## 1. Project Overview & Quickstart (milvus-io/milvus) ## File: README.md [](https://github.com/milvus-io/milvus/blob/master/LICENSE) [](https://milvus.io/docs/install_standalone-docker.md) [](https://milvus.io/docs/roadmap.md) [](https://cloud.zilliz.com/signup?utm_source=partner&utm_medium=referral&utm_campaign=2024-11-04_web_github-readme_global) [](https://milvus.io/docs/tutorials-overview.md) [](https://milvus.io/slack) [](https://discord.gg/mKc3R95yE5) [](https://x.com/milvusio) ## What is Milvus? 🐦 [Milvus](https://milvus.io/) is a high-performance vector database built for scale. It powers AI applications by efficiently organizing and searching vast amounts of unstructured data, such as text, images, and multi-modal information. 🧑‍💻 Written in Go and C++, Milvus implements hardware acceleration for CPU/GPU to achieve best-in-class vector search performance. Thanks to its [fully-distributed and K8s-native architecture](https://milvus.io/docs/overview.md#What-Makes-Milvus-so-Scalable), Milvus can scale horizontally, handle tens of thousands of search queries on billions of vectors, and keep data fresh with real-time streaming updates. Milvus also supports [Standalone mode](https://milvus.io/docs/install_standalone-docker.md) for single machine deployment. [Milvus Lite](https://milvus.io/docs/milvus_lite.md) is a lightweight version good for quickstart in python with `pip install`. Want to use Milvus with zero setup? Try out [Zilliz Cloud ☁️](https://cloud.zilliz.com/signup?utm_source=partner&utm_medium=referral&utm_campaign=2024-11-04_web_github-readme_global) for free. Milvus is available as a fully managed service on Zilliz Cloud, with [Serverless](https://zilliz.com/serverless?utm_source=partner&utm_medium=referral&utm_campaign=2024-11-04_web_github-readme_global), [Dedicated](https://zilliz.com/cloud?utm_source=partner&utm_medium=referral&utm_campaign=2024-11-04_web_github-readme_global) and [BYOC](https://zilliz.com/bring-your-own-cloud?utm_source=partner&utm_medium=referral&utm_campaign=2024-11-04_web_github-readme_global) options available. For questions about how to use Milvus, join the community on [Discord](https://discord.gg/33mfvwep3J) to get help. For reporting problems, file bugs and feature requests in GitHub [Issues](https://github.com/milvus-io/milvus/issues) or ask in [Discussions](https://github.com/milvus-io/milvus/discussions). The Milvus open-source project is under [LF AI & Data Foundation](https://lfaidata.foundation/projects/milvus/), distributed with [Apache 2.0](https://github.com/milvus-io/milvus/blob/master/LICENSE) License, with Zilliz as its major contributor. ## Quickstart ```python $ pip install -U pymilvus ``` This installs `pymilvus`, the Python SDK for Milvus. Use `MilvusClient` to create a client: ```python from pymilvus import MilvusClient ``` * You can also try Milvus Lite for quickstart by installing `pymilvus[milvus-lite]`. To create a local vector database, simply instantiate a client with a local file name for persisting data: ```python client = MilvusClient("milvus_demo.db") ``` * You can also specify the credentials to connect to your deployed [Milvus server](https://milvus.io/docs/authenticate.md?tab=docker) or [Zilliz Cloud](https://docs.zilliz.com/docs/quick-start): ```python client = MilvusClient( uri="", token="") ``` With the client, you can create collection: ```python client.create_collection( collection_name="demo_collection", dimension=768, # The vectors we will use in this demo have 768 dimensions ) ``` Ingest data: ```python res = client.insert(collection_name="demo_collection", data=data) ``` Perform vector search: ```python query_vectors = embedding_fn.encode_queries(["Who is Alan Turing?", "What is AI?"]) res = client.search( collection_name="demo_collection", # target collection data=query_vectors, # a list of one or more query vectors, supports batch limit=2, # how many results to return (topK) output_fields=["vector", "text", "subject"], # what fields to return ) ``` ## Why Milvus Milvus is designed to handle vector search at scale. It stores vectors, which are learned representations of unstructured data, together with other scalar data types such as integers, strings, and JSON objects. Users can conduct efficient vector search with metadata filtering or hybrid search. Here are why developers choose Milvus as the vector database for AI applications: **High Performance at Scale and High Availability** * Milvus features a [distributed architecture](https://milvus.io/docs/architecture_overview.md ) that separates [compute](https://milvus.io/docs/data_processing.md#Data-query) and [storage](https://milvus.io/docs/data_processing.md#Data-insertion). Milvus can horizontally scale and adapt to diverse traffic patterns, achieving optimal performance by independently increasing query nodes for read-heavy workload and data node for write-heavy workload. The stateless microservices on K8s allow [quick recovery](https://milvus.io/docs/coordinator_ha.md#Coordinator-HA) from failure, ensuring high availability. The support for [replicas](https://milvus.io/docs/replica.md) further enhances fault tolerance and throughput by loading data segments on multiple query nodes. See [benchmark](https://zilliz.com/vector-database-benchmark-tool) for performance comparison. **Support for Various Vector Index Types and Hardware Acceleration** * Milvus separates the system and core vector search engine, allowing it to support all major vector index types that are optimized for different scenarios, including HNSW, IVF, FLAT (brute-force), SCANN, and DiskANN, with [quantization-based](https://milvus.io/docs/index.md?tab=floating#IVFPQ) variations and [mmap](https://milvus.io/docs/mmap.md). Milvus optimizes vector search for advanced features such as [metadata filtering](https://milvus.io/docs/scalar_index.md#Scalar-Index) and [range search](https://milvus.io/docs/single-vector-search.md#Range-search). Additionally, Milvus implements hardware acceleration to enhance vector search performance and supports GPU indexing, such as NVIDIA's [CAGRA](https://github.com/rapidsai/cuvs). **Flexible Multi-tenancy and Hot/Cold Storage** * Milvus supports [multi-tenancy](https://milvus.io/docs/multi_tenancy.md#Multi-tenancy-strategies) through isolation at database, collection, partition, or partition key level. The flexible strategies allow a single cluster to handle hundreds to millions of tenants, also ensures optimized search performance and flexible access control. Milvus enhances cost-effectiveness with hot/cold storage. Frequently accessed hot data can be stored in memory or on SSDs for better performance, while less-accessed cold data is kept on slower, cost-effective storage. This mechanism can significantly reduce costs while maintaining high performance for critical tasks. **Sparse Vector for Full Text Search and Hybrid Search** * In addition to semantic search through dense vector, Milvus also natively supports [full text search](https://milvus.io/docs/full-text-search.md) with BM25 as well as learned sparse embeddings such as SPLADE and BGE-M3. Users can store sparse vectors and dense vectors in the same collection, and define functions to rerank results from multiple search requests. See examples of [Hybrid Search with semantic search + full text search](https://milvus.io/docs/full_text_search_with_milvus.md). **Data Security and Fine-grain Access Control** * Milvus ensures data security by implementing mandatory user authentication, TLS encryption, and Role-Based Access Control (RBAC). User authentication ensures that only authorized users with valid credentials can access the database, while TLS encryption secures all communications within the network. Additionally, RBAC allows for fine-grained access control by assigning specific permissions to users based on their roles. These features make Milvus a robust and secure choice for enterprise applications, protecting sensitive data from unauthorized access and potential breaches. Milvus is trusted by AI developers to build applications such as text and image search, Retrieval-Augmented Generation (RAG), and recommendation systems. Milvus powers [many mission-critical businesses](https://milvus.io/use-cases) for startups and enterprises. ## Demos and Tutorials Here is a selection of demos and tutorials to show how to build various types of AI applications made with Milvus: You can explore a comprehensive [Tutorials Overview](https://milvus.io/docs/tutorials-overview.md) covering topics such as Retrieval-Augmented Generation (RAG), Semantic Search, Hybrid Search, Question Answering, Recommendation Systems, and various quick-start guides. These resources are designed to help you get started quickly and efficiently. | Tutorial | Use Case | Related Milvus Features | | -------- | -------- | --------- | | [Build RAG with Milvus](https://milvus.io/docs/build-rag-with-milvus.md) | RAG | vector search | | [Advanced RAG Optimizations](https://milvus.io/docs/how_to_enhance_your_rag.md) | RAG | vector search, full text search | | [Full Text Search with