shibing624/ChatPDF
RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。
Implements a lightweight GraphRAG system with hybrid retrieval combining BM25 keyword matching and sentence-embedding similarity, plus a reranker module to refine candidate chunks. Supports multiple local LLM APIs (Ollama, Deepseek, Qwen) with pluggable embedding models and optimized Chinese/bilingual text chunking. Built on Gradio for the web interface with async concurrent requests and context-window expansion for retrieved passages.
840 stars. No commits in the last 6 months.
Stars
840
Forks
144
Language
Python
License
Apache-2.0
Category
Last pushed
Apr 02, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/shibing624/ChatPDF"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
vndee/local-assistant-examples
Build your own ChatPDF and run it locally
datvodinh/rag-chatbot
Chat with multiple PDFs locally
couchbase-examples/rag-demo
A RAG demo using LangChain that allows you to chat with your uploaded PDF documents
ikantkode/pdfLLM
pdfLLM is a completely open source, proof of concept RAG app.
docqai/docq
Private ChatGPT/Perplexity. Securely unlocks knowledge from confidential business information.