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: https://www.linkedin.com/in/venelin-valkov/
Follow me on X: https://twitter.com/venelin_valkov
Discord: https://discord.gg/UaNPxVD6tv
Subscribe: http://bit.ly/venelin-subscribe
GitHub repository: https://github.com/curiousily/AI-Bootcamp

👍 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:
https://www.youtube.com/channel/UCoW_WzQNJVAjxo4osNAxd_g/join

#deepseek #llm #rag #langchain #chatgpt #chatbot #python #streamlit #artificialintelligence

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