Agent Bricks - Building Multi-Agent Systems for Structured and Unstructured Information
Databricks via YouTube
Overview
Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore advanced techniques for building sophisticated multi-agent systems that enable natural language interactions with both structured databases and unstructured document collections in this 37-minute conference talk. Discover how to create unified and governed AI systems that seamlessly interpret questions, retrieve relevant information, and generate accurate answers across entire data ecosystems. Learn strategies for combining vector search over unstructured documents with retrieval from structured databases, while mastering techniques for optimizing unstructured data processing through effective parsing, metadata enrichment, and intelligent chunking. Understand methods for integrating different retrieval mechanisms while ensuring consistent data governance and security, and gain practical approaches for evaluating and improving Knowledge Base Question Answering (KBQA) system quality through automated and human feedback mechanisms.
Syllabus
Agent Bricks: Building Multi-Agent Systems for Structured and Unstructured Information
Taught by
Databricks