[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-2126":3},{"id":4,"name":5,"fullName":6,"owner":5,"repo":5,"description":7,"homepage":8,"htmlUrl":9,"language":10,"languages":9,"totalLinesOfCode":9,"stars":11,"forks":12,"watchers":13,"openIssues":14,"contributorsCount":15,"subscribersCount":15,"size":15,"stars1d":16,"stars7d":17,"stars30d":18,"stars90d":15,"forks30d":15,"starsTrendScore":19,"compositeScore":20,"rankGlobal":9,"rankLanguage":9,"license":21,"archived":22,"fork":22,"defaultBranch":23,"hasWiki":22,"hasPages":24,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":46,"readmeContent":47,"aiSummary":48,"trendingCount":15,"starSnapshotCount":15,"syncStatus":49,"lastSyncTime":50,"discoverSource":51},2126,"qdrant","qdrant\u002Fqdrant","Qdrant - High-performance, massive-scale Vector Database and Vector Search Engine for the next generation of AI. Also available in the cloud https:\u002F\u002Fcloud.qdrant.io\u002F","https:\u002F\u002Fqdrant.tech",null,"Rust",32032,2350,151,439,0,24,236,802,157,45,"Apache License 2.0",false,"master",true,[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"ai-search","ai-search-engine","embeddings-similarity","hnsw","hybrid-search","image-search","knn-algorithm","machine-learning","mlops","nearest-neighbor-search","neural-network","neural-search","recommender-system","search","search-engine","search-engines","similarity-search","vector-database","vector-search","vector-search-engine","2026-06-12 02:00:37","\u003Cp align=\"center\">\n  \u003Cpicture>\n      \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fraw\u002Fmaster\u002Fdocs\u002Flogo-dark.svg\">\n      \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fraw\u002Fmaster\u002Fdocs\u002Flogo-light.svg\">\n      \u003Cimg height=\"100\" alt=\"Qdrant\" src=\"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fraw\u002Fmaster\u002Fdocs\u002Flogo.svg\">\n  \u003C\u002Fpicture>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n    \u003Cb>Vector Search Engine for the next generation of AI applications\u003C\u002Fb>\n\u003C\u002Fp>\n\n\u003Cp align=center>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Factions\u002Fworkflows\u002Frust.yml\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Factions\u002Fworkflow\u002Fstatus\u002Fqdrant\u002Fqdrant\u002Frust.yml?style=flat-square\" alt=\"Tests status\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fapi.qdrant.tech\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDocs-OpenAPI%203.0-success?style=flat-square\" alt=\"OpenAPI Docs\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fblob\u002Fmaster\u002FLICENSE\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fgithub\u002Flicense\u002Fqdrant\u002Fqdrant?style=flat-square\" alt=\"Apache 2.0 License\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fqdrant.to\u002Fdiscord\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fdiscord\u002F907569970500743200?logo=Discord&style=flat-square&color=7289da\" alt=\"Discord\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fqdrant.to\u002Froadmap\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FRoadmap-2025-bc1439.svg?style=flat-square\" alt=\"Roadmap 2025\">\u003C\u002Fa>\n    \u003Ca href=\"https:\u002F\u002Fcloud.qdrant.io\u002F\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FQdrant-Cloud-24386C.svg?logo=cloud&style=flat-square\" alt=\"Qdrant Cloud\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n**Qdrant** (read: _quadrant_) is a vector similarity search engine and vector database.\nIt provides a production-ready service with a convenient API to store, search, and manage points—vectors with an additional payload\nQdrant is tailored to extended filtering support. It makes it useful for all sorts of neural-network or semantic-based matching, faceted search, and other applications.\n\nQdrant is written in Rust 🦀, which makes it fast and reliable even under high load. See [benchmarks](https:\u002F\u002Fqdrant.tech\u002Fbenchmarks\u002F).