Unverified50% confidenceFactExact time
raggy adopts a hybrid database design, using both vector retrieval and BM25 keyword retrieval mechanisms simultaneously.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/11/2026
First Seen
Valid until: 12/10/2026
Sources
Related Entities
Related Claims
Unverified传统RAG依赖基于BM25算法的关键词稀疏检索和基于FAISS、Chroma等向量数据库的稠密向量检索73% 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% similarVerifiedBM25 is a classic keyword retrieval algorithm based on term frequency statistics, which is complementary to vector retrieval.68% similarUnverifiedVector databases such as Pinecone, Weaviate, and Chroma can complete semantic similarity code retrieval at the millisecond level via approximate nearest neighbor (ANN) algorithms.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/906740API
curl https://kongchang.com/api/v1/knowledge/claims/906740MCP
get_claim(id=906740)