Milvus](https://milvus.io/docs/full_text_search_with_milvus.md) | Text Search | full text search | | [Hybrid Search with Milvus](https://milvus.io/docs/hybrid_search_with_milvus.md) | Hybrid Search | hybrid search, multi vector, dense embedding, sparse embedding | | [Image Search with Milvus](https://milvus.io/docs/image_similarity_search.md) | Semantic Search | vector search, dynamic field | | [Multimodal Search using Multi Vectors](https://milvus.io/docs/multimodal_rag_with_milvus.md) | Semantic Search | multi vector, hybrid search | | [Movie Recommendation with Milvus](https://milvus.io/docs/movie_recommendation_with_milvus.md) | Recommendation System | vector search | | [Graph RAG with Milvus](https://milvus.io/docs/graph_rag_with_milvus.md) | RAG | graph search | | [Contextual Retrieval with Milvus](https://milvus.io/docs/contextual_retrieval_with_milvus.md) | Quickstart | vector search | | [Vector Visualization](https://milvus.io/docs/vector_visualization.md) | Quickstart | vector search | | [HDBSCAN Clustering with Milvus](https://milvus.io/docs/hdbscan_clustering_with_milvus.md) | Quickstart | vector search | | [Use ColPali for Multi-Modal Retrieval with Milvus](https://milvus.io/docs/use_ColPali_with_milvus.md) | Quickstart | vector search | | | | | | --- | --- | --- | | [Image Search](https://milvus.io/milvus-demos) | [RAG](https://milvus.io/milvus-demos) | [Drug Discovery](https://milvus.io/milvus-demos) | ## Ecosystem and Integration Milvus integrates with a comprehensive suite of [AI development tools](https://milvus.io/docs/integrations_overview.md), such as LangChain, LlamaIndex, OpenAI and HuggingFace, making it an ideal vector store for GenAI applications such as Retrieval-Augmented Generation (RAG). Milvus works with both open-source embedding models and embedding services, in text, image and video modalities. Milvus also provides a convenient utility [`pymilvus[model]`](https://milvus.io/docs/embeddings.md), users can use the simple wrapper code to transform unstructured data into vector embeddings and leverage reranking models for optimized search results. The Milvus ecosystem also includes [Attu](https://github.com/zilliztech/attu?tab=readme-ov-file#attu) for GUI-based administration, [Birdwatcher](https://milvus.io/docs/birdwatcher_overview.md) for system debugging, [Prometheus/Grafana](https://milvus.io/docs/monitor_overview.md) for monitoring, [Milvus CDC](https://milvus.io/docs/milvus-cdc-overview.md) for data synchronization, [VTS](https://github.com/zilliztech/vts?tab=readme-ov-file#vts) for data migration and data connectors for [Spark](https://milvus.io/docs/integrate_with_spark.md#Spark-Milvus-Connector-User-Guide), [Kafka](https://github.com/zilliztech/kafka-connect-milvus?tab=readme-ov-file#kafka-connect-milvus-connector), [Fivetran](https://fivetran.com/docs/destinations/milvus), and [Airbyte](https://milvus.io/docs/integrate_with_airbyte.md) to build search pipelines. Check out https://milvus.io/docs/integrations_overview.md for more details. ## Documentation For guidance on installation, usage, deployment, and administration, check out [Milvus Docs](https://milvus.io/docs). For technical milestones and enhancement proposals, check out [issues on GitHub](https://github.com/milvus-io/milvus/issues). ## Contributing The Milvus open-source project accepts contributions from everyone. See [Guidelines for Contributing](https://github.com/milvus-io/milvus/blob/master/CONTRIBUTING.md) for details on submitting patches and the development workflow. See our [community repository](https://github.com/milvus-io/community) to learn about project governance and access more community resources. ### Build Milvus from Source Code Requirements: * Linux systems (Ubuntu 20.04 or later recommended): ```bash Go: >= 1.21 CMake: >= 3.26.4 && CMake < 4 GCC: >= 11 Python: > 3.8 and <= 3.11 ``` * MacOS systems with x86_64 (Big Sur 11.5 or later recommended): ```bash Go: >= 1.21 CMake: >= 3.26.4 && CMake < 4 llvm: >= 15 Python: > 3.8 and <= 3.11 ``` * MacOS systems with Apple Silicon (Monterey 12.0.1 or later recommended): ```bash Go: >= 1.21 (Arch=ARM64) CMake: >= 3.26.4 && CMake < 4 llvm: >= 15 Python: > 3.8 and <= 3.11 ``` Clone Milvus repo and build. ```bash # Clone github repository. $ git clone https://github.com/milvus-io/milvus.git # Install third-party dependencies. $ cd milvus/ $ ./scripts/install_deps.sh # Compile Milvus. $ make ``` For full instructions, see [developer's documentation](https://github.com/milvus-io/milvus/blob/master/DEVELOPMENT.md). ## Community Join the Milvus community