Unverified50% confidenceFactExact time
The retrieval side uses four-way recall: vector, keyword, entity, and graph channels, merged via reciprocal rank fusion, ultimately outputting a context block constrained by a token budget, and it reports which channels failed.
1
Sources
50%
Confidence
Long-term
Relevance
10/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedHybrid search runs dense vector search and classic keyword search (BM25) simultaneously, and typically uses Reciprocal Rank Fusion to merge the results, with the fusion formula summing 1 / (k + rank) over each document's rank in each list.72% similarVerifiedHybrid retrieval typically merges results from two retrieval pipelines using a weighted combination via the RRF (Reciprocal Rank Fusion) algorithm.71% similarUnverifiedThe debugging order is essentially layer-by-layer attribution, breaking an end-to-end failure into four independently verifiable stages: indexing, retrieval, ranking and generation.68% similarUnverifiedContext Mode使用Reciprocal Rank Fusion算法合并两种搜索策略的排序结果68% similarUnverifiedAgentic GraphRAG finds paragraphs through Neo4j's native full-text index and vector index, and uses reciprocal rank fusion (RRF) to fuse keyword rankings and semantic rankings.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1102756API
curl https://kongchang.com/api/v1/knowledge/claims/1102756MCP
get_claim(id=1102756)