Unverified50% confidenceFactExact time
微软 GraphRAG 引入两阶段检索机制：Local Search 通过图遍历定位实体邻域，Global Search 基于社区摘要进行层次化推理
1
Sources
50%
Confidence
Long-term
Relevance
7/24/2026
First Seen
Sources
6个开源工具系统补齐Claude Code五大短板
bilibiliNixAI7/8/2026
Related Claims
Unverified微软研究院于 2024 年提出 GraphRAG 框架，引入 Local Search 和 Global Search 两阶段检索机制82% similarVerifiedThe GraphRAG paper published by Microsoft Research in 2024 proposed a community-detection-based approach: using an LLM to extract entities and relationships to build a knowledge graph, then applying the Leiden algorithm for community partitioning, and finally generating a summary for each community.77% similarUnverifiedGraph RAG是微软研究院于2024年提出并开源的检索增强范式，先用LLM抽取实体与关系构建知识图谱，检索时沿图结构进行社区摘要71% similarVerifiedGraphRAG was proposed by Microsoft Research in 2024, combining knowledge graphs with vector retrieval to achieve deep cross-document reasoning through entity relationship networks.69% similarUnverifiedGoogle AI Overviews uses Retrieval-Augmented Generation (RAG) technology, first retrieving multiple authoritative web pages before having a large model synthesize a structured answer while retaining source citations.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/609092API
curl https://kongchang.com/api/v1/knowledge/claims/609092MCP
get_claim(id=609092)