Spaces:
Runtime error
Runtime error
levisstrauss commited on
Commit ·
a87ed52
1
Parent(s): 7d69d21
Fix API error
Browse files- app.py +9 -1
- base_agents.py +260 -335
- requirements.txt +1 -4
app.py
CHANGED
|
@@ -950,7 +950,15 @@ def create_interface():
|
|
| 950 |
"""Validate the API key format."""
|
| 951 |
if not api_key or len(api_key) < 20:
|
| 952 |
return "❌ Please enter a valid API key"
|
| 953 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 954 |
|
| 955 |
def load_example(example_name: str) -> str:
|
| 956 |
"""Load an example product specification."""
|
|
|
|
| 950 |
"""Validate the API key format."""
|
| 951 |
if not api_key or len(api_key) < 20:
|
| 952 |
return "❌ Please enter a valid API key"
|
| 953 |
+
|
| 954 |
+
if api_key.startswith("sk-ant-"):
|
| 955 |
+
return "✅ Anthropic Claude key detected"
|
| 956 |
+
elif api_key.startswith("voc-"):
|
| 957 |
+
return "✅ Vocareum key detected (requires Vocareum network)"
|
| 958 |
+
elif api_key.startswith("sk-"):
|
| 959 |
+
return "✅ OpenAI key detected"
|
| 960 |
+
else:
|
| 961 |
+
return "⚠️ Unknown key format - will try OpenAI"
|
| 962 |
|
| 963 |
def load_example(example_name: str) -> str:
|
| 964 |
"""Load an example product specification."""
|
base_agents.py
CHANGED
|
@@ -1,68 +1,195 @@
|
|
| 1 |
"""
|
| 2 |
Base Agents Library for AI Project Planner
|
| 3 |
|
| 4 |
-
|
| 5 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
"""
|
| 7 |
|
| 8 |
from openai import OpenAI
|
| 9 |
import numpy as np
|
| 10 |
from typing import Dict, Any, List, Optional, Callable
|
| 11 |
import logging
|
|
|
|
| 12 |
|
| 13 |
# Configure logging
|
| 14 |
logging.basicConfig(level=logging.INFO)
|
| 15 |
logger = logging.getLogger(__name__)
|
| 16 |
|
|
|
|
|
|
|
|
|
|
| 17 |
|
| 18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
"""
|
| 20 |
-
|
| 21 |
-
without additional context, memory, or specialized tools.
|
| 22 |
-
|
| 23 |
-
This is the most straightforward method for interacting with an LLM.
|
| 24 |
"""
|
| 25 |
-
|
| 26 |
-
def __init__(self,
|
| 27 |
-
|
| 28 |
-
Initialize the DirectPromptAgent.
|
| 29 |
-
|
| 30 |
-
Args:
|
| 31 |
-
openai_api_key: The OpenAI API key for authentication.
|
| 32 |
-
base_url: Optional custom base URL for API calls.
|
| 33 |
-
"""
|
| 34 |
-
self.openai_api_key = openai_api_key
|
| 35 |
self.base_url = base_url
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
"""Create and return an OpenAI client instance."""
|
| 39 |
-
if self.base_url:
|
| 40 |
-
return OpenAI(api_key=self.openai_api_key, base_url=self.base_url)
|
| 41 |
-
return OpenAI(api_key=self.openai_api_key)
|
| 42 |
|
| 43 |
-
def
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 44 |
"""
|
| 45 |
-
Generate a
|
| 46 |
-
|
| 47 |
Args:
|
| 48 |
-
|
| 49 |
-
|
|
|
|
|
|
|
| 50 |
Returns:
|
| 51 |
-
The
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 52 |
"""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 53 |
try:
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
response = client.chat.completions.create(
|
| 57 |
-
model="gpt-3.5-turbo",
|
| 58 |
-
messages=[
|
| 59 |
-
{"role": "user", "content": prompt}
|
| 60 |
-
],
|
| 61 |
-
temperature=0
|
| 62 |
-
)
|
| 63 |
-
|
| 64 |
-
return response.choices[0].message.content
|
| 65 |
-
|
| 66 |
except Exception as e:
|
| 67 |
logger.error(f"DirectPromptAgent error: {str(e)}")
|
| 68 |
raise
|
|
@@ -71,56 +198,22 @@ class DirectPromptAgent:
|
|
| 71 |
class AugmentedPromptAgent:
|
| 72 |
"""
|
| 73 |
An Augmented Prompt Agent that responds according to a predefined persona.
|
| 74 |
-
|
| 75 |
-
This agent explicitly adopts a persona via a system prompt, leading to
|
| 76 |
-
more targeted and contextually relevant outputs.
|
| 77 |
"""
|
| 78 |
-
|
| 79 |
def __init__(self, openai_api_key: str, persona: str, base_url: str = None):
|
| 80 |
-
|
| 81 |
-
Initialize the AugmentedPromptAgent.
|
| 82 |
-
|
| 83 |
-
Args:
|
| 84 |
-
openai_api_key: The OpenAI API key for authentication.
|
| 85 |
-
persona: The persona the agent should assume.
|
| 86 |
-
base_url: Optional custom base URL for API calls.
|
| 87 |
-
"""
|
| 88 |
-
self.openai_api_key = openai_api_key
|
| 89 |
self.persona = persona
|
| 90 |
-
self.base_url = base_url
|
| 91 |
-
|
| 92 |
-
def _get_client(self) -> OpenAI:
|
| 93 |
-
"""Create and return an OpenAI client instance."""
|
| 94 |
-
if self.base_url:
|
| 95 |
-
return OpenAI(api_key=self.openai_api_key, base_url=self.base_url)
|
| 96 |
-
return OpenAI(api_key=self.openai_api_key)
|
| 97 |
|
| 98 |
def respond(self, input_text: str) -> str:
|
| 99 |
-
"""
|
| 100 |
-
Generate a response using the defined persona.
|
| 101 |
-
|
| 102 |
-
Args:
|
| 103 |
-
input_text: The user's input prompt.
|
| 104 |
-
|
| 105 |
-
Returns:
|
| 106 |
-
The textual content of the LLM's response.
|
| 107 |
-
"""
|
| 108 |
try:
|
| 109 |
-
client = self._get_client()
|
| 110 |
-
|
| 111 |
system_prompt = f"{self.persona} Forget all previous conversational context."
