Advanced Vector Search for Agentic Systems
Technical implementation of vector databases, embedding strategies, and RAG architectures for production agents.
A comprehensive technical exploration of vector search systems powering modern agentic applications. This session covers embedding model selection and fine-tuning, vector index structures (HNSW, IVF, Product Quantization), approximate nearest neighbor algorithms, hybrid search combining dense and sparse vectors, and metadata filtering strategies. We examine production considerations including index optimization, query performance tuning, storage efficiency, and real-time updates. The discussion includes architectural patterns for RAG systems, chunking strategies, reranking pipelines, and handling complex multi-step retrieval in agentic workflows.
Overview
A comprehensive technical exploration of vector search systems powering modern agentic applications. This session covers embedding model selection and fine-tuning, vector index structures (HNSW, IVF, Product Quantization), approximate nearest neighbor algorithms, hybrid search combining dense and sparse vectors, and metadata filtering strategies. We examine production considerations including index optimization, query performance tuning, storage efficiency, and real-time updates. The discussion includes architectural patterns for RAG systems, chunking strategies, reranking pipelines, and handling complex multi-step retrieval in agentic workflows.
Thank you for your interest in this talk. We look forward to seeing you!
Recommended Talks
Explore related talks that complement this research
TECHNICAL
Agents
Introduction to Agentic AI
A practical introduction to the core components required to build reliable, production-ready agentic AI systems.
TECHNICAL
Agents
Agent Architectures and Design Patterns
Design Patterns for Robust, Controllable Multi-Agent Systems
TECHNICAL
Agents
Vector Databases for LLM Systems: Foundations, Architectures, and Emerging Directions
A practical look at how vector databases power RAG systems, improve retrieval quality, and support real-world LLM applications.
TECHNICAL
Agents
Building AI Systems That Learn from Real Humans
A practical overview of how human feedback, cognitive biases, and behavioral models can improve AI alignment.