100% Local RAG with DeepSeek-R1, Ollama and LangChain - Build Document AI for Your Private Files скачать в хорошем качестве

100% Local RAG with DeepSeek-R1, Ollama and LangChain - Build Document AI for Your Private Files

Source code (GitHub repository) and complete AI Bootcamp are available for MLExpert Pro subscribers: https://www.mlexpert.io/ Build your own local document AI assistant that can analyze PDFs, documents, and more - completely free and private. Learn to build an advanced RAG system using LangChain that integrates chunking, contextual retrieval, semantic search, and local LLM (DeepSeek-R1) with Ollama. Ollama model(s): https://ollama.com/library/deepseek-r1 https://ollama.com/library/llama3.2 AI Bootcamp: https://www.mlexpert.io/ LinkedIn:   / venelin-valkov   Follow me on X:   / venelin_valkov   Discord:   / discord   Subscribe: http://bit.ly/venelin-subscribe GitHub repository: https://github.com/curiousily/AI-Boot... 👍 Don't Forget to Like, Comment, and Subscribe for More Tutorials! 00:00 - Demo 00:36 - Welcome 02:01 - Architecture of our RAG 04:50 - Live "AI Engineering" Boot Camp on MLExpert.io 05:45 - Project structure and config 07:30 - Uploading files 08:21 - File ingestion (retrieval) - chunking, contextual retrieval, embeddings, bm25, reranking 16:49 - Chatbot (Ollama, LangGraph workflow, streaming, sources, chat history) 23:56 - App UI with Streamlit 26:35 - Test our RAG (chat with blog post) 29:14 - Conclusion Join this channel to get access to the perks and support my work:    / @venelin_valkov   #deepseek #llm #rag #langchain #chatgpt #chatbot #python #streamlit #artificialintelligence