mirror of
https://github.com/open-jarvis/OpenJarvis.git
synced 2026-07-30 02:42:16 +00:00
krypticmouseandClaude Opus 4.6
ef859e6a17
Add disk-persistent storage for ColBERT token-level embeddings so the reranker can reuse pre-computed embeddings across queries instead of re-encoding every document on every search. - EmbeddingStore: individual .pt files per chunk with SQLite index for O(1) lookup, graceful degradation when torch is not installed - ColBERTReranker: checks EmbeddingStore for cached embeddings before falling back to docFromText(), stores newly computed embeddings - KnowledgeStore: ensures chunk_id is always present in retrieval metadata (both at store time and as a backfill in retrieve) - 18 tests covering round-trip persistence, deletion, torch-absent degradation, and reranker cache-hit/miss behavior Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>