Spaces:
Sleeping
Sleeping
segovia commited on
Commit ·
5234643
1
Parent(s): 028d116
some fixes
Browse files- app.py +6 -17
- document_orchester.py → document_orchestrator.py +36 -12
- document_processing.py +1 -0
- firebase_tenant_config.py +14 -0
- receipt_ai.py +253 -53
app.py
CHANGED
|
@@ -7,7 +7,7 @@ os.environ["GRADIO_SSR_MODE"] = "false"
|
|
| 7 |
|
| 8 |
import gradio as gr
|
| 9 |
|
| 10 |
-
from
|
| 11 |
from google_sheets_service import GoogleSheetsConfigError, append_row_to_google_sheet
|
| 12 |
|
| 13 |
try:
|
|
@@ -28,7 +28,7 @@ def gpu_decorator(fn):
|
|
| 28 |
return spaces.GPU(fn)
|
| 29 |
|
| 30 |
@gpu_decorator
|
| 31 |
-
def run_orchestrator_endpoint(model: str,
|
| 32 |
"""Multi-tenant orchestration endpoint - processes all active tenants and their rules."""
|
| 33 |
expected_api_key = str(os.getenv("ORCHESTRATOR_API_KEY") or "").strip()
|
| 34 |
provided_api_key = str(api_key or "").strip()
|
|
@@ -44,8 +44,8 @@ def run_orchestrator_endpoint(model: str, include_subfolders: bool, send_to_shee
|
|
| 44 |
# Load all active tenants from Firebase
|
| 45 |
return orchestrate_all_active_tenants(
|
| 46 |
model=model_name,
|
| 47 |
-
include_subfolders=
|
| 48 |
-
send_to_sheet=
|
| 49 |
)
|
| 50 |
except Exception as exc:
|
| 51 |
return {
|
|
@@ -60,18 +60,7 @@ def build_app() -> gr.Blocks:
|
|
| 60 |
|
| 61 |
with gr.Accordion("Orquestador API - Multi Tenant", open=False):
|
| 62 |
gr.Markdown("Endpoint publico para ejecutar escaneo + parseo + persistencia del orquestador en modo multi-tenant (carga todos los tenants activos de Firebase).")
|
| 63 |
-
|
| 64 |
-
label="Modelo OpenAI",
|
| 65 |
-
value=os.getenv("OPENAI_MODEL", "gpt-4o"),
|
| 66 |
-
)
|
| 67 |
-
mt_orchestrator_subfolders = gr.Checkbox(
|
| 68 |
-
label="Incluir subcarpetas",
|
| 69 |
-
value=True,
|
| 70 |
-
)
|
| 71 |
-
mt_orchestrator_send = gr.Checkbox(
|
| 72 |
-
label="Enviar a Google Sheets",
|
| 73 |
-
value=True,
|
| 74 |
-
)
|
| 75 |
mt_orchestrator_api_key = gr.Textbox(
|
| 76 |
label="API Key",
|
| 77 |
type="password",
|
|
@@ -82,7 +71,7 @@ def build_app() -> gr.Blocks:
|
|
| 82 |
|
| 83 |
mt_orchestrator_button.click(
|
| 84 |
run_orchestrator_endpoint,
|
| 85 |
-
inputs=[
|
| 86 |
outputs=[mt_orchestrator_output],
|
| 87 |
api_name="orchestrate_all_tenants",
|
| 88 |
)
|
|
|
|
| 7 |
|
| 8 |
import gradio as gr
|
| 9 |
|
| 10 |
+
from document_orchestrator import orchestrate_all_active_tenants
|
| 11 |
from google_sheets_service import GoogleSheetsConfigError, append_row_to_google_sheet
|
| 12 |
|
| 13 |
try:
|
|
|
|
| 28 |
return spaces.GPU(fn)
|
| 29 |
|
| 30 |
@gpu_decorator
|
| 31 |
+
def run_orchestrator_endpoint(model: str, api_key: str) -> dict:
|
| 32 |
"""Multi-tenant orchestration endpoint - processes all active tenants and their rules."""
