Qdrant
Rust-based vector search engine with rich filtering
Qdrant is profiled here as a RAG Framework tool for engineering teams. Read about features, pricing, and how it compares to related options in the tools directory.
Description
Qdrant is an open-source vector database written in Rust, founded in Berlin in 2021 by Andrey Vasnetsov and Andre Zayarni. It pairs HNSW-based vector similarity search with expressive payload filtering, which suits workloads where metadata conditions matter as much as embedding distance. Quantization options shrink memory footprints for collections that reach into the billions of vectors, and Qdrant Cloud runs managed clusters. Qdrant also serves as the retrieval backend inside many RAG stacks, with first-party integrations for LangChain, LlamaIndex, and Haystack.
Key Capabilities:
Vector similarity search with filterable JSON payloads
Scalar, product, and binary quantization for memory efficiency
Sparse vectors with server-side hybrid search fusion
Distributed deployment with sharding and replication
REST and gRPC APIs with Python, TypeScript, Go, and Rust clients
Apache 2.0 license plus a managed cloud free cluster
Alternative tools
- Docling
Open-source document conversion built for RAG pipelines
- Unstructured
Turn raw documents into LLM-ready structured data
- Voyage AI
Retrieval-optimized embedding and reranking models
- Chroma
Developer-first embedding database that runs anywhere
- Weaviate
Open-source vector database with native hybrid search
- Pinecone
Managed vector database for production retrieval workloads