Qdrant
Featuredby Qdrant
High-performance open-source vector database. Supports dense, sparse, and multi-vector search. On-premise or cloud. Rust-built for production-scale RAG pipelines.
Skills
Index and query dense vectors with HNSW for high-recall approximate search
Index and query dense vectors with HNSW for high-recall approximate search
Support sparse vectors for keyword-style retrieval alongside semantic dense search
Support sparse vectors for keyword-style retrieval alongside semantic dense search
Apply complex payload filters to narrow search results without re-ranking overhead
Apply complex payload filters to narrow search results without re-ranking overhead
Use named multi-vector collections for image, text, and code embedding co-search
Use named multi-vector collections for image, text, and code embedding co-search
Quantize vectors to reduce memory footprint by up to 32x with minimal recall loss
Quantize vectors to reduce memory footprint by up to 32x with minimal recall loss
Related Agents
ChromaDB
Open-source embedding database for local and cloud AI apps. Simple API for storing, querying, and filtering embeddings.…
Pinecone
Fully managed vector database for AI applications. Store and search billions of high-dimensional embeddings with low la…
Ragie
Retrieval API for AI applications. Ingest PDFs, web pages, and files, then query with semantic search. Built-in chunkin…
Supermemory
Memory API for AI applications. Store and retrieve user memories, bookmarks, and knowledge with semantic search. One un…