Databricks Vector Search: What, Why and How

Databricks July 23, 2024
Video Thumbnail
Databricks Logo

Databricks

View Channel

About

Databricks is the Data and AI company. More than 20,000 organizations worldwide — including adidas, AT&T, Bayer, Block, Mastercard, Rivian, Unilever, and over 60% of the Fortune 500 — rely on Databricks to build and scale data and AI apps, analytics and agents. Headquartered in San Francisco with 30+ offices around the globe, Databricks offers a unified Data Intelligence Platform that includes Agent Bricks, Lakeflow, Lakehouse, Lakebase and Unity Catalog.

Video Description

Building a successful GenAI application requires more than just leveraging LLMs. It's essential to provide the right context for these models via semantic search to ensure fast and accurate responses. Databricks Vector Search is designed with scalability and simplicity in mind, offering a powerful tool for simplifying the complexity of semantic search. It includes data ingestion, embedding generation, and serving ""search."" This session will equip you with a toolbox to enhance your GenAI applications and speed up deployments to production while adhering to complex governance and compliance requirements. We'll cover the development of a prototypical RAG solution, along with the most common challenges faced in the field and how to overcome them, including: Maintaining Index Health  Using Effective Chunking Strategies Improving Vector Search recall and  precision Scaling ingestion Improving retrieval time Applying Governance Talk By: Ankit Vij, Senior Software Engineer, Databricks ; Sonali Guleria, Solutions Architect, Databricks Here's more to explore: LLM Compact Guide: https://dbricks.co/43WuQyb Big Book of MLOps: https://dbricks.co/3r0Pqiz Connect with us: Website: https://databricks.com Twitter: https://twitter.com/databricks LinkedIn: https://www.linkedin.com/company/data… Instagram: https://www.instagram.com/databricksinc Facebook: https://www.facebook.com/databricksinc

You May Also Like