Chinese-LangChain

Why we included this project

Chinese-language knowledge work often means dealing with documents in many formats, from PDFs to Word files to slide decks. This project is a working example of how to build a local Q&A system on top of them: ChatGLM-6B handles generation, LangChain orchestrates retrieval, and FAISS stores the vectors. You upload files through a Gradio web UI, the content gets parsed and indexed, and then you ask questions in natural language while the system pulls the relevant passages before answering. It also includes prebuilt FAISS indexes for hundreds of thousands of Chinese Wikipedia articles, so you can test retrieval-augmented generation without building your own corpus. If you're trying to understand how a complete Chinese RAG pipeline.