rock
abacd8c09e
feat: Configurable embeddings models via EMBEDDINGS_MODEL env var
Allow customers to choose embedding model without schema changes.
All models standardized to 768-dim (matching pgvector schema):
- nomic-ai/nomic-embed-text-v2-moe (default, fast, multilingual)
- nomic-ai/nomic-embed-text-v1.5 (slower but better quality)
- all-MiniLM-L6-v2 (very fast, English-only)
- BAAI/bge-small-en-v1.5 (fast retrieval)
- BAAI/bge-base-en-v1.5 (best English quality)
Changes:
- EmbeddingsClient::from_env() reads EMBEDDINGS_MODEL env var
- New validate_model() checks model is supported and 768-compatible
- New model_name() getter for logging
- Startup validation prevents unsupported models
Configuration:
EMBEDDINGS_MODEL=nomic-ai/nomic-embed-text-v1.5
LLM_API_BASE=https://api.riotpiao.com
LLM_API_KEY=<optional>
Documentation:
- docs/EMBEDDINGS_MODELS.md (performance comparison, troubleshooting)
- Kubernetes example for switching models
- Migration guide for re-embedding existing chunks
- Custom model integration instructions
Performance impact:
- Default (v2-moe): ~200 texts/sec
- Fast (all-MiniLM): ~330 texts/sec
- Quality (bge-base): ~165 texts/sec
2026-08-28 13:16:52 -07:00
..
2026-08-23 09:42:09 -07:00
2026-08-28 13:16:52 -07:00
2026-08-28 12:35:50 -07:00
2026-08-28 12:56:16 -07:00
2026-08-28 13:16:52 -07:00
2026-08-28 12:41:30 -07:00