[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-71874":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":24,"hasPages":24,"topics":25,"createdAt":9,"pushedAt":9,"updatedAt":34,"readmeContent":35,"aiSummary":36,"trendingCount":15,"starSnapshotCount":15,"syncStatus":37,"lastSyncTime":38,"discoverSource":39},71874,"lancedb","lancedb\u002Flancedb","Developer-friendly OSS embedded retrieval library for multimodal AI. Search More; Manage Less.","https:\u002F\u002Flancedb.com\u002Fdocs",null,"HTML",10568,905,53,549,0,47,111,299,141,118.87,"Apache License 2.0",false,"main",true,[26,27,28,29,30,31,32,33],"approximate-nearest-neighbor-search","image-search","nearest-neighbor-search","recommender-system","search-engine","semantic-search","similarity-search","vector-database","2026-06-12 04:01:02","\u003Ca href=\"https:\u002F\u002Fcloud.lancedb.com\" target=\"_blank\">\n  \u003Cimg src=\"https:\u002F\u002Fgithub.com\u002Fuser-attachments\u002Fassets\u002F92dad0a2-2a37-4ce1-b783-0d1b4f30a00c\" alt=\"LanceDB Cloud Public Beta\" width=\"100%\" style=\"max-width: 100%;\">\n\u003C\u002Fa>\n\u003Cdiv align=\"center\">\n\n[![LanceDB](docs\u002Fsrc\u002Fassets\u002Fhero-header.png)](https:\u002F\u002Flancedb.com)\n[![Website](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Website-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https:\u002F\u002Flancedb.com\u002F)\n[![Blog](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBlog-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https:\u002F\u002Fblog.lancedb.com\u002F)\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Discord-100000?style=for-the-badge&logo=discord&logoColor=white&labelColor=645cfb&color=645cfb)](https:\u002F\u002Fdiscord.gg\u002FzMM32dvNtd)\n[![Twitter](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Twitter-100000?style=for-the-badge&logo=x&logoColor=white&labelColor=645cfb&color=645cfb)](https:\u002F\u002Ftwitter.com\u002Flancedb)\n[![LinkedIn](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-LinkedIn-100000?style=for-the-badge&logo=linkedin&logoColor=white&labelColor=645cfb&color=645cfb)](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Flancedb\u002F)\n\n\n\u003Cimg src=\"docs\u002Fsrc\u002Fassets\u002Flancedb.png\" alt=\"LanceDB\" width=\"50%\">\n\n# **The Multimodal AI Lakehouse**\n\n[**How to Install** ](#how-to-install) ✦ [**Detailed Documentation**](https:\u002F\u002Fdocs.lancedb.com) ✦ [**Tutorials and Recipes**](https:\u002F\u002Fgithub.com\u002Flancedb\u002Fvectordb-recipes\u002Ftree\u002Fmain) ✦  [**Contributors**](#contributors) \n\n**The ultimate multimodal data platform for AI\u002FML applications.** \n\nLanceDB is designed for fast, scalable, and production-ready vector search. It is built on top of the Lance columnar format. You can store, index, and search over petabytes of multimodal data and vectors with ease. \nLanceDB is a central location where developers can build, train and analyze their AI workloads.\n\n\u003C\u002Fdiv>\n\n\u003Cbr>\n\n## **Demo: Multimodal Search by Keyword, Vector or with SQL**\n\u003Cimg max-width=\"750px\" alt=\"LanceDB Multimodal Search\" src=\"https:\u002F\u002Fgithub.com\u002Flancedb\u002Flancedb\u002Fassets\u002F917119\u002F09c5afc5-7816-4687-bae4-f2ca194426ec\">\n\n## **Star LanceDB to get updates!**\n\n\u003Cdetails>\n\u003Csummary>⭐ Click here ⭐  to see how fast we're growing!\u003C\u002Fsummary>\n\u003Cpicture>\n  \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=lancedb\u002Flancedb&theme=dark&type=Date\">\n  \u003Cimg width=\"100%\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fsvg?repos=lancedb\u002Flancedb&theme=dark&type=Date\">\n\u003C\u002Fpicture>\n\u003C\u002Fdetails>\n\n## **Key Features**:\n\n- **Fast Vector Search**: Search billions of vectors in milliseconds with state-of-the-art indexing.\n- **Comprehensive Search**: Support for vector similarity search, full-text search and SQL.