131
+ Automation Tracker service
132
+
133
+ ```python
134
+ # End tracking an operation within a transaction.
135
+ sdk.automation_tracker.end_operation(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
136
+
137
+ # End tracking an operation within a transaction (async).
138
+ sdk.automation_tracker.end_operation_async(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
139
+
140
+ # End tracking a business transaction.
141
+ sdk.automation_tracker.end_transaction(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
142
+
143
+ # End tracking a business transaction (async).
144
+ sdk.automation_tracker.end_transaction_async(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
145
+
146
+ # Start tracking an operation within a transaction.
147
+ sdk.automation_tracker.start_operation(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
148
+
149
+ # Start tracking an operation within a transaction (async).
150
+ sdk.automation_tracker.start_operation_async(transaction_id: str, operation_id: str, name: str, fingerprint: str, parent_operation: Optional[str]=None, status: <enum 'OperationStatus="OperationStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
151
+
152
+ # Start tracking a business transaction.
153
+ sdk.automation_tracker.start_transaction(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
154
+
155
+ # Start tracking a business transaction (async).
156
+ sdk.automation_tracker.start_transaction_async(transaction_id: str, name: str, reference: str, fingerprint: str, status: <enum 'TransactionStatus="TransactionStatus.UNKNOWN", result: Optional[str]=None, attributes: Optional[Dict[str, str]]=None, timestamp: Optional[datetime.datetime]=None) -> None
157
+
158
+ ```
159
+
160
+ ### Buckets
161
+
162
+ Buckets service
163
+
164
+ ```python
165
+ # Create a new bucket.
166
+ sdk.buckets.create(name: str, description: Optional[str]=None, identifier: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
167
+
168
+ # Async version of create().
169
+ sdk.buckets.create_async(name: str, description: Optional[str]=None, identifier: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
170
+
171
+ # Delete a bucket.
172
+ sdk.buckets.delete(name: Optional[str]=None, key: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
173
+
174
+ # Async version of delete().
175
+ sdk.buckets.delete_async(name: Optional[str]=None, key: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
176
+
177
+ # Delete a file from a bucket.
178
+ sdk.buckets.delete_file(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
179
+
180
+ # Delete a file from a bucket asynchronously.
181
+ sdk.buckets.delete_file_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
182
+
183
+ # Download a file from a bucket.
184
+ sdk.buckets.download(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, destination_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
185
+
186
+ # Download a file from a bucket asynchronously.
187
+ sdk.buckets.download_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, destination_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
188
+
189
+ # Check if bucket exists.
190
+ sdk.buckets.exists(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
191
+
192
+ # Async version of exists().
193
+ sdk.buckets.exists_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
194
+
195
+ # Check if a file exists in a bucket.
196
+ sdk.buckets.exists_file(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
197
+
198
+ # Async version of exists_file().
199
+ sdk.buckets.exists_file_async(name: Optional[str]=None, key: Optional[str]=None, blob_file_path: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
200
+
201
+ # Get files using OData GetFiles API with offset-based pagination.
202
+ sdk.buckets.get_files(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", recursive: bool=False, file_name_glob: Optional[str]=None, skip: int=0, top: int=500, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
203
+
204
+ # Async version of get_files() with offset-based pagination.
205
+ sdk.buckets.get_files_async(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", recursive: bool=False, file_name_glob: Optional[str]=None, skip: int=0, top: int=500, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
206
+
207
+ # List buckets using OData API with offset-based pagination.
208
+ sdk.buckets.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, name: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.Bucket]
209
+
210
+ # Async version of list() with offset-based pagination.
211
+ sdk.buckets.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, name: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.Bucket]
212
+
213
+ # List files in a bucket using cursor-based pagination.
214
+ sdk.buckets.list_files(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", take_hint: int=500, continuation_token: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
215
+
216
+ # Async version of list_files() with cursor-based pagination.
217
+ sdk.buckets.list_files_async(name: Optional[str]=None, key: Optional[str]=None, prefix: str="", take_hint: int=500, continuation_token: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.buckets.BucketFile]
218
+
219
+ # Retrieve bucket information by its name.
220
+ sdk.buckets.retrieve(name: Optional[str]=None, key: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
221
+
222
+ # Asynchronously retrieve bucket information by its name.
223
+ sdk.buckets.retrieve_async(name: Optional[str]=None, key: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.orchestrator.buckets.Bucket
224
+
225
+ # Upload a file to a bucket.
226
+ sdk.buckets.upload(key: Optional[str]=None, name: Optional[str]=None, blob_file_path: str, content_type: Optional[str]=None, source_path: Optional[str]=None, content: Union[str, bytes, NoneType]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
227
+
228
+ # Upload a file to a bucket asynchronously.
229
+ sdk.buckets.upload_async(key: Optional[str]=None, name: Optional[str]=None, blob_file_path: str, content_type: Optional[str]=None, source_path: Optional[str]=None, content: Union[str, bytes, NoneType]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
230
+
231
+ ```
232
+
233
+ ### Connections
234
+
235
+ Connections service
236
+
237
+ ```python
238
+ # Invoke an activity synchronously.
239
+ sdk.connections.invoke_activity(activity_metadata: uipath.platform.connections.connections.ActivityMetadata, connection_id: str, activity_input: Dict[str, Any]) -> typing.Any
240
+
241
+ # Invoke an activity asynchronously.
242
+ sdk.connections.invoke_activity_async(activity_metadata: uipath.platform.connections.connections.ActivityMetadata, connection_id: str, activity_input: Dict[str, Any]) -> typing.Any
243
+
244
+ # Lists all connections with optional filtering.
245
+ sdk.connections.list(name: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, connector_key: Optional[str]=None, skip: Optional[int]=None, top: Optional[int]=None) -> typing.List[uipath.platform.connections.connections.Connection]
246
+
247
+ # Asynchronously lists all connections with optional filtering.
248
+ sdk.connections.list_async(name: Optional[str]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, connector_key: Optional[str]=None, skip: Optional[int]=None, top: Optional[int]=None) -> typing.List[uipath.platform.connections.connections.Connection]
249
+
250
+ # Synchronously retrieve connection API metadata.
251
+ sdk.connections.metadata(element_instance_id: int, connector_key: str, tool_path: str, parameters: Optional[Dict[str, str]]=None, schema_mode: bool=True, max_jit_depth: int=5) -> uipath.platform.connections.connections.ConnectionMetadata
252
+
253
+ # Asynchronously retrieve connection API metadata.
254
+ sdk.connections.metadata_async(element_instance_id: int, connector_key: str, tool_path: str, parameters: Optional[Dict[str, str]]=None, schema_mode: bool=True, max_jit_depth: int=5) -> uipath.platform.connections.connections.ConnectionMetadata
255
+
256
+ # Retrieve connection details by its key.
257
+ sdk.connections.retrieve(key: str) -> uipath.platform.connections.connections.Connection
258
+
259
+ # Asynchronously retrieve connection details by its key.
260
+ sdk.connections.retrieve_async(key: str) -> uipath.platform.connections.connections.Connection
261
+
262
+ # Retrieve event payload from UiPath Integration Service.
263
+ sdk.connections.retrieve_event_payload(event_args: uipath.platform.connections.connections.EventArguments) -> typing.Dict[str, typing.Any]
264
+
265
+ # Retrieve event payload from UiPath Integration Service.
266
+ sdk.connections.retrieve_event_payload_async(event_args: uipath.platform.connections.connections.EventArguments) -> typing.Dict[str, typing.Any]
267
+
268
+ # Retrieve an authentication token for a connection.
269
+ sdk.connections.retrieve_token(key: str, token_type: <enum 'ConnectionTokenType="ConnectionTokenType.DIRECT") -> uipath.platform.connections.connections.ConnectionToken
270
+
271
+ # Asynchronously retrieve an authentication token for a connection.
272
+ sdk.connections.retrieve_token_async(key: str, token_type: <enum 'ConnectionTokenType="ConnectionTokenType.DIRECT") -> uipath.platform.connections.connections.ConnectionToken
273
+
274
+ ```
275
+
276
+ ### Context Grounding
277
+
278
+ Context Grounding service
279
+
280
+ ```python
281
+ # Add content to the index.
282
+ sdk.context_grounding.add_to_index(name: str, blob_file_path: str, content_type: Optional[str]=None, content: Union[str, bytes, NoneType]=None, source_path: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, ingest_data: bool=True) -> None
283
+
284
+ # Asynchronously add content to the index.
285
+ sdk.context_grounding.add_to_index_async(name: str, blob_file_path: str, content_type: Optional[str]=None, content: Union[str, bytes, NoneType]=None, source_path: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, ingest_data: bool=True) -> None
286
+
287
+ # Create a new ephemeral context grounding index.
