Documentation
Qdrant is an AI-compatible vector dabatase and a semantic search engine. You can use it to extract meaningful information from unstructured data. Learn more about vector search and how it works with AI.
| No-Code Quickstart | Docker Quickstart |
| Try the Qdrant Dashboard | Use Qdrant Client SDKs |
Ready to start developing?
Qdrant is open-source and can be self-hosted. However, the quickest way to get started is with the free tier on Qdrant Cloud. It scales easily and provides an UI where you can interact with data.
Features that make us special:
| Filtrable HNSW Single-stage payload filtering | Discovery & Context Search Exploratory advanced search | Pure-Vector Hybrid Search Full text and semantic search in one |
| Multitenancy Payload-based partitioning | Custom Sharding For data isolation and distribution | Role Based Access Control Secure JWT-based access |
| Binary Quantization Compress data for drastic speedups | Multivector Support For ColBERT late interaction | Built-in IDF Cutting-edge similarity calculation |