Learn to build an end-to-end RAG (Retrieval Augmented Generation) application in this first video of a three-part series focused on interacting with unstructured data including audio, video, images, PDF, Excel, and HTML files. Master the implementation of a RAG component using Langchain as the primary technology, while working with various LLMs including Gemini Pro Fast, Microsoft Phi3.5 Mini, and LLama 3.2 3B (hosted on Nvidia NIM). Explore different vector stores such as Elastic, Choma, Faiss, and Vilmus, alongside embedding models from Gemini and Nvidia. Develop the application using Streamlit for UX and application serving, and implement containerization with Docker and Docker Compose. Access the complete project materials through the provided GitHub repository to follow along with the Spanish-language tutorial.
RAG: End-to-End Application - Speaking with Unstructured Data - Part 1 (Spanish)
The Machine Learning Engineer via YouTube
Overview
Syllabus
RAG: E2E App. Habla con tu data no estructurada Parte 1 (Español) #machinelearning #datascience
Taught by
The Machine Learning Engineer
Related Courses
-
RAG: End-to-End Application - Speaking with Unstructured Data Part 2 - Spanish
-
RAG: End-to-End Application - Hablando con Datos No Estructurados - Parte 3
-
Building RAG Applications: Speaking with Unstructured Data Using LangChain - Part 1
-
Building End-to-End RAG Applications with Unstructured Data - Part 3: Docker Integration
-
Building RAG Applications: Speaking with Unstructured Data Using LangChain - Part 2
-
Generative AI Architectures with LLM, Prompt, RAG, Vector DB
