Hướng Dẫn Python RAG (với LLM cục bộ): AI cho các tệp PDF của bạn

Learn how to build a RAG (Retrieval Augmented Generation) app in Python that can let you query/chat with your PDFs using generative AI.

This project contains some more advanced topics, like how to run RAG apps locally (with Ollama), how to update a vector DB with new items, how to use RAG with PDFs (or any other files), and how to test the quality of AI generated responses.

👉 Links

🔗 GitHub: https://github.com/pixegami/rag-tutorial-v2

🔗 Basic RAG Tutorial: https://youtu.be/tcqEUSNCn8I

🔗 PyTest Video: https://youtu.be/YbpKMIUjvK8

👉 Resources

🔗 Document loaders: https://python.langchain.com/docs/modules/data_connection/document_loaders

🔗 PDF Loader: https://python.langchain.com/docs/modules/data_connection/document_loaders/pdf

🔗 Ollama: https://ollama.com

📚 Chapters

00:00 Introduction

01:06 RAG Recap

03:22 Loading PDF Data

05:08 Generate Embeddings

07:16 How To Store and Update Data

10:46 Updating Database

11:45 Running RAG Locally

15:12 Unit Testing AI Output

20:29 Wrapping Up