288
+ sdk.context_grounding.create_ephemeral_index(usage: <enum 'EphemeralIndexUsage, attachments: List[str], folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
289
+
290
+ # Create a new ephemeral context grounding index.
291
+ sdk.context_grounding.create_ephemeral_index_async(usage: <enum 'EphemeralIndexUsage, attachments: List[str], folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
292
+
293
+ # Create a new context grounding index.
294
+ sdk.context_grounding.create_index(name: str, source: Union[uipath.platform.context_grounding.context_grounding_payloads.BucketSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.GoogleDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.DropboxSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.OneDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.ConfluenceSourceConfig], description: Optional[str]=None, extraction_strategy: Optional[str]=None, embeddings_enabled: Optional[bool]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
295
+
296
+ # Create a new context grounding index.
297
+ sdk.context_grounding.create_index_async(name: str, source: Union[uipath.platform.context_grounding.context_grounding_payloads.BucketSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.GoogleDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.DropboxSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.OneDriveSourceConfig, uipath.platform.context_grounding.context_grounding_payloads.ConfluenceSourceConfig], description: Optional[str]=None, extraction_strategy: Optional[str]=None, embeddings_enabled: Optional[bool]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
298
+
299
+ # Delete a context grounding index by its name.
300
+ sdk.context_grounding.delete_by_name(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
301
+
302
+ # Asynchronously delete a context grounding index by its name.
303
+ sdk.context_grounding.delete_by_name_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
304
+
305
+ # Delete a context grounding index.
306
+ sdk.context_grounding.delete_index(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
307
+
308
+ # Asynchronously delete a context grounding index.
309
+ sdk.context_grounding.delete_index_async(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
310
+
311
+ # Downloads the Batch Transform result file to the specified path.
312
+ sdk.context_grounding.download_batch_transform_result(id: str, destination_path: str, validate_status: bool=True, index_name: str | None=None) -> None
313
+
314
+ # Asynchronously downloads the Batch Transform result file to the specified path.
315
+ sdk.context_grounding.download_batch_transform_result_async(id: str, destination_path: str, validate_status: bool=True, index_name: str | None=None) -> None
316
+
317
+ # Trigger ingestion on a context grounding index by its name.
318
+ sdk.context_grounding.ingest_by_name(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
319
+
320
+ # Asynchronously trigger ingestion on a context grounding index by its name.
321
+ sdk.context_grounding.ingest_by_name_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
322
+
323
+ # Ingest data into the context grounding index.
324
+ sdk.context_grounding.ingest_data(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
325
+
326
+ # Asynchronously ingest data into the context grounding index.
327
+ sdk.context_grounding.ingest_data_async(index: uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
328
+
329
+ # List all context grounding indexes in a folder.
330
+ sdk.context_grounding.list(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
331
+
332
+ # Asynchronously list all context grounding indexes in a folder.
333
+ sdk.context_grounding.list_async(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
334
+
335
+ # List all context grounding indexes in a folder.
336
+ sdk.context_grounding.list_indexes(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
337
+
338
+ # Asynchronously list all context grounding indexes in a folder.
339
+ sdk.context_grounding.list_indexes_async(folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
340
+
341
+ # Retrieve context grounding index information by its name.
342
+ sdk.context_grounding.retrieve(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
343
+
344
+ # Retrieve all context grounding indexes across all folders.
345
+ sdk.context_grounding.retrieve_across_folders(name: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
346
+
347
+ # Asynchronously retrieve all context grounding indexes across all folders.
348
+ sdk.context_grounding.retrieve_across_folders_async(name: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex]
349
+
350
+ # Asynchronously retrieve context grounding index information by its name.
351
+ sdk.context_grounding.retrieve_async(name: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding_index.ContextGroundingIndex
352
+
353
+ # Retrieves a Batch Transform task status.
354
+ sdk.context_grounding.retrieve_batch_transform(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformResponse
355
+
356
+ # Asynchronously retrieves a Batch Transform task status.
357
+ sdk.context_grounding.retrieve_batch_transform_async(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformResponse
358
+
359
+ # Retrieve context grounding index information by its ID.
360
+ sdk.context_grounding.retrieve_by_id(id: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Any
361
+
362
+ # Retrieve asynchronously context grounding index information by its ID.
363
+ sdk.context_grounding.retrieve_by_id_async(id: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.Any
364
+
365
+ # Retrieves a Deep RAG task.
366
+ sdk.context_grounding.retrieve_deep_rag(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagResponse
367
+
368
+ # Asynchronously retrieves a Deep RAG task.
369
+ sdk.context_grounding.retrieve_deep_rag_async(id: str, index_name: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagResponse
370
+
371
+ # Search for contextual information within a specific index.
372
+ sdk.context_grounding.search(name: str, query: str, number_of_results: int=10, threshold: Optional[float]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding.ContextGroundingQueryResponse]
373
+
374
+ # Search asynchronously for contextual information within a specific index.
375
+ sdk.context_grounding.search_async(name: str, query: str, number_of_results: int=10, threshold: Optional[float]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[uipath.platform.context_grounding.context_grounding.ContextGroundingQueryResponse]
376
+
377
+ # Starts a Batch Transform, task on the targeted index.
378
+ sdk.context_grounding.start_batch_transform(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, target_file_name: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_name: str | None=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
379
+
380
+ # Asynchronously starts a Batch Transform, task on the targeted index.
381
+ sdk.context_grounding.start_batch_transform_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, target_file_name: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_name: str | None=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
382
+
383
+ # Asynchronously starts a Batch Transform, task on the targeted index.
384
+ sdk.context_grounding.start_batch_transform_ephemeral(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
385
+
386
+ # Asynchronously starts a Batch Transform, task on the targeted index.
387
+ sdk.context_grounding.start_batch_transform_ephemeral_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], output_columns: List[uipath.platform.context_grounding.context_grounding.BatchTransformOutputColumn], storage_bucket_folder_path_prefix: Annotated[str | None, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]=None, enable_web_search_grounding: bool=False, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.BatchTransformCreationResponse
388
+
389
+ # Starts a Deep RAG task on the targeted index.
390
+ sdk.context_grounding.start_deep_rag(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_name: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
391
+
392
+ # Asynchronously starts a Deep RAG task on the targeted index.
393
+ sdk.context_grounding.start_deep_rag_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_name: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None, folder_key: str | None=None, folder_path: str | None=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
394
+
395
+ # Asynchronously starts a Deep RAG task on the targeted index.
396
+ sdk.context_grounding.start_deep_rag_ephemeral(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
397
+
398
+ # Asynchronously starts a Deep RAG task on the targeted index.
399
+ sdk.context_grounding.start_deep_rag_ephemeral_async(name: str, prompt: Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=250000)])], glob_pattern: Annotated[str, FieldInfo(annotation=NoneType, required=False, default='*', metadata=[MaxLen(max_length=512)])]="**", citation_mode: <enum 'CitationMode="CitationMode.SKIP", index_id: Optional[Annotated[str, FieldInfo(annotation=NoneType, required=True, metadata=[MaxLen(max_length=512)])]]=None) -> uipath.platform.context_grounding.context_grounding.DeepRagCreationResponse
400
+
401
+ # Perform a unified search on a context grounding index.
402
+ sdk.context_grounding.unified_search(name: str, query: str, search_mode: <enum 'SearchMode="SearchMode.SEMANTIC", number_of_results: int=10, threshold: float=0.0, scope: Optional[uipath.platform.context_grounding.context_grounding.UnifiedSearchScope]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding.UnifiedQueryResult
403
+
404
+ # Asynchronously perform a unified search on a context grounding index.
405
+ sdk.context_grounding.unified_search_async(name: str, query: str, search_mode: <enum 'SearchMode="SearchMode.SEMANTIC", number_of_results: int=10, threshold: float=0.0, scope: Optional[uipath.platform.context_grounding.context_grounding.UnifiedSearchScope]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, include_system_indexes: bool=False) -> uipath.platform.context_grounding.context_grounding.UnifiedQueryResult
406
+
407
+ ```
408
+
409
+ ### Conversational
410
+
411
+ Conversational service
412
+
413
+ ```python
414
+ # Access conversational service methods
415
+ service = sdk.conversational
416
+
417
+ ```
418
+
419
+ ### Documents
420
+
421
+ Documents service
422
+
423
+ ```python
424
+ # Classify a document using a DU Modern project.
425
+ sdk.documents.classify(project_type: <enum 'ProjectType, tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
426
+
427
+ # Asynchronously version of the [`classify`][uipath.platform.documents._documents_service.DocumentsService.classify] method.
