Local RAG with Llama 3.1 for PDFs - Private Chat with Documents using LangChain and Streamlit
Offered By: Venelin Valkov via YouTube
Course Description
Overview
Discover how to build a local Retrieval-Augmented Generation (RAG) system for efficient document processing using Large Language Models (LLMs) in this comprehensive tutorial video. Learn to extract high-quality text from PDFs, split and format documents for optimal LLM performance, create vector stores with Qdrant, implement advanced retrieval techniques, and integrate local and remote LLMs. Follow along to develop a private chat application for your documents using LangChain and Streamlit, covering everything from project structure and UI design to document ingestion, retrieval methods, and deployment on Streamlit Cloud.
Syllabus
- What is RagBase?
- Text tutorial on MLExpert.io
- How RagBase works
- Project Structure
- UI with Streamlit
- Config
- File Upload
- Document Processing Ingestion
- Retrieval Reranker & LLMChainFilter
- QA Chain
- Chat Memory/History
- Create Models
- Start RagBase Locally
- Deploy to Streamlit Cloud
- Conclusion
Taught by
Venelin Valkov
Related Courses
Prompt Templates for GPT-3.5 and Other LLMs - LangChainJames Briggs via YouTube Getting Started with GPT-3 vs. Open Source LLMs - LangChain
James Briggs via YouTube Chatbot Memory for Chat-GPT, Davinci + Other LLMs - LangChain
James Briggs via YouTube Chat in LangChain
James Briggs via YouTube LangChain Data Loaders, Tokenizers, Chunking, and Datasets - Data Prep
James Briggs via YouTube