Technology
LanceDB
LanceDB is the serverless, open-source vector database for multimodal AI: it powers fast, scalable RAG and semantic search applications.
LanceDB is your multimodal AI lakehouse, built on the high-performance Lance columnar format (Rust-based). This architecture provides a unified data store, natively handling vectors, metadata, and raw multimodal data (text, images, video) to eliminate separate databases. Leverage its disk-based indexes for low-latency vector search, full-text search, and SQL queries over petabyte-scale datasets. The platform delivers the speed and scalability required for production-ready RAG, autonomous agents, and large-scale model training workflows.
6 projects
·
8 cities
Related technologies
Recent Talks & Demos
Showing 1-6 of 6
Reality Check: Personal Fact-Checking
Tokyo
Feb 19
Claude Code
OpenAI Codex
FiftyOne Visual Similarity Search
Raleigh
Sep 30
FiftyOne
CLIP
Archetype ECS for AI Simulations
Chicago
Jun 3
Python
Daft
Tactician: Actionable Workplace Advice
Seattle
Apr 24
Python
TypeScript
Grounded Memory with LLM and OWL
San Francisco
Feb 27
GPT-4
Claude-3
dlt: Up-to-Date RAG Ingestion
Berlin
Jul 18
dlt
LanceDB