428
+ sdk.documents.classify_async(project_type: <enum 'ProjectType, tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
429
+
430
+ # Create a validate classification action for a document based on the classification results. More details about validation actions can be found in the [official documentation](https://docs.uipath.com/ixp/automation-cloud/latest/user-guide/validating-classifications).
431
+ sdk.documents.create_validate_classification_action(classification_results: List[uipath.platform.documents.documents.ClassificationResult], action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateClassificationAction
432
+
433
+ # Asynchronous version of the [`create_validation_action`][uipath.platform.documents._documents_service.DocumentsService.create_validate_classification_action] method.
434
+ sdk.documents.create_validate_classification_action_async(classification_results: List[uipath.platform.documents.documents.ClassificationResult], action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateClassificationAction
435
+
436
+ # Create a validate extraction action for a document based on the extraction response. More details about validation actions can be found in the [official documentation](https://docs.uipath.com/ixp/automation-cloud/latest/user-guide/validating-extractions).
437
+ sdk.documents.create_validate_extraction_action(extraction_response: uipath.platform.documents.documents.ExtractionResponse, action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateExtractionAction
438
+
439
+ # Asynchronous version of the [`create_validation_action`][uipath.platform.documents._documents_service.DocumentsService.create_validate_extraction_action] method.
440
+ sdk.documents.create_validate_extraction_action_async(extraction_response: uipath.platform.documents.documents.ExtractionResponse, action_title: str, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_catalog: Optional[str]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.ValidateExtractionAction
441
+
442
+ # Extract predicted data from a document using an DU Modern/IXP project.
443
+ sdk.documents.extract(tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None, classification_result: Optional[uipath.platform.documents.documents.ClassificationResult]=None, project_type: Optional[uipath.platform.documents.documents.ProjectType]=None, document_type_name: Optional[str]=None) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
444
+
445
+ # Asynchronously version of the [`extract`][uipath.platform.documents._documents_service.DocumentsService.extract] method.
446
+ sdk.documents.extract_async(tag: Optional[str]=None, version: Optional[int]=None, project_name: Optional[str]=None, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None, classification_result: Optional[uipath.platform.documents.documents.ClassificationResult]=None, project_type: Optional[uipath.platform.documents.documents.ProjectType]=None, document_type_name: Optional[str]=None) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
447
+
448
+ # Get the result of a validate classification action.
449
+ sdk.documents.get_validate_classification_result(validation_action: uipath.platform.documents.documents.ValidateClassificationAction) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
450
+
451
+ # Asynchronous version of the [`get_validation_result`][uipath.platform.documents._documents_service.DocumentsService.get_validate_classification_result] method.
452
+ sdk.documents.get_validate_classification_result_async(validation_action: uipath.platform.documents.documents.ValidateClassificationAction) -> typing.List[uipath.platform.documents.documents.ClassificationResult]
453
+
454
+ # Get the result of a validate extraction action.
455
+ sdk.documents.get_validate_extraction_result(validation_action: uipath.platform.documents.documents.ValidateExtractionAction) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
456
+
457
+ # Asynchronous version of the [`get_validation_result`][uipath.platform.documents._documents_service.DocumentsService.get_validate_extraction_result] method.
458
+ sdk.documents.get_validate_extraction_result_async(validation_action: uipath.platform.documents.documents.ValidateExtractionAction) -> typing.Union[uipath.platform.documents.documents.ExtractionResponse, uipath.platform.documents.documents.ExtractionResponseIXP]
459
+
460
+ # Retrieve the result of an IXP extraction operation (single-shot, non-blocking).
461
+ sdk.documents.retrieve_ixp_extraction_result(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ExtractionResponseIXP
462
+
463
+ # Asynchronous version of the [`retrieve_ixp_extraction_result`][uipath.platform.documents._documents_service.DocumentsService.retrieve_ixp_extraction_result] method.
464
+ sdk.documents.retrieve_ixp_extraction_result_async(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ExtractionResponseIXP
465
+
466
+ # Retrieve the result of an IXP create validate extraction action operation (single-shot, non-blocking).
467
+ sdk.documents.retrieve_ixp_extraction_validation_result(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ValidateExtractionAction
468
+
469
+ # Asynchronous version of the [`retrieve_ixp_extraction_validation_result`][uipath.platform.documents._documents_service.DocumentsService.retrieve_ixp_extraction_validation_result] method.
470
+ sdk.documents.retrieve_ixp_extraction_validation_result_async(project_id: str, tag: str, operation_id: str) -> uipath.platform.documents.documents.ValidateExtractionAction
471
+
472
+ # Start an IXP extraction process without waiting for results (non-blocking).
473
+ sdk.documents.start_ixp_extraction(project_name: str, tag: str, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionResponse
474
+
475
+ # Asynchronous version of the [`start_ixp_extraction`][uipath.platform.documents._documents_service.DocumentsService.start_ixp_extraction] method.
476
+ sdk.documents.start_ixp_extraction_async(project_name: str, tag: str, file: Union[IO[bytes], bytes, str, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionResponse
477
+
478
+ # Start an IXP extraction validation action without waiting for results (non-blocking).
479
+ sdk.documents.start_ixp_extraction_validation(extraction_response: uipath.platform.documents.documents.ExtractionResponseIXP, action_title: str, action_catalog: Optional[str]=None, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionValidationResponse
480
+
481
+ # Asynchronous version of the [`start_ixp_extraction_validation`][uipath.platform.documents._documents_service.DocumentsService.start_ixp_extraction_validation] method.
482
+ sdk.documents.start_ixp_extraction_validation_async(extraction_response: uipath.platform.documents.documents.ExtractionResponseIXP, action_title: str, action_catalog: Optional[str]=None, action_priority: Optional[uipath.platform.documents.documents.ActionPriority]=None, action_folder: Optional[str]=None, storage_bucket_name: Optional[str]=None, storage_bucket_directory_path: Optional[str]=None) -> uipath.platform.documents.documents.StartExtractionValidationResponse
483
+
484
+ ```
485
+
486
+ ### Entities
487
+
488
+ Entities service
489
+
490
+ ```python
491
+ # Create a new entity with the given schema and return its id.
492
+ sdk.entities.create_entity(name: str, fields: List[uipath.platform.entities.entities.EntityCreateFieldOptions], options: Optional[uipath.platform.entities.entities.EntityCreateOptions]=None) -> str
493
+
494
+ # Asynchronously create a new entity with the given schema.
495
+ sdk.entities.create_entity_async(name: str, fields: List[uipath.platform.entities.entities.EntityCreateFieldOptions], options: Optional[uipath.platform.entities.entities.EntityCreateOptions]=None) -> str
496
+
497
+ # Remove the file attached to a File-type field on a record.
498
+ sdk.entities.delete_attachment(entity_id: str, record_id: str, field_name: str, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
499
+
500
+ # Asynchronously remove the file attached to a File-type field.
501
+ sdk.entities.delete_attachment_async(entity_id: str, record_id: str, field_name: str, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
502
+
503
+ # Delete an entity and all of its records.
504
+ sdk.entities.delete_entity(entity_id: str) -> None
505
+
506
+ # Asynchronously delete an entity and all of its records.
507
+ sdk.entities.delete_entity_async(entity_id: str) -> None
508
+
509
+ # Delete a single record by id.
510
+ sdk.entities.delete_record(entity_key: str, record_id: str) -> None
511
+
512
+ # Asynchronously delete a single record by id.
513
+ sdk.entities.delete_record_async(entity_key: str, record_id: str) -> None
514
+
515
+ # Delete multiple records from an entity in a single batch operation.
516
+ sdk.entities.delete_records(entity_key: str, record_ids: List[str], fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
517
+
518
+ # Asynchronously delete multiple records from an entity in a single batch operation.
519
+ sdk.entities.delete_records_async(entity_key: str, record_ids: List[str], fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
520
+
521
+ # Download a file attached to a record and return its raw bytes.
522
+ sdk.entities.download_attachment(entity_id: str, record_id: str, field_name: str) -> bytes
523
+
524
+ # Asynchronously download a file attached to a record.
525
+ sdk.entities.download_attachment_async(entity_id: str, record_id: str, field_name: str) -> bytes
526
+
527
+ # Get the values of a choice set by its ID.
528
+ sdk.entities.get_choiceset_values(choiceset_id: str, start: Optional[int]=None, limit: Optional[int]=None) -> typing.List[uipath.platform.entities.entities.ChoiceSetValue]
529
+
530
+ # Asynchronously get the values of a choice set by its ID.
531
+ sdk.entities.get_choiceset_values_async(choiceset_id: str, start: Optional[int]=None, limit: Optional[int]=None) -> typing.List[uipath.platform.entities.entities.ChoiceSetValue]
532
+
533
+ # Fetch a single entity record by its id.
