Airmomo/graphrag-practice-chinese
GraphRAG的应用实例，项目特点在于提供了替换OpenAI模型的方法，并通过修改原有提示和切分文档的方法，提高了GraphRAG处理中文内容的能力。
Implements Microsoft's GraphRAG pipeline with optimizations for Chinese text processing: character-based chunking instead of token-based splitting to prevent corruption across chunk boundaries, Chinese-localized prompts, and integration with Zhipu AI's GLM models as a cost-effective alternative to OpenAI. Supports both local (entity-focused) and global (community-summary) graph-based retrieval modes for knowledge graphs extracted from documents.
185 stars. No commits in the last 6 months.
Stars
185
Forks
15
Language
Python
License
MIT
Category
Last pushed
Nov 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Airmomo/graphrag-practice-chinese"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
neo4j/neo4j-graphrag-python
Neo4j GraphRAG for Python
FalkorDB/GraphRAG-SDK
Build fast and accurate GenAI apps with GraphRAG SDK at scale.
microsoft/graphrag
A modular graph-based Retrieval-Augmented Generation (RAG) system
Hawksight-AI/semantica
Semantica 🧠 — A framework for building semantic layers, context graphs, and decision...
gusye1234/nano-graphrag
A simple, easy-to-hack GraphRAG implementation