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
],
|
| 119 |
-
temperature=1.0
|
| 120 |
-
)
|
| 121 |
-
|
| 122 |
-
return response.choices[0].message.content
|
| 123 |
-
|
| 124 |
except Exception as e:
|
| 125 |
logger.error(f"AugmentedPromptAgent error: {str(e)}")
|
| 126 |
raise
|
|
@@ -128,70 +221,34 @@ class AugmentedPromptAgent:
|
|
| 128 |
|
| 129 |
class KnowledgeAugmentedPromptAgent:
|
| 130 |
"""
|
| 131 |
-
A Knowledge Augmented Prompt Agent that
|
| 132 |
-
alongside a defined persona when responding to prompts.
|
| 133 |
-
|
| 134 |
-
This agent ensures answers are based on explicitly provided information
|
| 135 |
-
rather than the LLM's inherent knowledge.
|
| 136 |
"""
|
| 137 |
-
|
| 138 |
def __init__(
|
| 139 |
-
|
| 140 |
-
|
| 141 |
-
|
| 142 |
-
|
| 143 |
-
|
| 144 |
):
|
| 145 |
-
|
| 146 |
-
Initialize the KnowledgeAugmentedPromptAgent.
|
| 147 |
-
|
| 148 |
-
Args:
|
| 149 |
-
openai_api_key: The OpenAI API key for authentication.
|
| 150 |
-
persona: The persona the agent should assume.
|
| 151 |
-
knowledge: The specific knowledge to use for responses.
|
| 152 |
-
base_url: Optional custom base URL for API calls.
|
| 153 |
-
"""
|
| 154 |
-
self.openai_api_key = openai_api_key
|
| 155 |
self.persona = persona
|
| 156 |
self.knowledge = knowledge
|
| 157 |
-
self.base_url = base_url
|
| 158 |
-
|
| 159 |
-
def _get_client(self) -> OpenAI:
|
| 160 |
-
"""Create and return an OpenAI client instance."""
|
| 161 |
-
if self.base_url:
|
| 162 |
-
return OpenAI(api_key=self.openai_api_key, base_url=self.base_url)
|
| 163 |
-
return OpenAI(api_key=self.openai_api_key)
|
| 164 |
|
| 165 |
def respond(self, input_text: str) -> str:
|
| 166 |
-
"""
|
| 167 |
-
Generate a response using the persona and provided knowledge only.
|
| 168 |
-
|
| 169 |
-
Args:
|
| 170 |
-
input_text: The user's input prompt.
|
| 171 |
-
|
| 172 |
-
Returns:
|
| 173 |
-
The textual content of the LLM's response.
|
| 174 |
-
"""
|
| 175 |
try:
|
| 176 |
-
client = self._get_client()
|
| 177 |
-
|
| 178 |
system_prompt = (
|
| 179 |
f"You are {self.persona} knowledge-based assistant. Forget all previous context. "
|
| 180 |
f"Use only the following knowledge to answer, do not use your own knowledge: {self.knowledge} "
|
| 181 |
f"Answer the prompt based on this knowledge, not your own."
|
| 182 |
)
|
| 183 |
-
|
| 184 |
-
|
| 185 |
-
|
| 186 |
-
|
| 187 |
-
|
| 188 |
-
|
| 189 |
-
],
|
| 190 |
-
temperature=0
|
| 191 |
-
)
|
| 192 |
-
|
| 193 |
-
return response.choices[0].message.content
|
| 194 |
-
|
| 195 |
except Exception as e:
|
| 196 |
logger.error(f"KnowledgeAugmentedPromptAgent error: {str(e)}")
|
| 197 |
raise
|
|
@@ -199,107 +256,68 @@ class KnowledgeAugmentedPromptAgent:
|
|
| 199 |
|
| 200 |
class EvaluationAgent:
|
| 201 |
"""
|
| 202 |
-
An Evaluation Agent that assesses
|
| 203 |
-
against given criteria, potentially refining through iterative feedback.
|
| 204 |
-
|
| 205 |
-
This agent implements a feedback loop to ensure quality outputs.
|
| 206 |
"""
|
| 207 |
-
|
| 208 |
def __init__(
|
| 209 |
-
|
| 210 |
-
|
| 211 |
-
|
| 212 |
-
|
| 213 |
-
|
| 214 |
-
|
| 215 |
-
|
| 216 |
):
|
| 217 |
-
|
| 218 |
-
Initialize the EvaluationAgent.
|
| 219 |
-
|
| 220 |
-
Args:
|
| 221 |
-
openai_api_key: The OpenAI API key for authentication.
|
| 222 |
-
persona: The evaluator's persona.
|
| 223 |
-
evaluation_criteria: Criteria for evaluating responses.
|
| 224 |
-
worker_agent: The agent whose responses will be evaluated.
|
| 225 |
-
max_interactions: Maximum refinement iterations.
|
| 226 |
-
base_url: Optional custom base URL for API calls.
|
| 227 |
-
"""
|
| 228 |
-
self.openai_api_key = openai_api_key
|
| 229 |
self.persona = persona
|
| 230 |
self.evaluation_criteria = evaluation_criteria
|
| 231 |
self.worker_agent = worker_agent
|
| 232 |
self.max_interactions = max_interactions
|
| 233 |
-
self.base_url = base_url
|
| 234 |
-
|
| 235 |
-
def _get_client(self) -> OpenAI:
|
| 236 |
-
"""Create and return an OpenAI client instance."""