\n\nWith Qdrant, embeddings or neural network encoders can be turned into full-fledged applications for matching, searching, recommending, and much more!\n\nQdrant is also available as a fully managed **[Qdrant Cloud](https:\u002F\u002Fcloud.qdrant.io\u002F)** ⛅ including a **free tier**.\n\n\u003Cp align=\"center\">\n\u003Cstrong>\u003Ca href=\"docs\u002FQUICK_START.md\">Quick Start\u003C\u002Fa> • \u003Ca href=\"#clients\">Client Libraries\u003C\u002Fa> • \u003Ca href=\"#demo-projects\">Demo Projects\u003C\u002Fa> • \u003Ca href=\"#integrations\">Integrations\u003C\u002Fa> • \u003Ca href=\"#contacts\">Contact\u003C\u002Fa>\n\n\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n## Getting Started\n\n### Python\n\n```\npip install qdrant-client\n```\n\nThe python client offers a convenient way to start with Qdrant locally:\n\n```python\nfrom qdrant_client import QdrantClient\nqdrant = QdrantClient(\":memory:\") # Create in-memory Qdrant instance, for testing, CI\u002FCD\n# OR\nclient = QdrantClient(path=\"path\u002Fto\u002Fdb\")  # Persists changes to disk, fast prototyping\n```\n\n### Client-Server\n\nTo experience the full power of Qdrant locally, run the container with this command:\n\n```bash\ndocker run -p 6333:6333 qdrant\u002Fqdrant\n```\n\n> [!CAUTION]\n> Starts an insecure deployment without authentication open to all network interfaces. Please refer to [secure your instance](https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fguides\u002Fsecurity\u002F#secure-your-instance).\n\nNow you can connect to this with any client, including Python:\n\n```python\nqdrant = QdrantClient(\"http:\u002F\u002Flocalhost:6333\") # Connect to existing Qdrant instance\n```\n\nBefore deploying Qdrant to production, be sure to read our [installation](https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fguides\u002Finstallation\u002F) and [security](https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Fguides\u002Fsecurity\u002F) guides.\n\n### Clients\n\nQdrant offers the following client libraries to help you integrate it into your application stack with ease:\n\n- Official:\n  - [Go client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fgo-client)\n  - [Rust client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Frust-client)\n  - [JavaScript\u002FTypeScript client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-js)\n  - [Python client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-client)\n  - [.NET\u002FC# client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant-dotnet)\n  - [Java client](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fjava-client)\n- Community:\n  - [Elixir](https:\u002F\u002Fhexdocs.pm\u002Fqdrant\u002Freadme.html)\n  - [PHP](https:\u002F\u002Fgithub.com\u002Fhkulekci\u002Fqdrant-php)\n  - [Ruby](https:\u002F\u002Fgithub.com\u002Fandreibondarev\u002Fqdrant-ruby)\n  - [Java](https:\u002F\u002Fgithub.com\u002Fmetaloom\u002Fqdrant-java-client)\n\n### Where do I go from here?\n\n- [Quick Start Guide](docs\u002FQUICK_START.md)\n- End to End [Colab Notebook](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F1Bz8RSVHwnNDaNtDwotfPj0w7AYzsdXZ-?usp=sharing) demo with SentenceBERT and Qdrant\n- Detailed [Documentation](https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002F) are great starting points\n- [Step-by-Step Tutorial](https:\u002F\u002Fqdrant.to\u002Fqdrant-tutorial) to create your first neural network project with Qdrant\n\n## Demo Projects\u003Ca href=\"https:\u002F\u002Freplit.com\u002F@qdrant\">\u003Cimg align=\"right\" src=\"https:\u002F\u002Freplit.com\u002Fbadge\u002Fgithub\u002Fqdrant\u002Fqdrant\" alt=\"Run on Repl.it\">\u003C\u002Fa>\n\n### Discover Semantic Text Search 🔍\n\nUnlock the power of semantic embeddings with Qdrant, transcending keyword-based search to find meaningful connections in short texts. Deploy a neural search in minutes using a pre-trained neural network, and experience the future of text search. [Try it