Parse documents concurrently (up to 10 at a time via semaphore) instead of serially. Each coroutine uses its own DB session for per-document status updates, while a shared lock serializes job progress increments on the main session to avoid session-sharing issues. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| analysis_service.py | ||
| auth_service.py | ||
| email_service.py | ||
| gemini_service.py | ||
| knowledge_base_service.py | ||
| llamaparse_service.py | ||
| pdf_service.py | ||
| reference_docs.py | ||
| storage_service.py | ||