|
| 33 |
expected_api_key = str(os.getenv("ORCHESTRATOR_API_KEY") or "").strip()
|
| 34 |
provided_api_key = str(api_key or "").strip()
|
|
|
|
| 44 |
# Load all active tenants from Firebase
|
| 45 |
return orchestrate_all_active_tenants(
|
| 46 |
model=model_name,
|
| 47 |
+
include_subfolders=True,
|
| 48 |
+
send_to_sheet=True,
|
| 49 |
)
|
| 50 |
except Exception as exc:
|
| 51 |
return {
|
|
|
|
| 60 |
|
| 61 |
with gr.Accordion("Orquestador API - Multi Tenant", open=False):
|
| 62 |
gr.Markdown("Endpoint publico para ejecutar escaneo + parseo + persistencia del orquestador en modo multi-tenant (carga todos los tenants activos de Firebase).")
|
| 63 |
+
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 64 |
mt_orchestrator_api_key = gr.Textbox(
|
| 65 |
label="API Key",
|
| 66 |
type="password",
|
|
|
|
| 71 |
|
| 72 |
mt_orchestrator_button.click(
|
| 73 |
run_orchestrator_endpoint,
|
| 74 |
+
inputs=[mt_orchestrator_api_key],
|
| 75 |
outputs=[mt_orchestrator_output],
|
| 76 |
api_name="orchestrate_all_tenants",
|
| 77 |
)
|
document_orchester.py → document_orchestrator.py
RENAMED
|
@@ -31,7 +31,7 @@ from google_drive_service import (
|
|
| 31 |
scan_drive_supported_documents,
|
| 32 |
)
|
| 33 |
from google_sheets_service import GoogleSheetsConfigError, append_row_to_google_sheet
|
| 34 |
-
from receipt_ai import extract_receipt_json, extract_receipt_json_from_image
|
| 35 |
from receipt_results import build_empty_result
|
| 36 |
|
| 37 |
|
|
@@ -43,7 +43,7 @@ if not logger.handlers:
|
|
| 43 |
handler = logging.StreamHandler()
|
| 44 |
handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(name)s: %(message)s"))
|
| 45 |
logger.addHandler(handler)
|
| 46 |
-
logger.setLevel(logging.
|
| 47 |
logger.propagate = False
|
| 48 |
|
| 49 |
|
|
@@ -132,17 +132,41 @@ def _build_hyperlink_formula(url: str, label: str) -> str:
|
|
| 132 |
|
| 133 |
def _parse_document(client: OpenAI, model: str, local_path: str, source_file: str) -> dict[str, Any]:
|
| 134 |
path = Path(local_path)
|
| 135 |
-
|
| 136 |
-
|
| 137 |
-
|
| 138 |
-
|
| 139 |
-
|
| 140 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 141 |
else:
|
| 142 |
-
|
| 143 |
-
|
| 144 |
-
|
| 145 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 146 |
|
| 147 |
|
| 148 |
def _create_default_tenant_from_env() -> tuple[TenantConfig, RuleObject] | None:
|
|
|
|
| 31 |
scan_drive_supported_documents,
|
| 32 |
)
|
| 33 |
from google_sheets_service import GoogleSheetsConfigError, append_row_to_google_sheet
|
| 34 |
+
from receipt_ai import extract_receipt_json, extract_receipt_json_from_image, extract_receipt_json_from_pdf, extract_receipt_json_from_document
|
| 35 |
from receipt_results import build_empty_result
|
| 36 |
|
| 37 |
|
|
|
|
| 43 |
handler = logging.StreamHandler()
|
| 44 |
handler.setFormatter(logging.Formatter("%(asctime)s %(levelname)s %(name)s: %(message)s"))
|
| 45 |
logger.addHandler(handler)
|
| 46 |
+
logger.setLevel(logging.DEBUG)
|
| 47 |
logger.propagate = False
|
| 48 |
|
| 49 |
|
|
|
|
| 132 |
|
| 133 |
def _parse_document(client: OpenAI, model: str, local_path: str, source_file: str) -> dict[str, Any]:
|
| 134 |
path = Path(local_path)
|
| 135 |
+
|
| 136 |
+
# Debug: Check if file exists
|
| 137 |
+
if not path.exists():
|
| 138 |
+
logger.error("Document file does not exist: %s", local_path)
|
| 139 |
+
return build_empty_result(source_file)
|
| 140 |
+
|
| 141 |
+
logger.debug("Parsing document: %s (size: %s bytes)", local_path, path.stat().st_size)
|
| 142 |
+
|
| 143 |
+
try:
|
| 144 |
+
# Send all documents in their original format to OpenAI
|
| 145 |
+
file_type = path.suffix.lower()
|
| 146 |
+
|
| 147 |
+
if file_type in {".jpg", ".jpeg", ".png"}:
|
| 148 |
+
# Send image in original format
|
| 149 |
+
logger.debug("Sending image in original format to OpenAI")
|
| 150 |
+
parsed = extract_receipt_json_from_image(client, model, path, to_data_uri(path))
|
| 151 |
+
|
| 152 |
+
elif file_type == ".pdf":
|
| 153 |
+
# Send PDF in original format
|
| 154 |
+
logger.debug("Sending PDF in original format to OpenAI")
|
| 155 |
+
parsed = extract_receipt_json_from_pdf(client, model, path)
|
| 156 |
+
|
| 157 |
else:
|
| 158 |
+
# Send other document types (TXT, DOCX, etc) in original format
|
| 159 |
+
logger.debug("Sending %s in original format to OpenAI", file_type)
|
| 160 |
+
parsed = extract_receipt_json_from_document(client, model, path)
|
| 161 |
+
|
| 162 |
+
parsed["source_file"] = source_file
|
| 163 |
+
return parsed
|
| 164 |
+
|
| 165 |
+
except Exception as exc:
|
| 166 |
+
logger.exception("Error parsing document %s: %s", local_path, exc)
|
| 167 |
+
parsed = build_empty_result(source_file)
|
| 168 |
+
parsed["source_file"] = source_file
|
| 169 |
+
return parsed
|
| 170 |
|
| 171 |
|
| 172 |
def _create_default_tenant_from_env() -> tuple[TenantConfig, RuleObject] | None:
|
document_processing.py
CHANGED
|
@@ -1,6 +1,7 @@
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
import base64
|
|
|
|
| 4 |
from pathlib import Path
|
| 5 |
|
| 6 |
|
|
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
import base64
|
| 4 |
+
import io
|
| 5 |
from pathlib import Path
|
| 6 |
|
| 7 |
|
firebase_tenant_config.py
CHANGED
|
@@ -207,3 +207,17 @@ class FirebaseTenantConfigManager:
|
|
| 207 |
tenant_doc = self._get_db().collection(self.collection_name).document(tenant_id)
|
| 208 |
rules_subcoll = tenant_doc.collection("rules")
|
| 209 |
rules_subcoll.document(rule_id).delete()
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
tenant_doc = self._get_db().collection(self.collection_name).document(tenant_id)
|
| 208 |
rules_subcoll = tenant_doc.collection("rules")
|
| 209 |
rules_subcoll.document(rule_id).delete()
|
| 210 |
+
|
| 211 |
+
|
| 212 |
+
# Module-level convenience functions for backward compatibility
|
| 213 |
+
_manager = FirebaseTenantConfigManager()
|
| 214 |
+
|
| 215 |
+
|
| 216 |
+
def load_all_tenants() -> list[TenantConfig]:
|
| 217 |
+
"""Load all active tenants from Firebase."""
|
| 218 |
+
return _manager.list_active_tenants()
|
| 219 |
+
|
| 220 |
+
|
| 221 |
+
def load_tenant_rules(tenant_id: str) -> list[RuleObject]:
|
| 222 |
+
"""Load all rules for a specific tenant."""