|
| 237 |
-
if self.base_url:
|
| 238 |
-
return OpenAI(api_key=self.openai_api_key, base_url=self.base_url)
|
| 239 |
-
return OpenAI(api_key=self.openai_api_key)
|
| 240 |
|
| 241 |
def evaluate(self, prompt_to_evaluate: str) -> Dict[str, Any]:
|
| 242 |
-
"""
|
| 243 |
-
Evaluate and potentially refine a response through iteration.
|
| 244 |
-
|
| 245 |
-
Args:
|
| 246 |
-
prompt_to_evaluate: The initial prompt to evaluate.
|
| 247 |
-
|
| 248 |
-
Returns:
|
| 249 |
-
Dictionary containing final_response, evaluation, and iterations.
|
| 250 |
-
"""
|
| 251 |
try:
|
| 252 |
-
client = self._get_client()
|
| 253 |
initial_prompt = prompt_to_evaluate
|
| 254 |
response_from_worker = ""
|
| 255 |
evaluation = ""
|
| 256 |
-
|
| 257 |
for i in range(self.max_interactions):
|
| 258 |
logger.info(f"Evaluation iteration {i + 1}/{self.max_interactions}")
|
| 259 |
-
|
| 260 |
# Step 1: Get response from worker agent
|
| 261 |
response_from_worker = self.worker_agent.respond(prompt_to_evaluate)
|
| 262 |
-
|
| 263 |
# Step 2: Evaluate the response
|
| 264 |
eval_prompt = (
|
| 265 |
f"Does the following answer: {response_from_worker}\n"
|
| 266 |
f"Meet this criteria: {self.evaluation_criteria}\n"
|
| 267 |
f"Respond Yes or No, and the reason why it does or doesn't meet the criteria."
|
| 268 |
)
|
| 269 |
-
|
| 270 |
-
|
| 271 |
-
|
| 272 |
-
|
| 273 |
-
|
| 274 |
-
|
| 275 |
-
|
| 276 |
-
temperature=0
|
| 277 |
-
)
|
| 278 |
-
|
| 279 |
-
evaluation = response.choices[0].message.content.strip()
|
| 280 |
-
|
| 281 |
# Step 3: Check if evaluation passes
|
| 282 |
if evaluation.lower().startswith("yes"):
|
| 283 |
logger.info("Evaluation passed!")
|
| 284 |
break
|
| 285 |
-
|
| 286 |
# Step 4: Generate correction instructions
|
| 287 |
instruction_prompt = (
|
| 288 |
f"Provide instructions to fix an answer based on these reasons "
|
| 289 |
f"why it is incorrect: {evaluation}"
|
| 290 |
)
|
| 291 |
-
|
| 292 |
-
|
| 293 |
-
|
| 294 |
-
|
| 295 |
-
|
| 296 |
-
|
| 297 |
-
|
| 298 |
-
|
| 299 |
-
)
|
| 300 |
-
|
| 301 |
-
instructions = response.choices[0].message.content.strip()
|
| 302 |
-
|
| 303 |
# Step 5: Prepare refined prompt
|
| 304 |
prompt_to_evaluate = (
|
| 305 |
f"The original prompt was: {initial_prompt}\n"
|
|
@@ -307,13 +325,12 @@ class EvaluationAgent:
|
|
| 307 |
f"It has been evaluated as incorrect.\n"
|
| 308 |
f"Make only these corrections, do not alter content validity: {instructions}"
|
| 309 |
)
|
| 310 |
-
|
| 311 |
return {
|
| 312 |
"final_response": response_from_worker,
|
| 313 |
"evaluation": evaluation,
|
| 314 |
"iterations": i + 1
|
| 315 |
}
|
| 316 |
-
|
| 317 |
except Exception as e:
|
| 318 |
logger.error(f"EvaluationAgent error: {str(e)}")
|
| 319 |
raise
|
|
@@ -321,114 +338,57 @@ class EvaluationAgent:
|
|
| 321 |
|
| 322 |
class RoutingAgent:
|
| 323 |
"""
|
| 324 |
-
A Routing Agent that directs
|
| 325 |
-
specialized agent based on semantic similarity.
|
| 326 |
-
|
| 327 |
-
Uses embeddings to match prompts with agent descriptions.
|
| 328 |
"""
|
| 329 |
-
|
| 330 |
def __init__(
|
| 331 |
-
|
| 332 |
-
|
| 333 |
-
|
| 334 |
-
|
| 335 |
):
|
| 336 |
-
|
| 337 |
-
Initialize the RoutingAgent.
|
| 338 |
-
|
| 339 |
-
Args:
|
| 340 |
-
openai_api_key: The OpenAI API key for authentication.
|
| 341 |
-
agents: List of agent dictionaries with name, description, and func.
|
| 342 |
-
base_url: Optional custom base URL for API calls.
|
| 343 |
-
"""
|
| 344 |
-
self.openai_api_key = openai_api_key
|
| 345 |
self.agents = agents
|
| 346 |
-
self.base_url = base_url
|
| 347 |
self._embedding_cache = {}
|
| 348 |
|
| 349 |
-
def _get_client(self) -> OpenAI:
|
| 350 |
-
"""Create and return an OpenAI client instance."""
|
| 351 |
-
# Auto-detect Vocareum keys and use their base URL
|
| 352 |
-
if self.openai_api_key and self.openai_api_key.startswith("voc-"):
|
| 353 |
-
return OpenAI(
|
| 354 |
-
api_key=self.openai_api_key,
|
| 355 |
-
base_url="https://openai.vocareum.com/v1"
|
| 356 |
-
)
|
| 357 |
-
if self.base_url:
|
| 358 |
-
return OpenAI(api_key=self.openai_api_key, base_url=self.base_url)
|
| 359 |
-
return OpenAI(api_key=self.openai_api_key)
|
| 360 |
-
|
| 361 |
def get_embedding(self, text: str) -> List[float]:
|
| 362 |
-
"""
|
| 363 |
-
Calculate the embedding of text using the text-embedding-3-large model.
