Commit graph

2 commits

Author SHA1 Message Date
LLLin000
d24c78c5dc feat(#27 #28 #29 #30 #32): migrate write/read/status/build_state from ChromaDB to sqlite-vec
#27: write_encoded_payload and delete_paper_vectors use sqlite-vec
  - builder.py: writes to vec0 tables + companion meta tables
  - _chroma.py: delete_paper_vectors deletes from vec0 + meta by paper_id
  - Stores body_units_hash, object_units_hash, retrieval_policy_version in meta tables

#28: merge_retrieve and retrieve_chunks use vec0 k-NN search
  - search.py: vec0 k-NN queries with companion meta JOINs
  - Same dedup/per-paper-cap logic, same result shapes

#29: build_state migrated from JSON file to SQLite build_state table

#30: E2E embed+retrieve test with sqlite-vec + FixedProvider
  - 3 tests: body roundtrip, source correctness, per-paper cap

#32: E2E OCR pipeline test with fixture PDFs

Additional changes:
- schema.py: bump to v6, add hash/policy columns to vec companion meta tables
- embed.py: _assert_collections_healthy uses sqlite-vec; resume hash checks read from meta tables
- status.py: chunk counts from SQL COUNT on companion tables
- Removed unused get_collection/embed_paper imports from embed.py
- All tests updated: 76 pass (was 72, +4 new E2E tests, +4 for migration)
- FixedFixedProvider to generate 1536-dim vectors (matching vec0 schema)
- Fixed health check tests for sqlite-vec path
2026-07-09 17:52:45 +08:00
LLLin000
6ff0f6d38b PR9B: Embed Parallel Encode
- Four new dataclasses: EmbeddingPayload, EncodedPayload, PaperEmbeddingJob, PaperEncodedBundle
- prepare_legacy/body/object_payload: extract prepare phase from legacy embed functions
- encode_payload / encode_paper_job: worker-thread-safe encode functions
- write_encoded_payload: ChromaDB serial write
- prepare_payloads_for_entry: routing to correct prepare function
- Existing embed_body_units/embed_paper/embed_object_units refactored as wrappers
- Embed main loop: three-phase pipeline (PREPARE -> ENCODE -> WRITE) with ThreadPoolExecutor
- Bounded batch processing (BATCH_SIZE=8, MAX_WORKERS=4)
- Encode-success-gated delete: old vectors only removed after encode succeeds
- 23 regression tests for new functions
2026-07-06 22:41:25 +08:00