|
| 223 |
+
return _manager.get_all_rules(tenant_id)
|
receipt_ai.py
CHANGED
|
@@ -1,10 +1,15 @@
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
|
|
|
| 3 |
import json
|
|
|
|
| 4 |
from pathlib import Path
|
| 5 |
from typing import Any
|
| 6 |
|
| 7 |
|
|
|
|
|
|
|
|
|
|
| 8 |
EXTRACTION_INSTRUCTIONS = (
|
| 9 |
"You extract purchase receipt information from a single document. "
|
| 10 |
"Return one JSON object that matches the schema exactly. "
|
|
@@ -68,65 +73,260 @@ def build_schema() -> dict[str, Any]:
|
|
| 68 |
|
| 69 |
|
| 70 |
def extract_receipt_json(client: Any, model: str, file_path: Path, text: str) -> dict[str, Any]:
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
| 75 |
-
|
| 76 |
-
|
| 77 |
-
|
| 78 |
-
|
| 79 |
-
|
| 80 |
-
"
|
| 81 |
-
|
| 82 |
-
|
| 83 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 84 |
|
| 85 |
-
|
| 86 |
-
|
| 87 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 88 |
|
| 89 |
-
|
| 90 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 91 |
|
| 92 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 93 |
|
| 94 |
|
| 95 |
def extract_receipt_json_from_image(client: Any, model: str, file_path: Path, image_data_uri: str) -> dict[str, Any]:
|
| 96 |
-
|
| 97 |
-
|
| 98 |
-
|
| 99 |
-
|
| 100 |
-
|
| 101 |
-
|
| 102 |
-
|
| 103 |
-
|
| 104 |
-
|
| 105 |
-
|
| 106 |
-
|
| 107 |
-
|
| 108 |
-
|
| 109 |
-
|
| 110 |
-
|
| 111 |
-
|
| 112 |
-
|
| 113 |
-
|
| 114 |
-
|
| 115 |
-
|
| 116 |
-
|
| 117 |
-
|
| 118 |
-
|
| 119 |
-
|
| 120 |
-
|
| 121 |
-
|
| 122 |
-
|
| 123 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 124 |
|
| 125 |
-
|
| 126 |
-
|
| 127 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 128 |
|
| 129 |
-
|
| 130 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 131 |
|
| 132 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
from __future__ import annotations
|
| 2 |
|
| 3 |
+
import base64
|
| 4 |
import json
|
| 5 |
+
import logging
|
| 6 |
from pathlib import Path
|
| 7 |
from typing import Any
|
| 8 |
|
| 9 |
|
| 10 |
+
logger = logging.getLogger(__name__)
|
| 11 |
+
|
| 12 |
+
|
| 13 |
EXTRACTION_INSTRUCTIONS = (
|
| 14 |
"You extract purchase receipt information from a single document. "
|
| 15 |
"Return one JSON object that matches the schema exactly. "
|
|
|
|
| 73 |
|
| 74 |
|
| 75 |
def extract_receipt_json(client: Any, model: str, file_path: Path, text: str) -> dict[str, Any]:
|
| 76 |
+
logger.debug("extract_receipt_json called: file=%s, model=%s, text_length=%s", file_path.name, model, len(text))
|
| 77 |
+
|
| 78 |
+
try:
|
| 79 |
+
logger.debug("Sending text extraction request to OpenAI for %s", file_path.name)
|
| 80 |
+
response = client.responses.create(
|
| 81 |
+
model=model,
|
| 82 |
+
instructions=EXTRACTION_INSTRUCTIONS,
|
| 83 |
+
input=f"{build_user_prompt(file_path.name, 'text')}\n\nDocument text:\n{text[:20000]}",
|
| 84 |
+
text={
|
| 85 |
+
"format": {
|
| 86 |
+
"type": "json_schema",
|
| 87 |
+
"name": "purchase_receipt_extraction",
|
| 88 |
+
"schema": build_schema()["schema"],
|
| 89 |
+
"strict": True,
|
| 90 |
+
}
|
| 91 |
+
},
|
| 92 |
+
)
|
| 93 |
+
|
| 94 |
+
logger.debug("Received response from OpenAI for %s", file_path.name)
|
| 95 |
|
| 96 |
+
output_text = getattr(response, "output_text", None)
|
| 97 |
+
if output_text:
|
| 98 |
+
logger.debug("Parsing output_text from response")
|
| 99 |
+
result = json.loads(output_text)
|
| 100 |
+
logger.debug("Successfully parsed JSON: document_type=%s, total=%s, confidence=%s",
|
| 101 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 102 |
+
return result
|
| 103 |
|
| 104 |
+
