Building RAG Applications: Speaking with Unstructured Data Using LangChain - Part 2

Learn to build an end-to-end RAG (Retrieval Augmented Generation) application in this second video of a three-part series focused on enabling conversations with unstructured data including audio, video, images, PDF, Excel, CSV, and HTML files. Dive into the detailed architecture and code implementation while exploring the integration of Langchain with various technologies. Master working with multiple LLMs including Gemini Pro Fast, Microsoft Phi3.5 Mini, and LLama 3.2 3B hosted on Nvidia NIM. Gain hands-on experience with vector stores like Elastic, Chroma, Faiss, and Vilmus, while implementing embedding models from Gemini and Nvidia. Develop practical skills in using Streamlit for the user interface and application server, along with Docker and Docker compose for containerization. Access the complete project repository on GitHub to follow along with the implementation details and best practices for building robust RAG applications.