|
| 364 |
-
|
| 365 |
-
Args:
|
| 366 |
-
text: The text to embed.
|
| 367 |
-
|
| 368 |
-
Returns:
|
| 369 |
-
The embedding vector.
|
| 370 |
-
"""
|
| 371 |
-
# Check cache first
|
| 372 |
if text in self._embedding_cache:
|
| 373 |
return self._embedding_cache[text]
|
| 374 |
-
|
| 375 |
-
|
| 376 |
-
|
| 377 |
-
|
| 378 |
-
response = client.embeddings.create(
|
| 379 |
-
model="text-embedding-3-large",
|
| 380 |
-
input=text,
|
| 381 |
-
encoding_format="float"
|
| 382 |
-
)
|
| 383 |
-
|
| 384 |
-
embedding = response.data[0].embedding
|
| 385 |
-
self._embedding_cache[text] = embedding
|
| 386 |
-
|
| 387 |
-
return embedding
|
| 388 |
-
|
| 389 |
-
except Exception as e:
|
| 390 |
-
logger.error(f"Embedding error: {str(e)}")
|
| 391 |
-
raise
|
| 392 |
|
| 393 |
def route(self, user_input: str) -> Any:
|
| 394 |
-
"""
|
| 395 |
-
Route user prompts to the most appropriate agent based on similarity.
|
| 396 |
-
|
| 397 |
-
Args:
|
| 398 |
-
user_input: The user's input prompt.
|
| 399 |
-
|
| 400 |
-
Returns:
|
| 401 |
-
The response from the selected agent's function.
|
| 402 |
-
"""
|
| 403 |
try:
|
| 404 |
input_emb = self.get_embedding(user_input)
|
| 405 |
best_agent = None
|
| 406 |
best_score = -1
|
| 407 |
-
|
| 408 |
for agent in self.agents:
|
| 409 |
agent_emb = self.get_embedding(agent["description"])
|
| 410 |
-
|
| 411 |
if agent_emb is None:
|
| 412 |
continue
|
| 413 |
-
|
| 414 |
# Calculate cosine similarity
|
| 415 |
similarity = np.dot(input_emb, agent_emb) / (
|
| 416 |
-
|
| 417 |
)
|
| 418 |
-
|
| 419 |
logger.info(f"Agent '{agent['name']}' similarity: {similarity:.3f}")
|
| 420 |
-
|
| 421 |
if similarity > best_score:
|
| 422 |
best_score = similarity
|
| 423 |
best_agent = agent
|
| 424 |
-
|
| 425 |
if best_agent is None:
|
| 426 |
return "Sorry, no suitable agent could be selected."
|
| 427 |
-
|
| 428 |
logger.info(f"Selected agent: {best_agent['name']} (score={best_score:.3f})")
|
| 429 |
-
|
| 430 |
return best_agent["func"](user_input)
|
| 431 |
-
|
| 432 |
except Exception as e:
|
| 433 |
logger.error(f"RoutingAgent error: {str(e)}")
|
| 434 |
raise
|
|
@@ -436,75 +396,40 @@ class RoutingAgent:
|
|
| 436 |
|
| 437 |
class ActionPlanningAgent:
|
| 438 |
"""
|
| 439 |
-
An Action Planning Agent that extracts
|
| 440 |
-
from a user's prompt based on provided knowledge.
|
| 441 |
-
|
| 442 |
-
Crucial for constructing agentic workflows by breaking down complex tasks.
|
| 443 |
"""
|
| 444 |
-
|
| 445 |
def __init__(
|
| 446 |
-
|
| 447 |
-
|
| 448 |
-
|
| 449 |
-
|
| 450 |
):
|
| 451 |
-
|
| 452 |
-
Initialize the ActionPlanningAgent.
|
| 453 |
-
|
| 454 |
-
Args:
|
| 455 |
-
openai_api_key: The OpenAI API key for authentication.
|
| 456 |
-
knowledge: The knowledge base for extracting action steps.
|
| 457 |
-
base_url: Optional custom base URL for API calls.
|
| 458 |
-
"""
|
| 459 |
-
self.openai_api_key = openai_api_key
|
| 460 |
self.knowledge = knowledge
|
| 461 |
-
self.base_url = base_url
|
| 462 |
-
|
| 463 |
-
def _get_client(self) -> OpenAI:
|
| 464 |
-
"""Create and return an OpenAI client instance."""
|
| 465 |
-
if self.base_url:
|
| 466 |
-
return OpenAI(api_key=self.openai_api_key, base_url=self.base_url)
|
| 467 |
-
return OpenAI(api_key=self.openai_api_key)
|
| 468 |
|
| 469 |
def extract_steps_from_prompt(self, prompt: str) -> List[str]:
|
| 470 |
-
"""
|
| 471 |
-
Extract actionable steps from a user prompt using provided knowledge.
|
| 472 |
-
|
| 473 |
-
Args:
|
| 474 |
-
prompt: The user's input prompt describing a task.
|
| 475 |
-
|
| 476 |
-
Returns:
|
| 477 |
-
A clean list of action steps.