if response.output and response.output[0].content:
|
| 105 |
+
logger.debug("Parsing response.output content")
|
| 106 |
+
result = json.loads(response.output[0].content[0].text)
|
| 107 |
+
logger.debug("Successfully parsed JSON: document_type=%s, total=%s, confidence=%s",
|
| 108 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 109 |
+
return result
|
| 110 |
|
| 111 |
+
logger.error("No JSON returned for %s - no output_text and no response.output", file_path.name)
|
| 112 |
+
raise RuntimeError(f"No JSON returned for {file_path.name}")
|
| 113 |
+
|
| 114 |
+
except json.JSONDecodeError as e:
|
| 115 |
+
logger.error("JSON decode error for %s: %s", file_path.name, e)
|
| 116 |
+
raise
|
| 117 |
+
except Exception as e:
|
| 118 |
+
logger.error("Error in extract_receipt_json for %s: %s", file_path.name, e)
|
| 119 |
+
raise
|
| 120 |
|
| 121 |
|
| 122 |
def extract_receipt_json_from_image(client: Any, model: str, file_path: Path, image_data_uri: str) -> dict[str, Any]:
|
| 123 |
+
logger.debug("extract_receipt_json_from_image called: file=%s, model=%s, image_size=%s bytes",
|
| 124 |
+
file_path.name, model, len(image_data_uri))
|
| 125 |
+
|
| 126 |
+
try:
|
| 127 |
+
logger.debug("Sending image extraction request to OpenAI for %s", file_path.name)
|
| 128 |
+
response = client.responses.create(
|
| 129 |
+
model=model,
|
| 130 |
+
instructions=EXTRACTION_INSTRUCTIONS,
|
| 131 |
+
input=[
|
| 132 |
+
{
|
| 133 |
+
"role": "user",
|
| 134 |
+
"content": [
|
| 135 |
+
{
|
| 136 |
+
"type": "input_text",
|
| 137 |
+
"text": build_user_prompt(file_path.name, "image"),
|
| 138 |
+
},
|
| 139 |
+
{
|
| 140 |
+
"type": "input_image",
|
| 141 |
+
"image_url": image_data_uri,
|
| 142 |
+
"detail": "high",
|
| 143 |
+
},
|
| 144 |
+
],
|
| 145 |
+
}
|
| 146 |
+
],
|
| 147 |
+
text={
|
| 148 |
+
"format": {
|
| 149 |
+
"type": "json_schema",
|
| 150 |
+
"name": "purchase_receipt_extraction",
|
| 151 |
+
"schema": build_schema()["schema"],
|
| 152 |
+
"strict": True,
|
| 153 |
+
}
|
| 154 |
+
},
|
| 155 |
+
)
|
| 156 |
+
|
| 157 |
+
logger.debug("Received response from OpenAI for image %s", file_path.name)
|
| 158 |
+
|
| 159 |
+
output_text = getattr(response, "output_text", None)
|
| 160 |
+
if output_text:
|
| 161 |
+
logger.debug("Parsing output_text from image response")
|
| 162 |
+
result = json.loads(output_text)
|
| 163 |
+
logger.debug("Successfully parsed image JSON: document_type=%s, total=%s, confidence=%s",
|
| 164 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 165 |
+
return result
|
| 166 |
+
|
| 167 |
+
if response.output and response.output[0].content:
|
| 168 |
+
logger.debug("Parsing response.output content from image")
|
| 169 |
+
result = json.loads(response.output[0].content[0].text)
|
| 170 |
+
logger.debug("Successfully parsed image JSON: document_type=%s, total=%s, confidence=%s",
|
| 171 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 172 |
+
return result
|
| 173 |
+
|
| 174 |
+
logger.error("No JSON returned for image %s - no output_text and no response.output", file_path.name)
|
| 175 |
+
raise RuntimeError(f"No JSON returned for {file_path.name}")
|
| 176 |
+
|
| 177 |
+
except json.JSONDecodeError as e:
|
| 178 |
+
logger.error("JSON decode error for image %s: %s", file_path.name, e)
|
| 179 |
+
raise
|
| 180 |
+
except Exception as e:
|
| 181 |
+
logger.error("Error in extract_receipt_json_from_image for %s: %s", file_path.name, e)
|
| 182 |
+
raise
|
| 183 |
+
|
| 184 |
+
|
| 185 |
+
def extract_receipt_json_from_pdf(client: Any, model: str, file_path: Path) -> dict[str, Any]:
|
| 186 |
+
"""Upload PDF to OpenAI Files API and extract structured data."""