534
+ sdk.entities.get_record(entity_key: str, record_id: str, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
535
+
536
+ # Asynchronously fetch a single entity record by its id.
537
+ sdk.entities.get_record_async(entity_key: str, record_id: str, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
538
+
539
+ # Bulk-import records into an entity from a CSV file.
540
+ sdk.entities.import_records(entity_id: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.entities.entities.EntityImportRecordsResponse
541
+
542
+ # Asynchronously bulk-import records into an entity from a CSV file.
543
+ sdk.entities.import_records_async(entity_id: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None) -> uipath.platform.entities.entities.EntityImportRecordsResponse
544
+
545
+ # Insert a single record into an entity and return the inserted row.
546
+ sdk.entities.insert_record(entity_key: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
547
+
548
+ # Asynchronously insert a single record into an entity.
549
+ sdk.entities.insert_record_async(entity_key: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
550
+
551
+ # Insert multiple records into an entity in a single batch operation.
552
+ sdk.entities.insert_records(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
553
+
554
+ # Asynchronously insert multiple records into an entity in a single batch operation.
555
+ sdk.entities.insert_records_async(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
556
+
557
+ # List all choice sets in Data Service.
558
+ sdk.entities.list_choicesets() -> typing.List[uipath.platform.entities.entities.Entity]
559
+
560
+ # Asynchronously list all choice sets in Data Service.
561
+ sdk.entities.list_choicesets_async() -> typing.List[uipath.platform.entities.entities.Entity]
562
+
563
+ # List all entities in Data Service.
564
+ sdk.entities.list_entities() -> typing.List[uipath.platform.entities.entities.Entity]
565
+
566
+ # Asynchronously list all entities in the Data Service.
567
+ sdk.entities.list_entities_async() -> typing.List[uipath.platform.entities.entities.Entity]
568
+
569
+ # List records from an entity with optional pagination and schema validation.
570
+ sdk.entities.list_records(entity_key: str, schema: Optional[Type[Any]]=None, start: Optional[int]=None, limit: Optional[int]=None, expansion_level: Optional[int]=None, filter: Optional[str]=None, orderby: Optional[str]=None, select: Optional[List[str]]=None, expand: Optional[List[str]]=None) -> uipath.platform.entities.entities.EntityRecordsListResponse
571
+
572
+ # Asynchronously list records from an entity with optional pagination and schema validation.
573
+ sdk.entities.list_records_async(entity_key: str, schema: Optional[Type[Any]]=None, start: Optional[int]=None, limit: Optional[int]=None, expansion_level: Optional[int]=None, filter: Optional[str]=None, orderby: Optional[str]=None, select: Optional[List[str]]=None, expand: Optional[List[str]]=None) -> uipath.platform.entities.entities.EntityRecordsListResponse
574
+
575
+ # Query entity records using a validated SQL query.
576
+ sdk.entities.query_entity_records(sql_query: str) -> typing.List[typing.Dict[str, typing.Any]]
577
+
578
+ # Asynchronously query entity records using a validated SQL query.
579
+ sdk.entities.query_entity_records_async(sql_query: str) -> typing.List[typing.Dict[str, typing.Any]]
580
+
581
+ # Resolve an agent entity set, applying resource overwrites.
582
+ sdk.entities.resolve_entity_set(items: List[uipath.platform.entities.entities.DataFabricEntityItem]) -> uipath.platform.entities.entities.EntitySetResolution
583
+
584
+ # Resolve an agent entity set, applying resource overwrites.
585
+ sdk.entities.resolve_entity_set_async(items: List[uipath.platform.entities.entities.DataFabricEntityItem]) -> uipath.platform.entities.entities.EntitySetResolution
586
+
587
+ # Retrieve an entity by its key.
588
+ sdk.entities.retrieve(entity_key: str) -> uipath.platform.entities.entities.Entity
589
+
590
+ # Asynchronously retrieve an entity by its key.
591
+ sdk.entities.retrieve_async(entity_key: str) -> uipath.platform.entities.entities.Entity
592
+
593
+ # Retrieve an entity by its name.
594
+ sdk.entities.retrieve_by_name(entity_name: str, folder_key: Optional[str]=None) -> uipath.platform.entities.entities.Entity
595
+
596
+ # Asynchronously retrieve an entity by its name.
597
+ sdk.entities.retrieve_by_name_async(entity_name: str, folder_key: Optional[str]=None) -> uipath.platform.entities.entities.Entity
598
+
599
+ # Retrieve records with structured filters, sorting, expansion, joins, and aggregates.
600
+ sdk.entities.retrieve_records(entity_key: str, filter_group: Optional[uipath.platform.entities.entities.EntityQueryFilterGroup]=None, sort_options: Optional[List[uipath.platform.entities.entities.EntityQuerySortOption]]=None, selected_fields: Optional[List[str]]=None, expansions: Optional[List[Any]]=None, expansion_level: Optional[int]=None, aggregates: Optional[List[uipath.platform.entities.entities.EntityAggregate]]=None, group_by: Optional[List[str]]=None, joins: Optional[List[uipath.platform.entities.entities.EntityJoin]]=None, binnings: Optional[List[uipath.platform.entities.entities.EntityBinning]]=None, start: Optional[int]=None, limit: Optional[int]=None) -> uipath.platform.entities.entities.RetrieveEntityRecordsResponse
601
+
602
+ # Asynchronously retrieve records with structured filters, sorting, expansion, joins, and aggregates.
603
+ sdk.entities.retrieve_records_async(entity_key: str, filter_group: Optional[uipath.platform.entities.entities.EntityQueryFilterGroup]=None, sort_options: Optional[List[uipath.platform.entities.entities.EntityQuerySortOption]]=None, selected_fields: Optional[List[str]]=None, expansions: Optional[List[Any]]=None, expansion_level: Optional[int]=None, aggregates: Optional[List[uipath.platform.entities.entities.EntityAggregate]]=None, group_by: Optional[List[str]]=None, joins: Optional[List[uipath.platform.entities.entities.EntityJoin]]=None, binnings: Optional[List[uipath.platform.entities.entities.EntityBinning]]=None, start: Optional[int]=None, limit: Optional[int]=None) -> uipath.platform.entities.entities.RetrieveEntityRecordsResponse
604
+
605
+ # Update an entity's display name, description, and/or RBAC flag.
606
+ sdk.entities.update_entity_metadata(entity_id: str, metadata: Union[uipath.platform.entities.entities.EntityMetadataUpdateOptions, Dict[str, Any]]) -> None
607
+
608
+ # Asynchronously update an entity's display name, description, and/or RBAC flag.
609
+ sdk.entities.update_entity_metadata_async(entity_id: str, metadata: Union[uipath.platform.entities.entities.EntityMetadataUpdateOptions, Dict[str, Any]]) -> None
610
+
611
+ # Update a single record by id and return the updated row.
612
+ sdk.entities.update_record(entity_key: str, record_id: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
613
+
614
+ # Asynchronously update a single record by id.
615
+ sdk.entities.update_record_async(entity_key: str, record_id: str, data: Any, expansion_level: Optional[int]=None) -> uipath.platform.entities.entities.EntityRecord
616
+
617
+ # Update multiple records in an entity in a single batch operation.
618
+ sdk.entities.update_records(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
619
+
620
+ # Asynchronously update multiple records in an entity in a single batch operation.
621
+ sdk.entities.update_records_async(entity_key: str, records: List[Any], schema: Optional[Type[Any]]=None, expansion_level: Optional[int]=None, fail_on_first: Optional[bool]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
622
+
623
+ # Upload a file attachment to a File-type field on a record.
624
+ sdk.entities.upload_attachment(entity_id: str, record_id: str, field_name: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
625
+
626
+ # Asynchronously upload a file attachment to a File-type field on a record.
627
+ sdk.entities.upload_attachment_async(entity_id: str, record_id: str, field_name: str, file: Union[bytes, bytearray, memoryview, NoneType]=None, file_path: Optional[str]=None, expansion_level: Optional[int]=None) -> typing.Dict[str, typing.Any]
628
+
629
+ # Parse a batch response, optionally validating success records against ``schema``.
630
+ sdk.entities.validate_entity_batch(batch_response: httpx.Response, schema: Optional[Type[Any]]=None) -> uipath.platform.entities.entities.EntityRecordsBatchResponse
631
+
632
+ ```
633
+
634
+ ### Folders
635
+
636
+ Folders service
637
+
638
+ ```python
639
+ # Retrieve the personal workspace folder for the current user.
640
+ sdk.folders.get_personal_workspace() -> uipath.platform.orchestrator.folder.PersonalWorkspace
641
+
642
+ # Asynchronously retrieve the personal workspace folder for the current user.
