Learn to build a Multimodal RAG (Retrieval-Augmented Generation) agent in this 47-minute video tutorial that demonstrates handling both PDF documents and images using LangChain framework, Google's VertexAI SDK, and Chroma vector store. Follow along with practical implementation steps to create an agent capable of processing and understanding multiple data formats. Access the complete implementation through the provided GitHub repository, which includes detailed code examples and configurations for integrating these powerful tools. Master the techniques of combining different unstructured data types to create a more versatile and capable RAG system for advanced machine learning applications.
Multimodal RAG with LangChain, VertexAI, Gemini Pro and Chroma
The Machine Learning Engineer via YouTube
Overview
Syllabus
RAG: Multi-modal RAG with Langchain, VertexAi, Gemini Pro and Chroma #machinelearning #datascience
Taught by
The Machine Learning Engineer
Related Courses
-
Multimodal RAG with LangChain, VertexAI, Gemini Pro and Chroma
-
Retrieval Augmented Generation (RAG) with LangChain
-
Inspect Rich Documents with Gemini Multimodality and Multimodal RAG
-
RAG From Scratch - Implementing Retrieval-Augmented Generation with LangChain
-
Project: Generative AI Applications with RAG and LangChain
-
Langchain: RAG QA Tool with Gemini Pro, Langchain, and Chroma