|
| 187 |
+
logger.debug("extract_receipt_json_from_pdf called: file=%s, model=%s", file_path.name, model)
|
| 188 |
+
|
| 189 |
+
file_id = None
|
| 190 |
+
try:
|
| 191 |
+
# 1. Upload PDF to Files API
|
| 192 |
+
logger.debug("Uploading PDF to OpenAI Files API: %s", file_path.name)
|
| 193 |
+
with open(file_path, "rb") as pdf_file:
|
| 194 |
+
uploaded_file = client.files.create(
|
| 195 |
+
file=pdf_file,
|
| 196 |
+
purpose="user_data"
|
| 197 |
+
)
|
| 198 |
+
file_id = uploaded_file.id
|
| 199 |
+
logger.debug("PDF uploaded successfully, file_id: %s", file_id)
|
| 200 |
+
|
| 201 |
+
# 2. Send file_id to model for processing
|
| 202 |
+
logger.debug("Sending PDF to OpenAI via Files API for %s", file_path.name)
|
| 203 |
+
response = client.responses.create(
|
| 204 |
+
model=model,
|
| 205 |
+
instructions=EXTRACTION_INSTRUCTIONS,
|
| 206 |
+
input=[
|
| 207 |
+
{
|
| 208 |
+
"role": "user",
|
| 209 |
+
"content": [
|
| 210 |
+
{
|
| 211 |
+
"type": "input_file",
|
| 212 |
+
"file_id": file_id
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"type": "input_text",
|
| 216 |
+
"text": build_user_prompt(file_path.name, "pdf")
|
| 217 |
+
}
|
| 218 |
+
]
|
| 219 |
+
}
|
| 220 |
+
],
|
| 221 |
+
text={
|
| 222 |
+
"format": {
|
| 223 |
+
"type": "json_schema",
|
| 224 |
+
"name": "purchase_receipt_extraction",
|
| 225 |
+
"schema": build_schema()["schema"],
|
| 226 |
+
"strict": True,
|
| 227 |
+
}
|
| 228 |
+
},
|
| 229 |
+
)
|
| 230 |
+
|
| 231 |
+
logger.debug("Received response from OpenAI for PDF %s", file_path.name)
|
| 232 |
+
|
| 233 |
+
output_text = getattr(response, "output_text", None)
|
| 234 |
+
if output_text:
|
| 235 |
+
logger.debug("Parsing output_text from PDF response")
|
| 236 |
+
result = json.loads(output_text)
|
| 237 |
+
logger.debug("Successfully parsed PDF JSON: document_type=%s, total=%s, confidence=%s",
|
| 238 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 239 |
+
return result
|
| 240 |
+
|
| 241 |
+
if response.output and response.output[0].content:
|
| 242 |
+
logger.debug("Parsing response.output content from PDF")
|
| 243 |
+
result = json.loads(response.output[0].content[0].text)
|
| 244 |
+
logger.debug("Successfully parsed PDF JSON: document_type=%s, total=%s, confidence=%s",
|
| 245 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 246 |
+
return result
|
| 247 |
+
|
| 248 |
+
logger.error("No JSON returned for PDF %s - no output_text and no response.output", file_path.name)
|
| 249 |
+
raise RuntimeError(f"No JSON returned for {file_path.name}")
|
| 250 |
+
|
| 251 |
+
except json.JSONDecodeError as e:
|
| 252 |
+
logger.error("JSON decode error for PDF %s: %s", file_path.name, e)
|
| 253 |
+
raise
|
| 254 |
+
except Exception as e:
|
| 255 |
+
logger.error("Error in extract_receipt_json_from_pdf for %s: %s", file_path.name, e)
|
| 256 |
+
raise
|
| 257 |
+
finally:
|
| 258 |
+
# Clean up uploaded file
|
| 259 |
+
if file_id:
|
| 260 |
+
try:
|
| 261 |
+
logger.debug("Deleting uploaded file: %s", file_id)
|
| 262 |
+
client.files.delete(file_id)
|
| 263 |
+
except Exception as e:
|
| 264 |
+
logger.warning("Failed to delete file %s: %s", file_id, e)
|
| 265 |
+
|
| 266 |
+
|
| 267 |
+
def extract_receipt_json_from_document(client: Any, model: str, file_path: Path) -> dict[str, Any]:
|
| 268 |
+
"""Send document type to OpenAI by extracting text (DOCX, TXT, etc)."""