online!](https:\u002F\u002Fqdrant.to\u002Fsemantic-search-demo)\n\n### Explore Similar Image Search - Food Discovery 🍕\n\nThere's more to discovery than text search, especially when it comes to food. People often choose meals based on appearance rather than descriptions and ingredients. Let Qdrant help your users find their next delicious meal using visual search, even if they don't know the dish's name. [Check it out!](https:\u002F\u002Fqdrant.to\u002Ffood-discovery)\n\n### Master Extreme Classification - E-commerce Product Categorization 📺\n\nEnter the cutting-edge realm of extreme classification, an emerging machine learning field tackling multi-class and multi-label problems with millions of labels. Harness the potential of similarity learning models, and see how a pre-trained transformer model and Qdrant can revolutionize e-commerce product categorization. [Play with it online!](https:\u002F\u002Fqdrant.to\u002Fextreme-classification-demo)\n\n\u003Cdetails>\n\u003Csummary> More solutions \u003C\u002Fsummary>\n\n\u003Ctable>\n    \u003Ctr>\n        \u003Ctd width=\"30%\">\n            \u003Cimg src=\"https:\u002F\u002Fqdrant.tech\u002Fcontent\u002Fimages\u002Ftext_search.png\">\n        \u003C\u002Ftd>\n        \u003Ctd width=\"30%\">\n            \u003Cimg src=\"https:\u002F\u002Fqdrant.tech\u002Fcontent\u002Fimages\u002Fimage_search.png\">\n        \u003C\u002Ftd>\n        \u003Ctd width=\"30%\">\n            \u003Cimg src=\"https:\u002F\u002Fqdrant.tech\u002Fcontent\u002Fimages\u002Frecommendations.png\">\n        \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n        \u003Ctd>\n            Semantic Text Search\n        \u003C\u002Ftd>\n        \u003Ctd>\n            Similar Image Search\n        \u003C\u002Ftd>\n        \u003Ctd>\n            Recommendations\n        \u003C\u002Ftd>\n    \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003Ctable>\n    \u003Ctr>\n        \u003Ctd>\n            \u003Cimg width=\"300px\" src=\"https:\u002F\u002Fqdrant.tech\u002Fcontent\u002Fimages\u002Fchat_bots.png\">\n        \u003C\u002Ftd>\n        \u003Ctd>\n            \u003Cimg width=\"300px\" src=\"https:\u002F\u002Fqdrant.tech\u002Fcontent\u002Fimages\u002Fmatching_engines.png\">\n        \u003C\u002Ftd>\n        \u003Ctd>\n            \u003Cimg width=\"300px\" src=\"https:\u002F\u002Fqdrant.tech\u002Fcontent\u002Fimages\u002Fanomalies_detection.png\">\n        \u003C\u002Ftd>\n    \u003C\u002Ftr>\n    \u003Ctr>\n        \u003Ctd>\n            Chat Bots\n        \u003C\u002Ftd>\n        \u003Ctd>\n            Matching Engines\n        \u003C\u002Ftd>\n        \u003Ctd>\n            Anomaly Detection\n        \u003C\u002Ftd>\n    \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n\u003C\u002Fdetails>\n\n## API\n\n### REST\n\nOnline OpenAPI 3.0 documentation is available [here](https:\u002F\u002Fapi.qdrant.tech\u002F).\nOpenAPI makes it easy to generate a client for virtually any framework or programming language.\n\nYou can also download raw OpenAPI [definitions](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fblob\u002Fmaster\u002Fdocs\u002Fredoc\u002Fmaster\u002Fopenapi.json).\n\n### gRPC\n\nFor faster production-tier searches, Qdrant also provides a gRPC interface. You can find gRPC documentation [here](https:\u002F\u002Fqdrant.tech\u002Fdocumentation\u002Finterfaces\u002F#grpc-interface).\n\n## Features\n\n### Filtering and Payload\n\nQdrant can attach any JSON payloads to vectors, allowing for both the storage and filtering of data based on the values in these payloads.\nPayload supports a wide range of data types and query conditions, including keyword matching, full-text filtering, numerical ranges, geo-locations, and more.\n\nFiltering conditions can be combined in various ways, including `should`, `must`, and `must_not` clauses,\nensuring that you can implement any desired business logic on top of similarity matching.