About This Event
A deep-dive summit for engineers building AI-powered applications with vector search at their core. Covers the fundamentals of embedding generation, approximate nearest neighbor (ANN) algorithms, HNSW and IVF indexing, hybrid search combining vector and keyword retrieval, and production deployment patterns with pgvector, Qdrant, Weaviate, and Milvus. Learn how to tune recall vs. latency trade-offs, manage vector lifecycles, and integrate vector databases into existing data infrastructure.
Key Topics
Embedding generation and management
ANN algorithms: HNSW and IVF
Hybrid search: vector + keyword
Recall vs. latency trade-offs
pgvector, Qdrant, Weaviate, Milvus deep dives
Integrating vector DBs into production data pipelines
Who Should Attend
AI/ML engineers
Backend engineers building RAG and semantic search
Data engineers and architects
Tech leads evaluating vector database solutions
Speakers
James Wallace
Product Marketing Lead · Dragonfly
Hybrid search patterns at scale
Hybrid SearchSemantic Caching
Radoslaw Szulgo
Senior Product Manager · Percona
Vector Search on Your Terms: From Prototype to Production with Percona for MongoDB
Co-speaker with Sandra Romanchenko
AI Infrastructure
Sandra Romanchenko
Staff QA Engineer · Percona
Vector Search on Your Terms: From Prototype to Production with Percona for MongoDB
Co-speaker with Radoslaw Szulgo
Sergey Nikolaev
Engineer · Manticore Search
Vector SearchFull-Text Search
Sergey Pronin
Program CommitteeFounder · Solanica Inc.
Comparing Vector Databases on Kubernetes
AI InfrastructurePlatform Engineering
dekel asaf
Founder · Tovli Technologies
AI InfrastructurePerformance Engineering
Sponsors
Backed by Industry Leaders
Presenting
