Unverified50% confidenceFactExact time
ChromaDB's semantic search uses nearest-neighbor retrieval, by default using cosine similarity, supports specifying top-k with n_results, and supports where metadata filtering.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTop-K检索是从向量数据库中取相似度最高的前K个片段作为候选内容72% similarUnverifiedChromaDB检索时采用近似最近邻（ANN）算法，常见实现包括HNSW算法70% similarUnverified向量数据库Qdrant用Rust编写、高性能，Chroma为Python原生适合原型开发，Weaviate支持混合搜索，均通过HNSW等近似最近邻算法实现毫秒级检索69% similarVerified混合检索（Hybrid Search）将向量检索与BM25关键词检索的结果通过RRF（倒数排名融合）等算法合并，兼顾语义理解与精确匹配69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1043745API
curl https://kongchang.com/api/v1/knowledge/claims/1043745MCP
get_claim(id=1043745)