\n\n\n### Hybrid Search with Sparse Vectors\n\nTo address the limitations of vector embeddings when searching for specific keywords, Qdrant introduces support for sparse vectors in addition to the regular dense ones.\n\nSparse vectors can be viewed as an generalization of BM25 or TF-IDF ranking. They enable you to harness the capabilities of transformer-based neural networks to weigh individual tokens effectively.\n\n\n### Vector Quantization and On-Disk Storage\n\nQdrant provides multiple options to make vector search cheaper and more resource-efficient.\nBuilt-in vector quantization reduces RAM usage by up to 97% and dynamically manages the trade-off between search speed and precision.\n\n\n### Distributed Deployment\n\nQdrant offers comprehensive horizontal scaling support through two key mechanisms:\n1. Size expansion via sharding and throughput enhancement via replication\n2. Zero-downtime rolling updates and seamless dynamic scaling of the collections\n\n\n### Highlighted Features\n\n* **Query Planning and Payload Indexes** - leverages stored payload information to optimize query execution strategy.\n* **SIMD Hardware Acceleration** - utilizes modern CPU x86-x64 and Neon architectures to deliver better performance.\n* **Async I\u002FO** - uses `io_uring` to maximize disk throughput utilization even on a network-attached storage.\n* **Write-Ahead Logging** - ensures data persistence with update confirmation, even during power outages.\n\n\n# Integrations\n\nExamples and\u002For documentation of Qdrant integrations:\n\n- [Cohere](https:\u002F\u002Fdocs.cohere.com\u002Fdocs\u002Fqdrant-and-cohere) ([blogpost on building a QA app with Cohere and Qdrant](https:\u002F\u002Fqdrant.tech\u002Farticles\u002Fqa-with-cohere-and-qdrant\u002F)) - Use Cohere embeddings with Qdrant\n- [DocArray](https:\u002F\u002Fdocs.docarray.org\u002Fuser_guide\u002Fstoring\u002Findex_qdrant\u002F) - Use Qdrant as a document store in DocArray\n- [Haystack](https:\u002F\u002Fhaystack.deepset.ai\u002Fintegrations\u002Fqdrant-document-store) - Use Qdrant as a document store with Haystack ([blogpost](https:\u002F\u002Fhaystack.deepset.ai\u002Fblog\u002Fqdrant-integration)).\n- [LangChain](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fintegrations\u002Fproviders\u002Fqdrant\u002F) ([blogpost](https:\u002F\u002Fqdrant.tech\u002Farticles\u002Flangchain-integration\u002F)) - Use Qdrant as a memory backend for LangChain.\n- [LlamaIndex](https:\u002F\u002Fdevelopers.llamaindex.ai\u002Fpython\u002Fframework\u002Fintegrations\u002Fvector_stores\u002Fqdrantindexdemo\u002F) - Use Qdrant as a Vector Store with LlamaIndex.\n- [OpenAI - ChatGPT retrieval plugin](https:\u002F\u002Fgithub.com\u002Fopenai\u002Fchatgpt-retrieval-plugin\u002Fblob\u002Fmain\u002Fdocs\u002Fproviders\u002Fqdrant\u002Fsetup.md) - Use Qdrant as a memory backend for ChatGPT\n- [Microsoft Semantic Kernel](https:\u002F\u002Fdevblogs.microsoft.com\u002Fsemantic-kernel\u002Fthe-power-of-persistent-memory-with-semantic-kernel-and-qdrant-vector-database\u002F) - Use Qdrant as persistent memory with Semantic Kernel\n\n## Contacts\n\n- Have questions? Join our [Discord channel](https:\u002F\u002Fqdrant.to\u002Fdiscord) or mention [@qdrant_engine on Twitter](https:\u002F\u002Fqdrant.to\u002Ftwitter)\n- Want to stay in touch with latest releases? Subscribe to our [Newsletters](https:\u002F\u002Fqdrant.tech\u002Fsubscribe\u002F)\n- Looking for a managed cloud? Check [pricing](https:\u002F\u002Fqdrant.tech\u002Fpricing\u002F), need something personalised? We're at [info@qdrant.tech](mailto:info@qdrant.tech)\n\n## License\n\nQdrant is licensed under the Apache License, Version 2.0. View a copy of the [License file](https:\u002F\u002Fgithub.com\u002Fqdrant\u002Fqdrant\u002Fblob\u002Fmaster\u002FLICENSE).\n","Qdrant 是一个面向下一代AI应用的高性能大规模向量数据库和向量搜索引擎。它支持存储、搜索和管理带有附加负载的向量数据点，并且特别适合需要扩展过滤支持的场景，如基于神经网络或语义匹配的应用、面搜索以及其他相关领域。Qdrant 采用 Rust 语言编写，确保了即使在高负载下也能保持快速稳定运行。此外，Qdrant 支持多种算法如 HNSW 和 KNN，以实现高效的近邻搜索功能。无论是本地部署还是通过其提供的云服务（包括免费层级），Qdrant 都能帮助开发者将嵌入式模型或神经网络编码器转换为完整的匹配、搜索及推荐系统等应用。",2,"2026-06-11 02:48:18","top_all"]