cofacts / rumors-api / 30203190180

83%

master: 82%

Build Type

Pull #388

github

Committed by yutin1987

Commit Message

feat: hybrid BM25 + kNN vector search with Gemini embeddings

Add dense-vector (kNN) retrieval to ListArticles/ListReplies, opt-in via
the `embedding` similarity filter. kNN narrows the candidate set and the
existing BM25 / perceptual-hash scoring ranks the results.

- Embed articles and replies on create; backfill script for old docs.
- Audio/video embed as a single vector capped at 80s (no duration probe).
- Media queries reuse the doc-side embedding by content hash, else fetch
  bytes from the query URL and embed — search never persists to GCS, so
  no orphan files.
- All Gemini calls (embeddings + transcription) use the Developer API and
  feed media via the Files API; Vertex AI is removed.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Pull Request Pull Request #388: vector search

Coverage Stats

1011 of 1294 branches covered (78.13%)

Branch coverage included in aggregate %.

174 of 191 new or added lines in 10 files covered. (91.1%)

8 existing lines in 1 file now uncovered.

1899 of 2202 relevant lines covered (86.24%)

17.2 hits per line