|
| 478 |
-
"""
|
| 479 |
try:
|
| 480 |
-
client = self._get_client()
|
| 481 |
-
|
| 482 |
system_prompt = (
|
| 483 |
f"You are an action planning agent. Using your knowledge, you extract from the user prompt "
|
| 484 |
f"the steps requested to complete the action the user is asking for. You return the steps as a list. "
|
| 485 |
f"Only return the steps in your knowledge. Forget any previous context. "
|
| 486 |
f"This is your knowledge: {self.knowledge}"
|
| 487 |
)
|
| 488 |
-
|
| 489 |
-
|
| 490 |
-
|
| 491 |
-
|
| 492 |
-
|
| 493 |
-
|
| 494 |
-
|
| 495 |
-
temperature=0
|
| 496 |
-
)
|
| 497 |
-
|
| 498 |
-
response_text = response.choices[0].message.content
|
| 499 |
-
|
| 500 |
# Clean and format the extracted steps
|
| 501 |
steps = response_text.split("\n")
|
| 502 |
cleaned_steps = [step.strip() for step in steps if step.strip()]
|
| 503 |
-
|
| 504 |
logger.info(f"Extracted {len(cleaned_steps)} action steps")
|
| 505 |
-
|
| 506 |
return cleaned_steps
|
| 507 |
-
|
| 508 |
except Exception as e:
|
| 509 |
logger.error(f"ActionPlanningAgent error: {str(e)}")
|
| 510 |
raise
|
|
|
|
| 1 |
"""
|
| 2 |
Base Agents Library for AI Project Planner
|
| 3 |
|
| 4 |
+
Supports multiple AI providers:
|
| 5 |
+
- OpenAI (sk-...)
|
| 6 |
+
- Anthropic Claude (sk-ant-...)
|
| 7 |
+
- Vocareum (voc-...)
|
| 8 |
+
|
| 9 |
+
Author: AI Workflow Architect
|
| 10 |
+
License: MIT
|
| 11 |
"""
|
| 12 |
|
| 13 |
from openai import OpenAI
|
| 14 |
import numpy as np
|
| 15 |
from typing import Dict, Any, List, Optional, Callable
|
| 16 |
import logging
|
| 17 |
+
import os
|
| 18 |
|
| 19 |
# Configure logging
|
| 20 |
logging.basicConfig(level=logging.INFO)
|
| 21 |
logger = logging.getLogger(__name__)
|
| 22 |
|
| 23 |
+
# Try to import Anthropic (optional)
|
| 24 |
+
try:
|
| 25 |
+
import anthropic
|
| 26 |
|
| 27 |
+
ANTHROPIC_AVAILABLE = True
|
| 28 |
+
except ImportError:
|
| 29 |
+
ANTHROPIC_AVAILABLE = False
|
| 30 |
+
logger.info("Anthropic SDK not installed. Claude support disabled.")
|
| 31 |
+
|
| 32 |
+
|
| 33 |
+
class AIProvider:
|
| 34 |
"""
|
| 35 |
+
Unified AI provider interface supporting multiple backends.
|
|
|
|
|
|
|
|
|
|
| 36 |
"""
|
| 37 |
+
|
| 38 |
+
def __init__(self, api_key: str, base_url: str = None):
|
| 39 |
+
self.api_key = api_key
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 40 |
self.base_url = base_url
|
| 41 |
+
self.provider = self._detect_provider()
|
| 42 |
+
self.client = self._create_client()
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
|
| 44 |
+
def _detect_provider(self) -> str:
|
| 45 |
+
"""Auto-detect the AI provider based on API key format."""
|
| 46 |
+
if not self.api_key:
|
| 47 |
+
raise ValueError("API key is required")
|
| 48 |
+
|
| 49 |
+
if self.api_key.startswith("sk-ant-"):
|
| 50 |
+
return "anthropic"
|
| 51 |
+
elif self.api_key.startswith("voc-"):
|
| 52 |
+
return "vocareum"
|
| 53 |
+
elif self.api_key.startswith("sk-"):
|
| 54 |
+
return "openai"
|
| 55 |
+
else:
|
| 56 |
+
# Default to OpenAI for unknown formats
|
| 57 |
+
return "openai"
|
| 58 |
+
|
| 59 |
+
def _create_client(self):
|
| 60 |
+
"""Create the appropriate client based on provider."""
|
| 61 |
+
if self.provider == "anthropic":
|
| 62 |
+
if not ANTHROPIC_AVAILABLE:
|
| 63 |
+
raise ImportError("Anthropic SDK not installed. Run: pip install anthropic")
|
| 64 |
+
return anthropic.Anthropic(api_key=self.api_key)
|
| 65 |
+
|
| 66 |
+
elif self.provider == "vocareum":
|
| 67 |
+
return OpenAI(
|
| 68 |
+
api_key=self.api_key,
|
| 69 |
+
base_url="https://openai.vocareum.com/v1"
|
| 70 |
+
)
|
| 71 |
+
|
| 72 |
+
else: # openai
|
| 73 |
+
if self.base_url:
|
| 74 |
+
return OpenAI(api_key=self.api_key, base_url=self.base_url)
|
| 75 |
+
return OpenAI(api_key=self.api_key)
|
| 76 |
+
|
| 77 |
+
def chat_completion(
|
| 78 |
+
self,
|
| 79 |
+
messages: List[Dict[str, str]],
|
| 80 |
+
temperature: float = 0,
|
| 81 |
+
model: str = None
|
| 82 |
+
) -> str:
|
| 83 |
"""
|
| 84 |
+
Generate a chat completion using the detected provider.
|
| 85 |
+
|
| 86 |
Args:
|
| 87 |
+
messages: List of message dicts with 'role' and 'content'
|
| 88 |
+
temperature: Sampling temperature
|
| 89 |
+
model: Optional model override
|
| 90 |
+
|
| 91 |
Returns:
|
| 92 |
+
The assistant's response text
|
| 93 |
+
"""
|
| 94 |
+
if self.provider == "anthropic":
|
| 95 |
+
return self._anthropic_completion(messages, temperature, model)
|
| 96 |
+
else:
|
| 97 |
+
return self._openai_completion(messages, temperature, model)
|
| 98 |
+
|
| 99 |
+
def _openai_completion(
|
| 100 |
+
self,
|
| 101 |
+
messages: List[Dict[str, str]],
|
| 102 |
+
temperature: float,
|
| 103 |
+
model: str = None
|
| 104 |
+
) -> str:
|
| 105 |
+
"""OpenAI/Vocareum chat completion."""
