Unverified50% confidenceFactExact time
The project uses Neo4j to build a knowledge graph to improve RAG retrieval accuracy.
1
Sources
50%
Confidence
Long-term
Relevance
9/15/2026
First Seen
Sources
Related Entities
Related Claims
Unverified检索增强生成（RAG）技术让Agent每次推理前从向量库中检索最相关的历史信息片段注入上下文74% similarUnverifiedRAGFlow specializes in RAG (retrieval-augmented generation) scenarios, with targeted optimizations in document parsing quality and retrieval precision71% similarUnverifiedRetrieval-Augmented Generation (RAG) architecture decouples knowledge storage from language generation, evolving from simple vector similarity retrieval to hybrid retrieval combining BM25 and semantic vectors, iterative retrieval, and Graph RAG.71% similarUnverified工程界普遍采用RAG架构：将历史信息切分成语义块，通过嵌入模型转化为向量存入向量数据库（如Faiss、Pinecone、Weaviate），用户提问时计算余弦相似度检索最相关片段68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/923676API
curl https://kongchang.com/api/v1/knowledge/claims/923676MCP
get_claim(id=923676)