Explore the expansion of Retrieval-Augmented Generation (RAG) workflows to incorporate multimodal capabilities in this conference talk from Haystack US 2024. Delve into the challenges of traditional RAG systems that primarily focus on text-based retrieval, and discover how to leverage Language Models (LLMs) and multimodal embeddings to enhance both retrieval and generation processes. Witness a live demonstration showcasing the processing of PDF documents in a vector database, extracting content from images, tables, and text. Learn how multimodal search can be employed in the retriever and how LLMs can enrich the final response. Gain insights from search specialist Praveen Mohan Prasad and solutions architect Hajer Bouafif on implementing and operationalizing strategies to improve search experiences using Machine Learning and building large-scale Machine Learning search solutions.
Overview
Syllabus
Haystack US 2024 - Praveen Mohan Prasad & Hajer Bouafif: Expanding RAG with multimodal capabilities
Taught by
OpenSource Connections
Related Courses
-
Building Multimodal Search and RAG
-
RAG Fundamentals and Advanced Techniques - Full Course
-
RAG From Scratch - Implementing Retrieval-Augmented Generation with LangChain
-
Vector Databases: from Embeddings to Applications
-
Learn Embeddings and Vector Databases
-
Vector Search RAG Tutorial – Combine Your Data with LLMs with Advanced Search