|
| 106 |
+
model = model or "gpt-3.5-turbo"
|
| 107 |
+
|
| 108 |
+
response = self.client.chat.completions.create(
|
| 109 |
+
model=model,
|
| 110 |
+
messages=messages,
|
| 111 |
+
temperature=temperature
|
| 112 |
+
)
|
| 113 |
+
return response.choices[0].message.content
|
| 114 |
+
|
| 115 |
+
def _anthropic_completion(
|
| 116 |
+
self,
|
| 117 |
+
messages: List[Dict[str, str]],
|
| 118 |
+
temperature: float,
|
| 119 |
+
model: str = None
|
| 120 |
+
) -> str:
|
| 121 |
+
"""Anthropic Claude chat completion."""
|
| 122 |
+
model = model or "claude-3-haiku-20240307"
|
| 123 |
+
|
| 124 |
+
# Convert messages format for Anthropic
|
| 125 |
+
system_msg = ""
|
| 126 |
+
chat_messages = []
|
| 127 |
+
|
| 128 |
+
for msg in messages:
|
| 129 |
+
if msg["role"] == "system":
|
| 130 |
+
system_msg = msg["content"]
|
| 131 |
+
else:
|
| 132 |
+
chat_messages.append({
|
| 133 |
+
"role": msg["role"],
|
| 134 |
+
"content": msg["content"]
|
| 135 |
+
})
|
| 136 |
+
|
| 137 |
+
# Ensure messages alternate user/assistant
|
| 138 |
+
if chat_messages and chat_messages[0]["role"] != "user":
|
| 139 |
+
chat_messages.insert(0, {"role": "user", "content": "Hello"})
|
| 140 |
+
|
| 141 |
+
response = self.client.messages.create(
|
| 142 |
+
model=model,
|
| 143 |
+
max_tokens=4096,
|
| 144 |
+
system=system_msg if system_msg else "You are a helpful assistant.",
|
| 145 |
+
messages=chat_messages,
|
| 146 |
+
temperature=temperature
|
| 147 |
+
)
|
| 148 |
+
return response.content[0].text
|
| 149 |
+
|
| 150 |
+
def get_embedding(self, text: str) -> List[float]:
|
| 151 |
"""
|
| 152 |
+
Get text embedding. Only supported for OpenAI/Vocareum.
|
| 153 |
+
For Anthropic, falls back to a simple hash-based embedding.
|
| 154 |
+
"""
|
| 155 |
+
if self.provider == "anthropic":
|
| 156 |
+
# Anthropic doesn't have embeddings API
|
| 157 |
+
# Use a simple fallback for routing
|
| 158 |
+
logger.warning("Embeddings not available for Anthropic. Using fallback.")
|
| 159 |
+
return self._fallback_embedding(text)
|
| 160 |
+
|
| 161 |
+
response = self.client.embeddings.create(
|
| 162 |
+
model="text-embedding-3-large",
|
| 163 |
+
input=text,
|
| 164 |
+
encoding_format="float"
|
| 165 |
+
)
|
| 166 |
+
return response.data[0].embedding
|
| 167 |
+
|
| 168 |
+
def _fallback_embedding(self, text: str) -> List[float]:
|
| 169 |
+
"""Simple fallback embedding using character frequencies."""
|
| 170 |
+
# Create a basic 256-dim embedding based on character frequencies
|
| 171 |
+
embedding = [0.0] * 256
|
| 172 |
+
for char in text.lower():
|
| 173 |
+
idx = ord(char) % 256
|
| 174 |
+
embedding[idx] += 1
|
| 175 |
+
# Normalize
|
| 176 |
+
total = sum(embedding) or 1
|
| 177 |
+
return [x / total for x in embedding]
|
| 178 |
+
|
| 179 |
+
|
| 180 |
+
class DirectPromptAgent:
|
| 181 |
+
"""
|
| 182 |
+
A Direct Prompt Agent that relays user input directly to the LLM.
|
| 183 |
+
"""
|
| 184 |
+
|
| 185 |
+
def __init__(self, openai_api_key: str, base_url: str = None):
|
| 186 |
+
self.provider = AIProvider(openai_api_key, base_url)
|
| 187 |
+
|
| 188 |
+
def respond(self, prompt: str) -> str:
|
| 189 |
+
"""Generate a response by passing the user prompt directly to the LLM."""
|
| 190 |
try:
|
| 191 |
+
messages = [{"role": "user", "content": prompt}]
|
| 192 |
+
return self.provider.chat_completion(messages, temperature=0)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 193 |
except Exception as e:
|
| 194 |
logger.error(f"DirectPromptAgent error: {str(e)}")
|
| 195 |
raise
|
|
|
|
| 198 |
class AugmentedPromptAgent:
|
| 199 |
"""
|
| 200 |
An Augmented Prompt Agent that responds according to a predefined persona.
|
|
|
|
|
|
|
|
|
|
| 201 |
"""
|
| 202 |
+
|
| 203 |
def __init__(self, openai_api_key: str, persona: str, base_url: str = None):
|
| 204 |
+
self.provider = AIProvider(openai_api_key, base_url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 205 |
self.persona = persona
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 206 |
|
| 207 |
def respond(self, input_text: str) -> str:
|
| 208 |
+
"""Generate a response using the defined persona."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 209 |
try:
|
|
|
|
|
|
|
| 210 |
system_prompt = f"{self.persona} Forget all previous conversational context."
