In this video, you will learn how to build a RAG (Retrieval-Augmented Generation) system that answers questions from your own documents, using only free tools. No API key is needed, and everything runs on your own computer.

📌 What you will learn:
What a vector database is and how to use ChromaDB
How to store chunks with metadata (add, search, filter, update, delete)
How to search by meaning, not just keywords
How to send the best chunks to a local LLM using Ollama
How RAG gives answers from your documents, and says "I don't know" when the answer is missing

🛠 Tools used (all free):
Python | sentence-transformers | ChromaDB | Ollama

💻 Setup:
pip install sentence-transformers chromadb ollama
ollama pull llama3.2

🔗 Series so far:
1. Chunking techniques
2. Embeddings: how a chunk becomes a vector
3. Vector database + RAG with Ollama (this video)



🔔 Subscribe for more AI tutorials, and turn on the bell so you never miss a video.

#rag #ollama #chromadb #python #ai