cofacts / rumors-api / 37339395935

84%

master: 84%

Build Type

push

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>

Coverage Stats

1031 of 1296 branches covered (79.55%)

Branch coverage included in aggregate %.

189 of 202 new or added lines in 9 files covered. (93.56%)

9 existing lines in 3 files now uncovered.

1919 of 2201 relevant lines covered (87.19%)

16.85 hits per line