RAG Examples

This Python repository demonstrates a Retriever-Augmented Generation (RAG) pipeline for document-based question answering

qna-rag

A RAG pipeline that ingest the document from a provided URL and answer question related to document using FAISS as document vectorstore and llama3 70b as llm model.

You can refer to qna_rag to ingest the URL and interact with it.

rag-lc.mp4