Beyond Simple RAG - Unlocking Quality, Scale and Cost-Efficient Retrieval With Mosaic AI Vector Search
Databricks via YouTube
Master Agentic AI, GANs, Fine-Tuning & LLM Apps
Finance Certifications Goldman Sachs & Amazon Teams Trust
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Learn how to implement high-quality retrieval systems using Mosaic AI Vector Search in this 37-minute conference talk from Databricks. Discover advanced techniques beyond basic RAG (Retrieval-Augmented Generation) applications, including hybrid retrieval methods and reranking strategies that improve out-of-the-box results. Explore best practices for managing vector indexes with minimal operational overhead while examining real-world examples of organizations that have successfully scaled their search and recommendation systems. Understand how Mosaic AI Vector Search integrates with the Databricks Data Intelligence Platform to eliminate pipeline maintenance through automatic data synchronization from source to index. Gain insights into optimizing retrieval systems for better scalability, efficiency, and relevance across various use cases including RAG applications, entity resolution, recommendation systems, and search functionality. The session covers major product advancements that address customer demands for greater scale, improved quality, and cost-efficient performance in production environments.
Syllabus
Beyond Simple RAG:Unlocking Quality, Scale and Cost-Efficient Retrieval With Mosaic AI Vector Search
Taught by
Databricks