A RAG-based PDF QA system for local document understanding, combining FAISS vector retrieval with a LangChain pipeline over ChatGLM. Supports chunking, vector indexing, retrieval, and question-answering / summarization on your own PDFs — a practical companion to the retrieval research.
•
1 min read
ChatGLM + RAG PDF QA
Local document understanding · chunk → embed → retrieve → answer
- Python
- ChatGLM
- FAISS
- LangChain
- RAG