643
+ sdk.folders.get_personal_workspace_async() -> uipath.platform.orchestrator.folder.PersonalWorkspace
644
+
645
+ # Resolve a folder path to its corresponding folder key.
646
+ sdk.folders.retrieve_folder_key(folder_path: str | None) -> str | None
647
+
648
+ # Asynchronously resolve a folder path to its corresponding folder key.
649
+ sdk.folders.retrieve_folder_key_async(folder_path: str | None) -> str | None
650
+
651
+ # Retrieve the folder key by folder path with pagination support.
652
+ sdk.folders.retrieve_key(folder_path: str) -> typing.Optional[str]
653
+
654
+ # Retrieve the folder key by folder path with pagination support.
655
+ sdk.folders.retrieve_key_async(folder_path: str) -> typing.Optional[str]
656
+
657
+ ```
658
+
659
+ ### Guardrails
660
+
661
+ Guardrails service
662
+
663
+ ```python
664
+ # Validate input text using the provided guardrail.
665
+ sdk.guardrails.evaluate_guardrail(input_data: str | dict[str, Any], guardrail: uipath.platform.guardrails.guardrails.BuiltInValidatorGuardrail) -> uipath.core.guardrails.guardrails.GuardrailValidationResult
666
+
667
+ ```
668
+
669
+ ### Jobs
670
+
671
+ Jobs service
672
+
673
+ ```python
674
+ # Create and upload an attachment, optionally linking it to a job.
675
+ sdk.jobs.create_attachment(name: str, content: Union[str, bytes, NoneType]=None, source_path: Union[str, pathlib.Path, NoneType]=None, job_key: Union[str, uuid.UUID, NoneType]=None, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uuid.UUID
676
+
677
+ # Create and upload an attachment asynchronously, optionally linking it to a job.
678
+ sdk.jobs.create_attachment_async(name: str, content: Union[str, bytes, NoneType]=None, source_path: Union[str, pathlib.Path, NoneType]=None, job_key: Union[str, uuid.UUID, NoneType]=None, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uuid.UUID
679
+
680
+ # Check if job exists.
681
+ sdk.jobs.exists(job_key: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
682
+
683
+ # Async version of exists().
684
+ sdk.jobs.exists_async(job_key: str, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> bool
685
+
686
+ # Get the actual output data, downloading from attachment if necessary.
687
+ sdk.jobs.extract_output(job: uipath.platform.orchestrator.job.Job) -> typing.Optional[str]
688
+
689
+ # Asynchronously fetch the actual output data, downloading from attachment if necessary.
690
+ sdk.jobs.extract_output_async(job: uipath.platform.orchestrator.job.Job) -> typing.Optional[str]
691
+
692
+ # Link an attachment to a job.
693
+ sdk.jobs.link_attachment(attachment_key: uuid.UUID, job_key: uuid.UUID, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None)
694
+
695
+ # Link an attachment to a job asynchronously.
696
+ sdk.jobs.link_attachment_async(attachment_key: uuid.UUID, job_key: uuid.UUID, category: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None)
697
+
698
+ # List jobs using OData API with offset-based pagination.
699
+ sdk.jobs.list(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.job.Job]
700
+
701
+ # Async version of list() with offset-based pagination.
702
+ sdk.jobs.list_async(folder_path: Optional[str]=None, folder_key: Optional[str]=None, filter: Optional[str]=None, orderby: Optional[str]=None, skip: int=0, top: int=100) -> uipath.platform.common.paging.PagedResult[uipath.platform.orchestrator.job.Job]
703
+
704
+ # List attachments associated with a specific job.
705
+ sdk.jobs.list_attachments(job_key: uuid.UUID, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[str]
706
+
707
+ # List attachments associated with a specific job asynchronously.
708
+ sdk.jobs.list_attachments_async(job_key: uuid.UUID, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> typing.List[str]
709
+
710
+ # Restart a completed or failed job.
711
+ sdk.jobs.restart(job_key: str, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.job.Job
712
+
713
+ # Async version of restart().
714
+ sdk.jobs.restart_async(job_key: str, folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> uipath.platform.orchestrator.job.Job
715
+
716
+ # Sends a payload to resume a paused job waiting for input, identified by its inbox ID.
717
+ sdk.jobs.resume(inbox_id: Optional[str]=None, job_id: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, payload: Any) -> None
718
+
719
+ # Asynchronously sends a payload to resume a paused job waiting for input, identified by its inbox ID.
720
+ sdk.jobs.resume_async(inbox_id: Optional[str]=None, job_id: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, payload: Any) -> None
721
+
722
+ # Retrieve a job identified by its key.
723
+ sdk.jobs.retrieve(job_key: str, folder_key: str | None=None, folder_path: str | None=None, process_name: str | None=None) -> uipath.platform.orchestrator.job.Job
724
+
725
+ # Fetch payload data for API triggers.
726
+ sdk.jobs.retrieve_api_payload(inbox_id: str) -> typing.Any
727
+
728
+ # Asynchronously fetch payload data for API triggers.
729
+ sdk.jobs.retrieve_api_payload_async(inbox_id: str) -> typing.Any
730
+
731
+ # Asynchronously retrieve a job identified by its key.
732
+ sdk.jobs.retrieve_async(job_key: str, folder_key: str | None=None, folder_path: str | None=None, process_name: str | None=None) -> uipath.platform.orchestrator.job.Job
733
+
734
+ # Fetch payload data for Integration Services (Inbox) triggers.
735
+ sdk.jobs.retrieve_inbox_payload(inbox_id: str) -> typing.Any
736
+
737
+ # Asynchronously fetch payload data for Integration Services (Inbox) triggers.
738
+ sdk.jobs.retrieve_inbox_payload_async(inbox_id: str) -> typing.Any
739
+
740
+ # Stop one or more jobs with specified strategy.
741
+ sdk.jobs.stop(job_keys: List[str], strategy: str="SoftStop", folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
742
+
743
+ # Async version of stop().
744
+ sdk.jobs.stop_async(job_keys: List[str], strategy: str="SoftStop", folder_path: Optional[str]=None, folder_key: Optional[str]=None) -> None
745
+
746
+ ```
747
+
748
+ ### Llm
749
+
750
+ Llm service
751
+
752
+ ```python
753
+ # Generate chat completions using UiPath's normalized LLM Gateway API.
754
+ sdk.llm.chat_completions(messages: list[dict[str, str]] | list[tuple[str, str]], model: str="gpt-4.1-mini-2025-04-14", max_tokens: int=4096, temperature: float=0, n: int=1, frequency_penalty: float=0, presence_penalty: float=0, top_p: float | None=1, top_k: int | None=None, tools: list[uipath.platform.chat.llm_gateway.ToolDefinition] | None=None, tool_choice: Union[uipath.platform.chat.llm_gateway.AutoToolChoice, uipath.platform.chat.llm_gateway.RequiredToolChoice, uipath.platform.chat.llm_gateway.SpecificToolChoice, Literal['auto', 'none'], NoneType]=None, response_format: dict[str, Any] | type[pydantic.main.BaseModel] | None=None, api_version: str="2024-08-01-preview")
755
+
756
+ ```
757
+
758
+ ### Llm Openai
759
+
760
+ Llm Openai service
761
+
762
+ ```python
763
+ # Generate chat completions using UiPath's LLM Gateway service.
764
+ sdk.llm_openai.chat_completions(messages: list[dict[str, str]], model: str="gpt-4.1-mini-2025-04-14", max_tokens: int=4096, temperature: float=0, response_format: dict[str, Any] | type[pydantic.main.BaseModel] | None=None, api_version: str="2024-10-21")
765
+
766
+ # Generate text embeddings using UiPath's LLM Gateway service.
767
+ sdk.llm_openai.embeddings(input: str, embedding_model: str="text-embedding-ada-002", openai_api_version: str="2024-10-21")
768
+
769
+ ```
770
+
771
+ ### Mcp
772
+
773
+ Mcp service
774
+
775
+ ```python
776
+ # List all MCP servers.
777
+ sdk.mcp.list(folder_path: str | None=None) -> typing.List[uipath.platform.orchestrator.mcp.McpServer]
778
+
779
+ # Asynchronously list all MCP servers.
780
+ sdk.mcp.list_async(folder_path: str | None=None) -> typing.List[uipath.platform.orchestrator.mcp.McpServer]
781
+
782
+ # Retrieve a specific MCP server by its slug.
783
+ sdk.mcp.retrieve(slug: str, folder_path: str | None=None) -> uipath.platform.orchestrator.mcp.McpServer
784
+
785
+ # Asynchronously retrieve a specific MCP server by its slug.
