In this video, we will build a Voice RAG (Retrieval-Augmented Generation) system using Deepseek, LangChain, and Streamlit to chat with audio files and answer complex questions about them. I will guide you step by step in setting up Ollama’s Deepseek R1 LLM model, transcribing audio using OpenAI’s Whisper, integrating everything with a LangChain-powered RAG, and then showing you how to use a simple Streamlit interface so you can query your audio files in real time. If you’re curious about the Deepseek model or how to build RAGs that even support audio files, this tutorial is for you.
You can watch it here: https://youtu.be/HT4a6A_wXdA