copilot-swe-agent[bot] 8d7c8e7c4e feat(similarity): add embedding pipeline, debug endpoints, backfill task, and scalable similarity search ...

- Add embedding_model config setting (replaces hardcoded text-embedding-3-small)
- Add compute_document_embedding Celery task for ingestion-time embedding
- Chain embedding task into finalize_document_storage pipeline
- Add backfill_missing_embeddings periodic task (every 5 min) for legacy files
- Add debug API endpoints: embedding-status, compute-embedding, diagnostic/embeddings, diagnostic/compute-all-embeddings
- Refactor find_similar_documents to only use pre-computed embeddings (no lazy API calls)
- Use yield_per(500) and column-only queries for 100K+ scale
- Add embedding status indicator and recompute button in file detail UI

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>

2026-03-02 13:01:57 +00:00

..

api

feat(similarity): add embedding pipeline, debug endpoints, backfill task, and scalable similarity search

2026-03-02 13:01:57 +00:00

middleware

style: apply ruff auto-fix

2026-02-22 16:32:30 +00:00

tasks

feat(similarity): add embedding pipeline, debug endpoints, backfill task, and scalable similarity search

2026-03-02 13:01:57 +00:00

utils

feat(similarity): add embedding pipeline, debug endpoints, backfill task, and scalable similarity search

2026-03-02 13:01:57 +00:00

views

feat(duplicates): add duplicate document detection and management

2026-03-02 10:21:57 +00:00

__init__.py

feat: add frontend views and file management functionality, enhance user response structure, and update configuration guide

2025-04-03 21:49:15 +02:00

auth.py

feat(auth): implement CSRF token protection for state-changing operations

2026-02-22 16:27:37 +00:00

celery_app.py

style: fix all flake8 linter errors across app/ directory

2026-02-08 17:42:33 +00:00

celery_worker.py

feat(similarity): add embedding pipeline, debug endpoints, backfill task, and scalable similarity search

2026-03-02 13:01:57 +00:00

config.py

feat(similarity): add embedding pipeline, debug endpoints, backfill task, and scalable similarity search

2026-03-02 13:01:57 +00:00

database.py

fix(database): skip create_all for Alembic-tracked databases to prevent OperationalError on webhook_configs

2026-03-02 10:25:34 +00:00

frontend.py

style: fix all flake8 linter errors across app/ directory

2026-02-08 17:42:33 +00:00

main.py

feat(ocr): auto-install Tesseract/EasyOCR languages from settings

2026-02-24 16:28:14 +00:00

models.py

Merge branch 'main' into copilot/add-document-similarity-detection

2026-03-01 22:06:55 +01:00