|
| 211 |
+
|
| 212 |
+
messages = [
|
| 213 |
+
{"role": "system", "content": system_prompt},
|
| 214 |
+
{"role": "user", "content": input_text}
|
| 215 |
+
]
|
| 216 |
+
return self.provider.chat_completion(messages, temperature=1.0)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 217 |
except Exception as e:
|
| 218 |
logger.error(f"AugmentedPromptAgent error: {str(e)}")
|
| 219 |
raise
|
|
|
|
| 221 |
|
| 222 |
class KnowledgeAugmentedPromptAgent:
|
| 223 |
"""
|
| 224 |
+
A Knowledge Augmented Prompt Agent that uses specific knowledge with a persona.
|
|
|
|
|
|
|
|
|
|
|
|
|
| 225 |
"""
|
| 226 |
+
|
| 227 |
def __init__(
|
| 228 |
+
self,
|
| 229 |
+
openai_api_key: str,
|
| 230 |
+
persona: str,
|
| 231 |
+
knowledge: str,
|
| 232 |
+
base_url: str = None
|
| 233 |
):
|
| 234 |
+
self.provider = AIProvider(openai_api_key, base_url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 235 |
self.persona = persona
|
| 236 |
self.knowledge = knowledge
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 237 |
|
| 238 |
def respond(self, input_text: str) -> str:
|
| 239 |
+
"""Generate a response using the persona and provided knowledge."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 240 |
try:
|
|
|
|
|
|
|
| 241 |
system_prompt = (
|
| 242 |
f"You are {self.persona} knowledge-based assistant. Forget all previous context. "
|
| 243 |
f"Use only the following knowledge to answer, do not use your own knowledge: {self.knowledge} "
|
| 244 |
f"Answer the prompt based on this knowledge, not your own."
|
| 245 |
)
|
| 246 |
+
|
| 247 |
+
messages = [
|
| 248 |
+
{"role": "system", "content": system_prompt},
|
| 249 |
+
{"role": "user", "content": input_text}
|
| 250 |
+
]
|
| 251 |
+
return self.provider.chat_completion(messages, temperature=0)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 252 |
except Exception as e:
|
| 253 |
logger.error(f"KnowledgeAugmentedPromptAgent error: {str(e)}")
|
| 254 |
raise
|
|
|
|
| 256 |
|
| 257 |
class EvaluationAgent:
|
| 258 |
"""
|
| 259 |
+
An Evaluation Agent that assesses and refines responses iteratively.
|
|
|
|
|
|
|
|
|
|
| 260 |
"""
|
| 261 |
+
|
| 262 |
def __init__(
|
| 263 |
+
self,
|
| 264 |
+
openai_api_key: str,
|
| 265 |
+
persona: str,
|
| 266 |
+
evaluation_criteria: str,
|
| 267 |
+
worker_agent: Any,
|
| 268 |
+
max_interactions: int = 10,
|
| 269 |
+
base_url: str = None
|
| 270 |
):
|
| 271 |
+
self.provider = AIProvider(openai_api_key, base_url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 272 |
self.persona = persona
|
| 273 |
self.evaluation_criteria = evaluation_criteria
|
| 274 |
self.worker_agent = worker_agent
|
| 275 |
self.max_interactions = max_interactions
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 276 |
|
| 277 |
def evaluate(self, prompt_to_evaluate: str) -> Dict[str, Any]:
|
| 278 |
+
"""Evaluate and potentially refine a response through iteration."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 279 |
try:
|
|
|
|
| 280 |
initial_prompt = prompt_to_evaluate
|
| 281 |
response_from_worker = ""
|
| 282 |
evaluation = ""
|
| 283 |
+
|
| 284 |
for i in range(self.max_interactions):
|
| 285 |
logger.info(f"Evaluation iteration {i + 1}/{self.max_interactions}")
|
| 286 |
+
|
| 287 |
# Step 1: Get response from worker agent
|
| 288 |
response_from_worker = self.worker_agent.respond(prompt_to_evaluate)
|
| 289 |
+
|
| 290 |
# Step 2: Evaluate the response
|
| 291 |
eval_prompt = (
|
| 292 |
f"Does the following answer: {response_from_worker}\n"
|
| 293 |
f"Meet this criteria: {self.evaluation_criteria}\n"
|
| 294 |
f"Respond Yes or No, and the reason why it does or doesn't meet the criteria."
|
| 295 |
)
|
| 296 |
+
|
| 297 |
+
messages = [
|
| 298 |
+
{"role": "system", "content": self.persona},
|
| 299 |
+
{"role": "user", "content": eval_prompt}
|
| 300 |
+
]
|
| 301 |
+
evaluation = self.provider.chat_completion(messages, temperature=0)
|
| 302 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 303 |
# Step 3: Check if evaluation passes
|
| 304 |
if evaluation.lower().startswith("yes"):
|
| 305 |
logger.info("Evaluation passed!")
|
| 306 |
break
|
| 307 |
+
|
| 308 |
# Step 4: Generate correction instructions
|
| 309 |
instruction_prompt = (
|
| 310 |
f"Provide instructions to fix an answer based on these reasons "
|
| 311 |
f"why it is incorrect: {evaluation}"
|
| 312 |
)
|
| 313 |
+
|
| 314 |
+
messages = [
|
| 315 |
+
{"role": "system",
|
| 316 |
+
"content": "You are a helpful assistant that provides clear correction instructions."},
|
| 317 |
+
{"role": "user", "content": instruction_prompt}
|
| 318 |
+
]
|
| 319 |
+
instructions = self.provider.chat_completion(messages, temperature=0)
|
| 320 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
| 321 |
# Step 5: Prepare refined prompt
|
| 322 |
prompt_to_evaluate = (
|
| 323 |
f"The original prompt was: {initial_prompt}\n"
|
|
|
|
| 325 |
f"It has been evaluated as incorrect.\n"
|
| 326 |
f"Make only these corrections, do not alter content validity: {instructions}"
|
| 327 |
)
|
| 328 |
+
|
| 329 |
return {
|
| 330 |
"final_response": response_from_worker,
|
| 331 |
"evaluation": evaluation,
|
| 332 |
"iterations": i + 1
|
| 333 |
}
|
|
|
|
| 334 |
except Exception as e:
|
| 335 |
logger.error(f"EvaluationAgent error: {str(e)}")
|
| 336 |
raise
|
|
|
|
| 338 |
|
| 339 |
class RoutingAgent:
|
| 340 |
"""
|
| 341 |
+
A Routing Agent that directs prompts to appropriate specialized agents.
