ruvnet / dspy.ts

What it does

• Vector store. store / storeText / search / searchText / update / delete / batchStore / getStats, with k / minScore / filter / includeVectors, a search cache, and stats. backendKind reports 'agentdb-rvf' or 'memory'; storage.backend ('auto'
• Filtered search. search(v, { filter: { kind: 'doc', score: { $gt: 0.5 } } }) (operators $eq $ne $lt $le $gt $ge $in $range) or an agentdb expression { op: 'eq', field: 'kind', value: 'doc' } with and / or / not. Only matching items are ret
• RaBitQ quantization. performance.quantization: 'rabitq' stores a 1-bit-per-dimension sign code (codes alone are ~32× smaller than float32; original vectors are retained); search becomes a Hamming coarse-filter → cosine re-rank of the top r
• Hierarchical tiers. store(v, m, { tier }) (working | short | long, default long), searchTiered({ tiers }), promote(id, tier), evictTier(tier, { maxAgeMs, max }), tierCounts().
• ReasoningBank + SAFLA. knowledge units learned from experiences, embedded via the AgentDB EmbeddingService; retrieveSemantic(queryText, …) does real vector search over stored units; SAFLA prunes/evolves the knowledge base.