\n- **Multimodal Support**: Store, query and filter vectors, metadata and multimodal data (text, images, videos, point clouds, and more).\n- **Advanced Features**: Zero-copy, automatic versioning, manage versions of your data without needing extra infrastructure. GPU support in building vector index.\n\n### **Products**:\n- **Open Source & Local**: 100% open source, runs locally or in your cloud. No vendor lock-in.\n- **Cloud and Enterprise**: Production-scale vector search with no servers to manage. Complete data sovereignty and security.\n\n### **Ecosystem**:\n- **Columnar Storage**: Built on the Lance columnar format for efficient storage and analytics.\n- **Seamless Integration**: Python, Node.js, Rust, and REST APIs for easy integration. Native Python and Javascript\u002FTypescript support.\n- **Rich Ecosystem**: Integrations with [**LangChain** 🦜️🔗](https:\u002F\u002Fpython.langchain.com\u002Fdocs\u002Fintegrations\u002Fvectorstores\u002Flancedb\u002F), [**LlamaIndex** 🦙](https:\u002F\u002Fgpt-index.readthedocs.io\u002Fen\u002Flatest\u002Fexamples\u002Fvector_stores\u002FLanceDBIndexDemo.html), Apache-Arrow, Pandas, Polars, DuckDB and more on the way.\n\n## **How to Install**:\n\nFollow the [Quickstart](https:\u002F\u002Fdocs.lancedb.com\u002Fquickstart) doc to set up LanceDB locally. \n\n**API & SDK:** We also support Python, Typescript and Rust SDKs\n\n| Interface | Documentation |\n|-----------|---------------|\n| Python SDK | https:\u002F\u002Flancedb.github.io\u002Flancedb\u002Fpython\u002Fpython\u002F |\n| Typescript SDK | https:\u002F\u002Flancedb.github.io\u002Flancedb\u002Fjs\u002Fglobals\u002F |\n| Rust SDK | https:\u002F\u002Fdocs.rs\u002Flancedb\u002Flatest\u002Flancedb\u002Findex.html |\n| REST API | https:\u002F\u002Fdocs.lancedb.com\u002Fapi-reference\u002Frest |\n\n## **Join Us and Contribute**\n\nWe welcome contributions from everyone! Whether you're a developer, researcher, or just someone who wants to help out. \n\nIf you have any suggestions or feature requests, please feel free to open an issue on GitHub or discuss it on our [**Discord**](https:\u002F\u002Fdiscord.gg\u002FG5DcmnZWKB) server.\n\n[**Check out the GitHub Issues**](https:\u002F\u002Fgithub.com\u002Flancedb\u002Flancedb\u002Fissues) if you would like to work on the features that are planned for the future. If you have any suggestions or feature requests, please feel free to open an issue on GitHub. \n\n## **Contributors**\n\n\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Flancedb\u002Flancedb\u002Fgraphs\u002Fcontributors\">\n  \u003Cimg src=\"https:\u002F\u002Fcontrib.rocks\u002Fimage?repo=lancedb\u002Flancedb\" \u002F>\n\u003C\u002Fa>\n\n\n## **Stay in Touch With Us**\n\u003Cdiv align=\"center\">\n\n\u003C\u002Fbr>\n\n[![Website](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Website-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https:\u002F\u002Flancedb.com\u002F)\n[![Blog](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FBlog-100000?style=for-the-badge&labelColor=645cfb&color=645cfb)](https:\u002F\u002Fblog.lancedb.com\u002F)\n[![Discord](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Discord-100000?style=for-the-badge&logo=discord&logoColor=white&labelColor=645cfb&color=645cfb)](https:\u002F\u002Fdiscord.gg\u002FzMM32dvNtd)\n[![Twitter](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-Twitter-100000?style=for-the-badge&logo=x&logoColor=white&labelColor=645cfb&color=645cfb)](https:\u002F\u002Ftwitter.com\u002Flancedb)\n[![LinkedIn](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002F-LinkedIn-100000?style=for-the-badge&logo=linkedin&logoColor=white&labelColor=645cfb&color=645cfb)](https:\u002F\u002Fwww.linkedin.com\u002Fcompany\u002Flancedb\u002F)\n\n\u003C\u002Fdiv>\n","LanceDB 是一个面向开发者的开源嵌入式检索库，专为多模态AI应用设计。它支持快速的向量搜索、全文本搜索和SQL查询，能够存储、索引并搜索PB级别的多模态数据（包括文本、图像、视频等）。LanceDB基于Lance列格式构建，具备先进的索引技术，能够在毫秒级时间内完成对数十亿向量的搜索任务，并且提供了零拷贝、自动版本管理以及GPU加速等高级特性。适用于需要高效处理大规模多模态数据集的人工智能\u002F机器学习项目，特别是在推荐系统、语义搜索及相似性搜索等领域。",2,"2026-06-11 03:39:03","high_star"]