Managed vector database for AI applications — fast, scalable similarity search at any scale.
Data framework for building LLM applications over custom data with advanced RAG capabilities.
Intelligent memory layer for AI assistants — persistent, personalized memory across conversations.
Open-source vector database with built-in ML models, GraphQL API, and hybrid search.
High-performance vector search engine with rich filtering, payload storage, and Rust-based speed.
Open-source embedding database for building AI applications with persistent vector storage.
Document parsing and preprocessing library that extracts clean text from PDFs, HTML, and more.
RAG evaluation framework — measure faithfulness, relevancy, and context precision of your pipelines.