786
+ sdk.mcp.retrieve_async(slug: str, folder_path: str | None=None) -> uipath.platform.orchestrator.mcp.McpServer
787
+
788
+ ```
789
+
790
+ ### Memory
791
+
792
+ Memory service
793
+
794
+ ```python
795
+ # Create a new memory space.
796
+ sdk.memory.create(name: str, description: Optional[str]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpace
797
+
798
+ # Asynchronously create a new memory space.
799
+ sdk.memory.create_async(name: str, description: Optional[str]=None, is_encrypted: Optional[bool]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpace
800
+
801
+ # Ingest a resolved escalation outcome into memory.
802
+ sdk.memory.escalation_ingest(memory_space_id: str, request: uipath.platform.memory.memory.EscalationMemoryIngestRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
803
+
804
+ # Asynchronously ingest a resolved escalation outcome into memory.
805
+ sdk.memory.escalation_ingest_async(memory_space_id: str, request: uipath.platform.memory.memory.EscalationMemoryIngestRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> None
806
+
807
+ # Search escalation memory for previously resolved outcomes.
808
+ sdk.memory.escalation_search(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.EscalationMemorySearchResponse
809
+
810
+ # Asynchronously search escalation memory for previously resolved outcomes.
811
+ sdk.memory.escalation_search_async(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.EscalationMemorySearchResponse
812
+
813
+ # List memory spaces with optional OData query parameters.
814
+ sdk.memory.list(filter: Optional[str]=None, orderby: Optional[str]=None, top: Optional[int]=None, skip: Optional[int]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpaceListResponse
815
+
816
+ # Asynchronously list memory spaces.
817
+ sdk.memory.list_async(filter: Optional[str]=None, orderby: Optional[str]=None, top: Optional[int]=None, skip: Optional[int]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySpaceListResponse
818
+
819
+ # Search a memory space via LLMOps.
820
+ sdk.memory.search(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySearchResponse
821
+
822
+ # Asynchronously search a memory space via LLMOps.
823
+ sdk.memory.search_async(memory_space_id: str, request: uipath.platform.memory.memory.MemorySearchRequest, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> uipath.platform.memory.memory.MemorySearchResponse
824
+
825
+ ```
826
+
827
+ ### Orchestrator Setup
828
+
829
+ Orchestrator Setup service
830
+
831
+ ```python
832
+ # Fire-and-forget POST requests to enable first run for StudioWeb.
833
+ sdk.orchestrator_setup.enable_first_run() -> None
834
+
835
+ # Fire-and-forget POST requests to enable first run for StudioWeb.
836
+ sdk.orchestrator_setup.enable_first_run_async() -> None
837
+
838
+ ```
839
+
840
+ ### Processes
841
+
842
+ Processes service
843
+
844
+ ```python
845
+ # Start execution of a process by its name.
846
+ sdk.processes.invoke(name: str, input_arguments: Optional[Dict[str, Any]]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, attachments: Optional[list[uipath.platform.attachments.attachments.Attachment]]=None, parent_operation_id: Optional[str]=None, run_as_me: Optional[bool]=None, **kwargs) -> uipath.platform.orchestrator.job.Job
847
+
848
+ # Asynchronously start execution of a process by its name.
849
+ sdk.processes.invoke_async(name: str, input_arguments: Optional[Dict[str, Any]]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None, attachments: Optional[list[uipath.platform.attachments.attachments.Attachment]]=None, parent_operation_id: Optional[str]=None, run_as_me: Optional[bool]=None, **kwargs) -> uipath.platform.orchestrator.job.Job
850
+
851
+ ```
852
+
853
+ ### Queues
854
+
855
+ Queues service
856
+
857
+ ```python
858
+ # Completes a transaction item with the specified result.
859
+ sdk.queues.complete_transaction_item(transaction_key: str, result: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItemResult], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
860
+
861
+ # Asynchronously completes a transaction item with the specified result.
862
+ sdk.queues.complete_transaction_item_async(transaction_key: str, result: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItemResult], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
863
+
864
+ # Creates a new queue item in the Orchestrator.
865
+ sdk.queues.create_item(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
866
+
867
+ # Asynchronously creates a new queue item in the Orchestrator.
868
+ sdk.queues.create_item_async(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem], queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
869
+
870
+ # Creates multiple queue items in bulk.
871
+ sdk.queues.create_items(items: List[Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem]], queue_name: str, commit_type: <enum 'CommitType, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
872
+
873
+ # Asynchronously creates multiple queue items in bulk.
874
+ sdk.queues.create_items_async(items: List[Union[Dict[str, Any], uipath.platform.orchestrator.queues.QueueItem]], queue_name: str, commit_type: <enum 'CommitType, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
875
+
876
+ # Creates a new transaction item in a queue.
877
+ sdk.queues.create_transaction_item(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItem], queue_name: Optional[str]=None, no_robot: bool=False, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
878
+
879
+ # Asynchronously creates a new transaction item in a queue.
880
+ sdk.queues.create_transaction_item_async(item: Union[Dict[str, Any], uipath.platform.orchestrator.queues.TransactionItem], queue_name: Optional[str]=None, no_robot: bool=False, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
881
+
882
+ # Retrieves a list of queue items from the Orchestrator.
883
+ sdk.queues.list_items(queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
884
+
885
+ # Asynchronously retrieves a list of queue items from the Orchestrator.
886
+ sdk.queues.list_items_async(queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
887
+
888
+ # Updates the progress of a transaction item.
889
+ sdk.queues.update_progress_of_transaction_item(transaction_key: str, progress: str, queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
890
+
891
+ # Asynchronously updates the progress of a transaction item.
892
+ sdk.queues.update_progress_of_transaction_item_async(transaction_key: str, progress: str, queue_name: Optional[str]=None, folder_key: Optional[str]=None, folder_path: Optional[str]=None) -> httpx.Response
893
+
894
+ ```
895
+
896
+ ### Remote A2A
897
+
898
+ Remote A2A service
899
+
900
+ ```python
901
+ # List Remote A2A agents.
902
+ sdk.remote_a2a.list(top: int | None=None, skip: int | None=None, search: str | None=None, folder_path: str | None=None) -> typing.List[uipath.platform.agenthub.remote_a2a.RemoteA2aAgent]
903
+
904
+ # Asynchronously list Remote A2A agents.
905
+ sdk.remote_a2a.list_async(top: int | None=None, skip: int | None=None, search: str | None=None, folder_path: str | None=None) -> typing.List[uipath.platform.agenthub.remote_a2a.RemoteA2aAgent]
906
+
907
+ # Retrieve a specific Remote A2A agent by slug.
908
+ sdk.remote_a2a.retrieve(slug: str, folder_path: str | None=None) -> uipath.platform.agenthub.remote_a2a.RemoteA2aAgent
909
+
910
+ # Asynchronously retrieve a specific Remote A2A agent by slug.
911
+ sdk.remote_a2a.retrieve_async(slug: str, folder_path: str | None=None) -> uipath.platform.agenthub.remote_a2a.RemoteA2aAgent
912
+
913
+ ```
914
+
915
+ ### Resource Catalog
916
+
917
+ Resource Catalog service
918
+
919
+ ```python
920
+ # Get tenant scoped resources and folder scoped resources (accessible to the user).
921
+ sdk.resource_catalog.list(resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
922
+
923
+ # Asynchronously get tenant scoped resources and folder scoped resources (accessible to the user).
924
+ sdk.resource_catalog.list_async(resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
925
+
926
+ # Get resources of a specific type (tenant scoped or folder scoped).
927
+ sdk.resource_catalog.list_by_type(resource_type: <enum 'ResourceType, name: Optional[str]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
928
+
929
+ # Asynchronously get resources of a specific type (tenant scoped or folder scoped).
930
+ sdk.resource_catalog.list_by_type_async(resource_type: <enum 'ResourceType, name: Optional[str]=None, resource_sub_types: Optional[List[str]]=None, folder_path: Optional[str]=None, folder_key: Optional[str]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
931
+
932
+ # Search for tenant scoped resources and folder scoped resources (accessible to the user).
933
+ sdk.resource_catalog.search(name: Optional[str]=None, resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, page_size: int=20) -> typing.Iterator[uipath.platform.resource_catalog.resource_catalog.Resource]
934
+
935
+ # Asynchronously search for tenant scoped resources and folder scoped resources (accessible to the user).
936
+ sdk.resource_catalog.search_async(name: Optional[str]=None, resource_types: Optional[List[uipath.platform.resource_catalog.resource_catalog.ResourceType]]=None, resource_sub_types: Optional[List[str]]=None, page_size: int=20) -> typing.AsyncGenerator[uipath.platform.resource_catalog.resource_catalog.Resource, NoneType]
937
+
938
+ ```
939
+
940
+ ### Semantic Proxy
941
+
942
+ Semantic Proxy service
943
+
944
+ ```python
945
+ # Detect PII in the provided documents and/or files.
