copilot-swe-agent[bot]
d08040ac4a
- Run Black formatter and isort on all app/ files - Remove unused imports (F401) across multiple files - Add # noqa: F401 for intentional re-exports in celery_worker.py, tasks/__init__.py, utils.py, frontend.py, views/base.py - Fix f-strings without placeholders (F541) in azure.py, notification.py, check_credentials.py, upload_to_onedrive.py, settings.py - Fix bare except (E722) in upload_to_sftp.py - Fix block comment format (E265) in models.py - Move imports to top of file to fix E402 in celery_app.py, celery_worker.py - Fix line-too-long (E501) by wrapping strings in multiple files - Remove unused variable (F841) in upload_to_nextcloud.py Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
39 lines
1.3 KiB
Python
39 lines
1.3 KiB
Python
#!/usr/bin/env python3
|
|
|
|
import openai
|
|
|
|
# Import the shared Celery instance
|
|
from app.celery_app import celery
|
|
from app.config import settings
|
|
from app.tasks.retry_config import BaseTaskWithRetry
|
|
|
|
# Initialize OpenAI client dynamically
|
|
client = openai.OpenAI(api_key=settings.openai_api_key, base_url=settings.openai_base_url)
|
|
|
|
|
|
@celery.task(base=BaseTaskWithRetry)
|
|
def refine_text_with_gpt(filename: str, raw_text: str):
|
|
"""Uses OpenAI to clean and refine OCR text."""
|
|
response = client.chat.completions.create(
|
|
model=settings.openai_model,
|
|
messages=[
|
|
{
|
|
"role": "system",
|
|
"content": (
|
|
"Clean and format the following text. The idea is that the text you see comes from an OCR "
|
|
"system and your task is to eliminate OCR errors. Keep the original language when doing so."
|
|
),
|
|
},
|
|
{"role": "user", "content": raw_text},
|
|
],
|
|
)
|
|
|
|
cleaned_text = response.choices[0].message.content
|
|
|
|
# Trigger next task (import locally if needed to avoid circular imports)
|
|
from app.tasks.extract_metadata_with_gpt import extract_metadata_with_gpt
|
|
|
|
extract_metadata_with_gpt.delay(filename, cleaned_text)
|
|
|
|
return {"filename": filename, "cleaned_text": cleaned_text}
|