|
|
|
|
|
|
|
|
|
|
| 342 |
"""
|
| 343 |
+
|
| 344 |
def __init__(
|
| 345 |
+
self,
|
| 346 |
+
openai_api_key: str,
|
| 347 |
+
agents: List[Dict[str, Any]],
|
| 348 |
+
base_url: str = None
|
| 349 |
):
|
| 350 |
+
self.provider = AIProvider(openai_api_key, base_url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 351 |
self.agents = agents
|
|
|
|
| 352 |
self._embedding_cache = {}
|
| 353 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 354 |
def get_embedding(self, text: str) -> List[float]:
|
| 355 |
+
"""Get embedding with caching."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 356 |
if text in self._embedding_cache:
|
| 357 |
return self._embedding_cache[text]
|
| 358 |
+
|
| 359 |
+
embedding = self.provider.get_embedding(text)
|
| 360 |
+
self._embedding_cache[text] = embedding
|
| 361 |
+
return embedding
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 362 |
|
| 363 |
def route(self, user_input: str) -> Any:
|
| 364 |
+
"""Route user prompts to the most appropriate agent."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 365 |
try:
|
| 366 |
input_emb = self.get_embedding(user_input)
|
| 367 |
best_agent = None
|
| 368 |
best_score = -1
|
| 369 |
+
|
| 370 |
for agent in self.agents:
|
| 371 |
agent_emb = self.get_embedding(agent["description"])
|
| 372 |
+
|
| 373 |
if agent_emb is None:
|
| 374 |
continue
|
| 375 |
+
|
| 376 |
# Calculate cosine similarity
|
| 377 |
similarity = np.dot(input_emb, agent_emb) / (
|
| 378 |
+
np.linalg.norm(input_emb) * np.linalg.norm(agent_emb)
|
| 379 |
)
|
| 380 |
+
|
| 381 |
logger.info(f"Agent '{agent['name']}' similarity: {similarity:.3f}")
|
| 382 |
+
|
| 383 |
if similarity > best_score:
|
| 384 |
best_score = similarity
|
| 385 |
best_agent = agent
|
| 386 |
+
|
| 387 |
if best_agent is None:
|
| 388 |
return "Sorry, no suitable agent could be selected."
|
| 389 |
+
|
| 390 |
logger.info(f"Selected agent: {best_agent['name']} (score={best_score:.3f})")
|
|
|
|
| 391 |
return best_agent["func"](user_input)
|
|
|
|
| 392 |
except Exception as e:
|
| 393 |
logger.error(f"RoutingAgent error: {str(e)}")
|
| 394 |
raise
|
|
|
|
| 396 |
|
| 397 |
class ActionPlanningAgent:
|
| 398 |
"""
|
| 399 |
+
An Action Planning Agent that extracts actionable steps from prompts.
|
|
|
|
|
|
|
|
|
|
| 400 |
"""
|
| 401 |
+
|
| 402 |
def __init__(
|
| 403 |
+
self,
|
| 404 |
+
openai_api_key: str,
|
| 405 |
+
knowledge: str,
|
| 406 |
+
base_url: str = None
|
| 407 |
):
|
| 408 |
+
self.provider = AIProvider(openai_api_key, base_url)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 409 |
self.knowledge = knowledge
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 410 |
|
| 411 |
def extract_steps_from_prompt(self, prompt: str) -> List[str]:
|
| 412 |
+
"""Extract actionable steps from a user prompt."""
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 413 |
try:
|
|
|
|
|
|
|
| 414 |
system_prompt = (
|
| 415 |
f"You are an action planning agent. Using your knowledge, you extract from the user prompt "
|
| 416 |
f"the steps requested to complete the action the user is asking for. You return the steps as a list. "
|
| 417 |
f"Only return the steps in your knowledge. Forget any previous context. "
|
| 418 |
f"This is your knowledge: {self.knowledge}"
|
| 419 |
)
|
| 420 |
+
|
| 421 |
+
messages = [
|
| 422 |
+
{"role": "system", "content": system_prompt},
|
| 423 |
+
{"role": "user", "content": prompt}
|
| 424 |
+
]
|
| 425 |
+
response_text = self.provider.chat_completion(messages, temperature=0)
|
| 426 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 427 |
# Clean and format the extracted steps
|
| 428 |
steps = response_text.split("\n")
|
| 429 |
cleaned_steps = [step.strip() for step in steps if step.strip()]
|
| 430 |
+
|
| 431 |
logger.info(f"Extracted {len(cleaned_steps)} action steps")
|
|
|
|
| 432 |
return cleaned_steps
|
|
|
|
| 433 |
except Exception as e:
|
| 434 |
logger.error(f"ActionPlanningAgent error: {str(e)}")
|
| 435 |
raise
|
requirements.txt
CHANGED
|
@@ -1,8 +1,5 @@
|
|
| 1 |
-
# AI Project Planner - Dependencies
|
| 2 |
-
# For Hugging Face Spaces deployment
|
| 3 |
-
|
| 4 |
-
# Core Framework
|
| 5 |
gradio==4.44.0
|
| 6 |
openai>=1.0.0
|
|
|
|
| 7 |
numpy>=1.24.0
|
| 8 |
python-dotenv>=1.0.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
gradio==4.44.0
|
| 2 |
openai>=1.0.0
|
| 3 |
+
anthropic>=0.18.0
|
| 4 |
numpy>=1.24.0
|
| 5 |
python-dotenv>=1.0.0
|