946
+ sdk.semantic_proxy.detect_pii(request: uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionRequest) -> uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionResponse
947
+
948
+ # Detect PII in the provided documents and/or files (async).
949
+ sdk.semantic_proxy.detect_pii_async(request: uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionRequest) -> uipath.platform.semantic_proxy.semantic_proxy.PiiDetectionResponse
950
+
951
+ ```
952
+
953
+ ### Tasks
954
+
955
+ Tasks service
956
+
957
+ ```python
958
+ # Creates a new task synchronously.
959
+ sdk.tasks.create(title: str, data: Optional[Dict[str, Any]]=None, app_name: Optional[str]=None, app_key: Optional[str]=None, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, assignee: Optional[str]=None, recipient: Optional[uipath.platform.action_center.tasks.TaskRecipient]=None, priority: Optional[str]=None, labels: Optional[List[str]]=None, is_actionable_message_enabled: Optional[bool]=None, actionable_message_metadata: Optional[Dict[str, Any]]=None, source_name: str="Agent") -> uipath.platform.action_center.tasks.Task
960
+
961
+ # Creates a new action asynchronously.
962
+ sdk.tasks.create_async(title: str, data: Optional[Dict[str, Any]]=None, app_name: Optional[str]=None, app_key: Optional[str]=None, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, assignee: Optional[str]=None, recipient: Optional[uipath.platform.action_center.tasks.TaskRecipient]=None, priority: Optional[str]=None, labels: Optional[List[str]]=None, is_actionable_message_enabled: Optional[bool]=None, actionable_message_metadata: Optional[Dict[str, Any]]=None, source_name: str="Agent") -> uipath.platform.action_center.tasks.Task
963
+
964
+ # Retrieves a task by its key synchronously.
965
+ sdk.tasks.retrieve(action_key: str, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, app_name: str | None=None) -> uipath.platform.action_center.tasks.Task
966
+
967
+ # Retrieves a task by its key asynchronously.
968
+ sdk.tasks.retrieve_async(action_key: str, app_folder_path: Optional[str]=None, app_folder_key: Optional[str]=None, app_name: str | None=None) -> uipath.platform.action_center.tasks.Task
969
+
970
+ ```
971
+
agents/agent_2_sanctions_screener/.claude/commands/eval.md ADDED
@@ -0,0 +1,287 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ allowed-tools: Bash, Read, Write, Edit, Glob
3
+ description: Create and run agent evaluations
4
+ ---
5
+
6
+ I'll help you create and run evaluations for your UiPath agent.
7
+
8
+ ## Step 1: Check project setup
9
+
10
+ Let me check your project structure:
11
+
12
+ !ls -la evaluations/ entry-points.json 2>/dev/null || echo "NEEDS_SETUP"
13
+
14
+ # Check if schemas might be stale (main.py newer than entry-points.json)
15
+ !if [ -f main.py ] && [ -f entry-points.json ] && [ main.py -nt entry-points.json ]; then echo "SCHEMAS_MAY_BE_STALE"; fi
16
+
17
+ ### If NEEDS_SETUP
18
+
19
+ If `entry-points.json` doesn't exist, initialize the project first:
20
+
21
+ !uv run uipath init
22
+
23
+ Then re-run this skill.
24
+
25
+ ### If SCHEMAS_MAY_BE_STALE
26
+
27
+ Your `main.py` is newer than `entry-points.json`. Refresh schemas:
28
+
29
+ !uv run uipath init --no-agents-md-override
30
+
31
+ ## Step 2: What would you like to do?
32
+
33
+ 1. **Create new eval set** - Set up evaluations from scratch
34
+ 2. **Add test case** - Add a test to existing eval set
35
+ 3. **Run evaluations** - Execute tests and see results
36
+ 4. **Analyze failures** - Debug failing tests
37
+
38
+ ---
39
+
40
+ ## Creating an Eval Set
41
+
42
+ First, create the directory structure:
43
+
44
+ !mkdir -p evaluations/eval-sets evaluations/evaluators
45
+
46
+ Read the agent's Input/Output schema from entry-points.json to understand the data types.
47
+
48
+ ### Evaluator Selection Guide
49
+
50
+ | If your output is... | Use this evaluator | evaluatorTypeId |
51
+ |---------------------|-------------------|-----------------|
52
+ | Exact string/number | `ExactMatchEvaluator` | `uipath-exact-match` |
53
+ | Contains key phrases | `ContainsEvaluator` | `uipath-contains` |
54
+ | Semantically correct | `LLMJudgeOutputEvaluator` | `uipath-llm-judge-output-semantic-similarity` |
55
+ | JSON with numbers | `JsonSimilarityEvaluator` | `uipath-json-similarity` |
56
+
57
+ ### Step 1: Create Evaluator Config Files
58
+
59
+ **Each evaluator needs a JSON config file** in `evaluations/evaluators/`.
60
+
61
+ **ExactMatchEvaluator** (`evaluations/evaluators/exact-match.json`):
62
+ ```json
63
+ {
64
+ "version": "1.0",
65
+ "id": "ExactMatchEvaluator",
66
+ "name": "ExactMatchEvaluator",
67
+ "description": "Checks for exact output match",
68
+ "evaluatorTypeId": "uipath-exact-match",
69
+ "evaluatorConfig": {
70
+ "name": "ExactMatchEvaluator",
71
+ "targetOutputKey": "*"
72
+ }
73
+ }
74
+ ```
75
+
76
+ **LLMJudgeOutputEvaluator** (`evaluations/evaluators/llm-judge-output.json`):
77
+ ```json
78
+ {
79
+ "version": "1.0",
80
+ "id": "LLMJudgeOutputEvaluator",
81
+ "name": "LLMJudgeOutputEvaluator",
82
+ "description": "Uses LLM to judge semantic similarity",
83
+ "evaluatorTypeId": "uipath-llm-judge-output-semantic-similarity",
84
+ "evaluatorConfig": {
85
+ "name": "LLMJudgeOutputEvaluator",
86
+ "model": "gpt-4o-mini-2024-07-18"
87
+ }
88
+ }
89
+ ```
90
+
91
+ **JsonSimilarityEvaluator** (`evaluations/evaluators/json-similarity.json`):
92
+ ```json
93
+ {
94
+ "version": "1.0",
95
+ "id": "JsonSimilarityEvaluator",
96
+ "name": "JsonSimilarityEvaluator",
97
+ "description": "Compares JSON structures",
98
+ "evaluatorTypeId": "uipath-json-similarity",
99
+ "evaluatorConfig": {
100
+ "name": "JsonSimilarityEvaluator",
101
+ "targetOutputKey": "*"
102
+ }
103
+ }
104
+ ```
105
+
106
+ **ContainsEvaluator** (`evaluations/evaluators/contains.json`):
107
+ ```json
108
+ {
109
+ "version": "1.0",
110
+ "id": "ContainsEvaluator",
111
+ "name": "ContainsEvaluator",
112
+ "description": "Checks if output contains text",
113
+ "evaluatorTypeId": "uipath-contains",
114
+ "evaluatorConfig": {
115
+ "name": "ContainsEvaluator"
116
+ }
117
+ }
118
+ ```
119
+
120
+ ### Step 2: Create Eval Set
121
+
122
+ **Eval Set Template** (`evaluations/eval-sets/default.json`):
123
+ ```json
124
+ {
125
+ "version": "1.0",
126
+ "id": "default-eval-set",
127
+ "name": "Default Evaluation Set",
128
+ "evaluatorRefs": ["ExactMatchEvaluator"],
129
+ "evaluations": [
130
+ {
131
+ "id": "test-1",
132
+ "name": "Test description",
133
+ "inputs": {
134
+ "field": "value"
135
+ },
136
+ "evaluationCriterias": {
137
+ "ExactMatchEvaluator": {
138
+ "expectedOutput": {
139
+ "result": "expected value"
140
+ }
141
+ }
142
+ }
143
+ }
144
+ ]
145
+ }
146
+ ```
147
+
148
+ **Important notes:**
149
+ - `evaluatorRefs` must list ALL evaluators used in any test case
150
+ - Each evaluator in `evaluatorRefs` needs a matching JSON config in `evaluations/evaluators/`
151
+ - `evaluationCriterias` keys must match entries in `evaluatorRefs`
152
+ - Use `expectedOutput` for most evaluators
153
+ - LLM evaluators need `model` in their config. Available models are defined in the SDK's `ChatModels` class (`uipath.platform.chat.ChatModels`):
154
+ - `gpt-4o-mini-2024-07-18` (recommended for cost-efficiency)
155
+ - `gpt-4o-2024-08-06` (higher quality, higher cost)
156
+ - `o3-mini-2025-01-31` (latest reasoning model)
157
+ - Model availability varies by region and tenant configuration
158
+ - Check your UiPath Automation Cloud portal under AI Trust Layer for available models in your region
159
+
160
+ ---
161
+
162
+ ## Adding a Test Case
163
+
164
+ When adding a test to an existing eval set:
165
+
166
+ 1. Read the existing eval set
167
+ 2. Check which evaluators are in `evaluatorRefs`
168
+ 3. Add the new test to `evaluations` array
169
+ 4. If using a new evaluator, add it to `evaluatorRefs`
170
+
171
+ ### Test Case Template
172
+
173
+ ```json
174
+ {
175
+ "id": "test-{n}",
176
+ "name": "Description of what this tests",
177
+ "inputs": { },
178
+ "evaluationCriterias": {
179
+ "EvaluatorName": {
180
+ "expectedOutput": { }
181
+ }
182
+ }
183
+ }
184
+ ```
185
+
186
+ ---
187
+
188
+ ## Running Evaluations
189
+
190
+ First, read entry-points.json to get the entrypoint name (e.g., `main`):
191
+
192
+ !uv run uipath eval main evaluations/eval-sets/default.json --output-file eval-results.json
193
+
194
+ **Note:** Replace `main` with your actual entrypoint from entry-points.json.
