RAG: End-to-End Application - Speaking with Unstructured Data Part 2 - Spanish
The Machine Learning Engineer via YouTube
Overview
Learn to build an end-to-end RAG (Retrieval Augmented Generation) application in this Spanish language video tutorial, part 2 of a 3-part series. Explore the code implementation and architecture for creating a RAG component capable of interacting with various unstructured data types including audio, video, images, PDF, Excel, and HTML. Master the integration of multiple technologies including Langchain for the core functionality, multiple LLMs (Gemini Pro Fast, Microsoft Phi3.5 Mini, and LLama 3.2 3B hosted on Nvidia NIM), various vector stores (Elastic, Choma, Faiss, and Vilmus), and embedding models from Gemini and Nvidia. Gain hands-on experience with Streamlit for UX and application serving, while learning to containerize the application using Docker and Docker Compose. Access the complete source code through the provided GitHub repository to follow along with the implementation.
Syllabus
RAG: E2E App. Habla con tu data no estructurada Parte 2 (Español) #machinelearning #datascience
Taught by
The Machine Learning Engineer