|
| 269 |
+
logger.debug("extract_receipt_json_from_document called: file=%s, model=%s", file_path.name, model)
|
| 270 |
+
|
| 271 |
+
try:
|
| 272 |
+
logger.debug("Extracting text from document: %s", file_path.name)
|
| 273 |
+
|
| 274 |
+
# Extract text based on file type
|
| 275 |
+
if file_path.suffix.lower() == ".txt":
|
| 276 |
+
text = file_path.read_text(encoding="utf-8", errors="ignore")
|
| 277 |
+
logger.debug("Read TXT file: %s characters", len(text))
|
| 278 |
+
|
| 279 |
+
elif file_path.suffix.lower() == ".docx":
|
| 280 |
+
from docx import Document
|
| 281 |
+
document = Document(str(file_path))
|
| 282 |
+
paragraphs = [paragraph.text for paragraph in document.paragraphs]
|
| 283 |
+
text = "\n".join(paragraphs)
|
| 284 |
+
logger.debug("Extracted DOCX file: %s characters", len(text))
|
| 285 |
+
|
| 286 |
+
else:
|
| 287 |
+
logger.warning("Unsupported document format: %s, attempting generic text read", file_path.suffix)
|
| 288 |
+
text = file_path.read_text(encoding="utf-8", errors="ignore")
|
| 289 |
+
logger.debug("Read document file: %s characters", len(text))
|
| 290 |
+
|
| 291 |
+
# Send extracted text to OpenAI
|
| 292 |
+
logger.debug("Sending extracted document text to OpenAI for %s", file_path.name)
|
| 293 |
+
response = client.responses.create(
|
| 294 |
+
model=model,
|
| 295 |
+
instructions=EXTRACTION_INSTRUCTIONS,
|
| 296 |
+
input=f"{build_user_prompt(file_path.name, 'document')}\n\nDocument text:\n{text[:20000]}",
|
| 297 |
+
text={
|
| 298 |
+
"format": {
|
| 299 |
+
"type": "json_schema",
|
| 300 |
+
"name": "purchase_receipt_extraction",
|
| 301 |
+
"schema": build_schema()["schema"],
|
| 302 |
+
"strict": True,
|
| 303 |
+
}
|
| 304 |
+
},
|
| 305 |
+
)
|
| 306 |
+
|
| 307 |
+
logger.debug("Received response from OpenAI for document %s", file_path.name)
|
| 308 |
|
| 309 |
+
output_text = getattr(response, "output_text", None)
|
| 310 |
+
if output_text:
|
| 311 |
+
logger.debug("Parsing output_text from document response")
|
| 312 |
+
result = json.loads(output_text)
|
| 313 |
+
logger.debug("Successfully parsed document JSON: document_type=%s, total=%s, confidence=%s",
|
| 314 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 315 |
+
return result
|
| 316 |
|
| 317 |
+
if response.output and response.output[0].content:
|
| 318 |
+
logger.debug("Parsing response.output content from document")
|
| 319 |
+
result = json.loads(response.output[0].content[0].text)
|
| 320 |
+
logger.debug("Successfully parsed document JSON: document_type=%s, total=%s, confidence=%s",
|
| 321 |
+
result.get("document_type"), result.get("total"), result.get("confidence"))
|
| 322 |
+
return result
|
| 323 |
|
| 324 |
+
logger.error("No JSON returned for document %s - no output_text and no response.output", file_path.name)
|
| 325 |
+
raise RuntimeError(f"No JSON returned for {file_path.name}")
|
| 326 |
+
|
| 327 |
+
except json.JSONDecodeError as e:
|
| 328 |
+
logger.error("JSON decode error for document %s: %s", file_path.name, e)
|
| 329 |
+
raise
|
| 330 |
+
except Exception as e:
|
| 331 |
+
logger.error("Error in extract_receipt_json_from_document for %s: %s", file_path.name, e)
|
| 332 |
+
raise
|