Woody
|
181f4eca5b
|
feat: Phase 1.3 query pipeline with decomposition, relevance filter, and response
- Add QueryDecomposer: extracts keywords from question via LLM JSON response
- Add RelevanceFilter: batch scores chunks 0-10, filters by threshold
- Add POST /api/v1/query endpoint with full 3-step pipeline:
1. QueryDecomposer.decompose() → keywords
2. RAGService.retrieve() → chunks from ChromaDB
3. RelevanceFilter.filter() → score and filter chunks
4. RAGService.generate_response() → bullet-point answer
- Fix SourceMetadata.upload_date type from datetime to str for flexibility
- Test-first: 13 new tests pass (5 decomposer, 5 relevance filter, 3 query endpoint)
- All Phase 1 tests: 41 passed, 2 skipped
|
2026-04-22 17:19:21 +08:00 |
|
Woody
|
3712397d64
|
feat: Phase 1.1 project setup with config, database, and models
- Add requirements.txt with all dependencies
- Add .env.example with required environment variables
- Add Pydantic Settings (config.py) with .env loading
- Add ChromaDB persistent client (database.py)
- Add Pydantic schemas (ingest.py) for request/response
- Add FastAPI main.py with CORS middleware
- Add package __init__.py files
- Add tests: test_phase1_config.py, test_phase1_database.py
- All 5 tests pass
|
2026-04-22 16:13:52 +08:00 |