Documentation
Qdrant is an AI-native vector dabatase and a semantic search engine. You can use it to extract meaningful information from unstructured data. Want to see how it works? Clone this repo now and build a search engine in five minutes.
Ready to start developing?
Qdrant is open-source and can be self-hosted. However, the quickest way to get started is with our free tier on Qdrant Cloud. It scales easily and provides an UI where you can interact with data.
Qdrant’s most popular features:
| Filtrable HNSWSingle-stage payload filtering | Recommendations & Context SearchExploratory advanced search | Pure-Vector Hybrid SearchFull text and semantic search in one |
| MultitenancyPayload-based partitioning | Custom ShardingFor data isolation and distribution | Role Based Access ControlSecure JWT-based access |
| QuantizationCompress data for drastic speedups | Multivector SupportFor ColBERT late interaction | Built-in IDFAdvanced similarity calculation |
Developer guidebooks:
| A Complete Guide to Filtering in Vector SearchBeginner & advanced examples showing how to improve precision in vector search. | Building Hybrid Search with Query APIBuild a pure vector-based hybrid search system with our new fusion feature. |
|---|---|
| Multitenancy and Sharding: Best PracticesCombine two powerful features for complete data isolation and scaling. | Benefits of Binary Quantization in Vector SearchCompress data points while retaining essential meaning for extreme search performance. |