Add PostgreSQL full-text search alongside pgvector for exact matches
on Jira keys, error messages, file paths. Merge results with
Reciprocal Rank Fusion. Default mode: hybrid, with graceful
degradation to keyword-only when embeddings unavailable.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
SHA-256 hash check before embedding API call eliminates ~60-80% of
redundant embedding requests. Consolidates dual INSERT paths to single
INSERT with nullable embedding column.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
When LiteLLM embedding service is unavailable, archive_search now gracefully falls back to PostgreSQL text search (ILIKE) instead of returning an error. Also adds dotenv support for proper credential loading.
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Switch from external Gemini API (3072 dims, $0.15/1M tokens) to local
Ollama mxbai-embed-large (1024 dims, free) for cost savings and HNSW
index support.
Changes:
- Updated embeddings.ts: model 'mxbai-embed-large', API URL fixed
- Updated migration 015: vector(1024) with HNSW index
- Regenerated 268 tool_docs embeddings with new model
Benefits:
- Free embeddings (no API costs)
- HNSW index enabled (1024 < 2000 dim limit)
- Fast similarity search (O(log n) vs O(n))
- No external API dependency
Trade-offs:
- 5% quality loss (MTEB 64.68 vs ~70 Gemini)
- Uses local compute (1.2GB RAM, <1s per embedding)
Task: CF-251
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