195
+
196
+ ### Analyze Results
197
+
198
+ After running, read `eval-results.json` and show:
199
+ - Pass/fail summary table
200
+ - For failures: expected vs actual output
201
+ - Suggestions for fixing or changing evaluators
202
+
203
+ ### Results Format
204
+
205
+ ```json
206
+ {
207
+ "evaluationSetResults": [{
208
+ "evaluationRunResults": [
209
+ {
210
+ "evaluationId": "test-1",
211
+ "evaluatorId": "ExactMatchEvaluator",
212
+ "result": { "score": 1.0 },
213
+ "errorMessage": null
214
+ }
215
+ ]
216
+ }]
217
+ }
218
+ ```
219
+
220
+ - Score 1.0 = PASS
221
+ - Score < 1.0 = FAIL (show expected vs actual)
222
+ - errorMessage present = ERROR (show message)
223
+
224
+ ---
225
+
226
+ ## Evaluator Reference
227
+
228
+ ### Deterministic Evaluators
229
+
230
+ **ExactMatchEvaluator** - Exact output matching
231
+ ```json
232
+ "ExactMatchEvaluator": {
233
+ "expectedOutput": { "result": "exact value" }
234
+ }
235
+ ```
236
+
237
+ **ContainsEvaluator** - Output contains substring
238
+ ```json
239
+ "ContainsEvaluator": {
240
+ "searchText": "must contain this"
241
+ }
242
+ ```
243
+
244
+ **JsonSimilarityEvaluator** - JSON comparison with tolerance
245
+ ```json
246
+ "JsonSimilarityEvaluator": {
247
+ "expectedOutput": { "value": 10.0 }
248
+ }
249
+ ```
250
+
251
+ ### LLM-Based Evaluators
252
+
253
+ **LLMJudgeOutputEvaluator** - Semantic correctness
254
+ ```json
255
+ "LLMJudgeOutputEvaluator": {
256
+ "expectedOutput": { "summary": "Expected semantic meaning" }
257
+ }
258
+ ```
259
+
260
+ **LLMJudgeTrajectoryEvaluator** - Validate agent reasoning
261
+ ```json
262
+ "LLMJudgeTrajectoryEvaluator": {
263
+ "expectedAgentBehavior": "The agent should first fetch data, then process it"
264
+ }
265
+ ```
266
+
267
+ ---
268
+
269
+ ## Common Issues
270
+
271
+ ### "No evaluations found"
272
+ - Check `evaluations/eval-sets/` directory exists
273
+ - Verify JSON file is valid
274
+
275
+ ### Evaluator not found
276
+ - Each evaluator needs a JSON config file in `evaluations/evaluators/`
277
+ - Config file must have correct `evaluatorTypeId` (see templates above)
278
+ - Config file must have `name` field at root level
279
+ - LLM evaluators need `model` in `evaluatorConfig`
280
+
281
+ ### Evaluator skipped
282
+ - Ensure evaluator is listed in root `evaluatorRefs` array
283
+ - Check evaluator config file exists in `evaluations/evaluators/`
284
+
285
+ ### Schema mismatch
286
+ - Run `uv run uipath init --no-agents-md-override` to refresh schemas
287
+ - Check `entry-points.json` matches your Input/Output models
agents/agent_2_sanctions_screener/.claude/commands/new-agent.md ADDED
@@ -0,0 +1,103 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ allowed-tools: Bash, Read, Write, Edit, Glob
3
+ description: Create a new UiPath coded agent from a description
4
+ ---
5
+
6
+ I'll help you create a new UiPath coded agent.
7
+
8
+ ## Step 1: Check existing project
9
+
10
+ Let me check if this is an existing UiPath project:
11
+
12
+ !ls uipath.json main.py 2>/dev/null || echo "NEW_PROJECT"
13
+
14
+ ## Step 2: Gather requirements
15
+
16
+ **What should this agent do?**
17
+
18
+ Please describe:
19
+
20
+ - What inputs it needs (e.g., "a file path and bucket name")
21
+ - What it should accomplish (e.g., "process CSV data")
22
+ - What outputs it should return (e.g., "total count and status")
23
+
24
+ I'll generate the agent structure based on your description.
25
+
26
+ ## Step 3: Generate agent
27
+
28
+ After you describe the agent, I will:
29
+
30
+ 1. Create `main.py` with Input/Output Pydantic models and `async def main()`
31
+ 2. Add entrypoint to `uipath.json` under `"functions": {"agent_name": "main.py:main"}`
32
+ 3. Run `uv run uipath init --no-agents-md-override` to generate schemas
33
+
34
+ **Template structure** (from .agent/REQUIRED_STRUCTURE.md):
35
+
36
+ ```python
37
+ from pydantic import BaseModel
38
+ from uipath.platform import UiPath
39
+
40
+ class Input(BaseModel):
41
+ """Input fields for the agent."""
42
+ # Fields based on your description
43
+ pass
44
+
45
+
46
+ class Output(BaseModel):
47
+ """Output fields returned by the agent."""
48
+ # Fields based on your description
49
+ pass
50
+
51
+
52
+ async def main(input: Input) -> Output:
53
+ """Main entry point for the agent.
54
+
55
+ Args:
56
+ input: The input data for the agent.
57
+
58
+ Returns:
59
+ The output data from the agent.
60
+ """
61
+
62
+ uipath = UiPath()
63
+
64
+ # TODO: Implement agent logic
65
+ return Output()
66
+ ```
67
+
68
+ **Important notes:**
69
+
70
+ - Use `async def main` - many SDK methods are async
71
+ - Initialize `UiPath()` inside the function, not at module level
72
+ - After creating main.py, add entrypoint to `uipath.json` under `"functions"`
73
+
74
+ ## Step 4: Update entry-point schemas
75
+
76
+ After creating main.py, regenerate the schemas:
77
+
78
+ !uv run uipath init --no-agents-md-override
79
+
80
+ ## Step 5: Verify
81
+
82
+ Quick test to verify the setup:
83
+
84
+ !uv run uipath run main '{}' 2>&1 | head -30
85
+
86
+ ## Summary
87
+
88
+ Once complete, you'll have:
89
+
90
+ | File | Purpose |
91
+ | ------------------- | ----------------------------------- |
92
+ | `main.py` | Agent code with Input/Output models |
93
+ | `uipath.json` | Project configuration |
94
+ | `entry-points.json` | Entry point schemas |
95
+ | `bindings.json` | Resource bindings |
96
+ | `.agent/` | SDK and CLI reference docs |
97
+
98
+ **Next steps:**
99
+
100
+ 1. Implement your logic in `main()`
101
+ 2. Test: `uv run uipath run main '{"field": "value"}'`
102
+ 3. Create `eval_set.json` for evaluations
103
+ 4. Evaluate: `uv run uipath eval`
agents/agent_2_sanctions_screener/.env ADDED
File without changes
agents/agent_2_sanctions_screener/.uipath/.telemetry.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "ProjectKey": "15eabd06-5d83-46a9-9457-b7418ce29986"
3
+ }
agents/agent_2_sanctions_screener/.uipath/studio_metadata.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "schemaVersion": 1,
3
+ "codeVersion": "1.0.0"
4
+ }