on [Discord](https://discord.gg/8uyFbECzPX) to share your suggestions, advice, and questions with our engineering team. To learn the latest news about Milvus, follow us on social media: - [X](https://twitter.com/milvusio) - [LinkedIn](https://www.linkedin.com/company/the-milvus-project) - [YouTube](https://www.youtube.com/channel/UCMCo_F7pKjMHBlfyxwOPw-g) - [Medium](https://medium.com/@milvusio) You can also check out our [FAQ page](https://milvus.io/docs/performance_faq.md) to discover solutions or answers to your issues or questions, and subscribe to Milvus mailing lists: - [Technical Steering Committee](https://lists.lfai.foundation/g/milvus-tsc) - [Technical Discussions](https://lists.lfai.foundation/g/milvus-technical-discuss) - [Announcement](https://lists.lfai.foundation/g/milvus-announce) ## Reference Reference to cite when you use Milvus in a research paper: ``` @inproceedings{2021milvus, title={Milvus: A Purpose-Built Vector Data Management System}, author={Wang, Jianguo and Yi, Xiaomeng and Guo, Rentong and Jin, Hai and Xu, Peng and Li, Shengjun and Wang, Xiangyu and Guo, Xiangzhou and Li, Chengming and Xu, Xiaohai and others}, booktitle={Proceedings of the 2021 International Conference on Management of Data}, pages={2614--2627}, year={2021} } @article{2022manu, title={Manu: a cloud native vector database management system}, author={Guo, Rentong and Luan, Xiaofan and Xiang, Long and Yan, Xiao and Yi, Xiaomeng and Luo, Jigao and Cheng, Qianya and Xu, Weizhi and Luo, Jiarui and Liu, Frank and others}, journal={Proceedings of the VLDB Endowment}, volume={15}, number={12}, pages={3548--3561}, year={2022}, publisher={VLDB Endowment} } ``` [](https://github.com/0xflotus) [](https://github.com/404-P4rziv4L) [](https://github.com/9Eurydice9) [](https://github.com/ABNER-1) [](https://github.com/Accagain2014) [](https://github.com/AgNess-G) [](https://github.com/Ahmetyasin) [](https://github.com/Ald392) [](https://github.com/AliDotS) [](https://github.com/AlintaLu) [](https://github.com/AllenYu1987) [](https://github.com/Anosh21) [](https://github.com/AnthonyTsu1984) [](https://github.com/Aredcap) [](https://github.com/ArenaSu) [](https://github.com/Armaggheddon) [](https://github.com/BUPTAnderson) [](https://github.com/Ben-Aaron-Bio-Rad) [](https://github.com/Bennu-Li) [](https://github.com/Biki-das) [](https://github.com/BossZou) [](https://github.com/CNLHC) [](https://github.com/CaoHaiNam) [](https://github.com/ChelseyZ) [](https://github.com/Chisdo) [](https://github.com/ChunelFeng) [](https://github.com/CocytusElias) [](https://github.com/CodeInDreams) [](https://github.com/Cplus-plus) [](https://github.com/CsterKuroi) [](https://github.com/Cupchen) [](https://github.com/DLT1412) [](https://github.com/DanielHuang1983) [](https://github.com/Deep1Shikha) [](https://github.com/DingQK) [](https://github.com/DiptoChakrabarty) [](https://github.com/EricStarer) [](https://github.com/Erzangel) [](https://github.com/FeilongHou) [](https://github.com/Fierralin) [](https://github.com/FluorineDog) [](https://github.com/Gofastasf) [](https://github.com/Goodnight77) [](https://github.com/Gracieeea) [](https://github.com/GuanyunFeng) [](https://github.com/GuoRentong) [](https://github.com/GuyKh) [](https://github.com/Hard-Coder05) [](https://github.com/Heisenberg-Y) [](https://github.com/HesterG) [](https://github.com/Hoyaspark) [](https://github.com/HuaSheng2000) [](https://github.com/HuangHua) [](https://github.com/HurSungYun) [](https://github.com/Ice-YcY) [](https://github.com/JackLCL) [](https://github.com/JadeFlute0127) [](https://github.com/Janglearnstocode) [](https://github.com/Javajava1) [](https://github.com/Jeri-jose) [](https://github.com/JianPeng20) [](https://github.com/JinHai-CN) [](https://github.com/JsDove) [](https://github.com/Juneezee) [](https://github.com/KubrickLiu) [](https://github.com/KumaJie) [](https://github.com/LeoReeYang) [](https://github.com/Leslie-Wong-H) [](https://github.com/Light-City) [](https://github.com/Lin-gh-Saint) [](https://github.com/Linkwei) [](https://github.com/LionelDong) [](https://github.com/LocoRichard) [](https://github.com/LoveEachDay) [](https://github.com/MrPresent-Han) [](https://github.com/NavanshGoel) [](https://github.com/NicoYuan1986) [](https://github.com/NotRyan) [](https://github.com/OxalisCu) [](https://github.com/PahudPlus) [](https://github.com/PiercarloSlavazza) [](https://github.com/PowderLi) [](https://github.com/QipengZhou) [](https://github.com/RangerCD) [](https://github.com/Raysilience) [](https://github.com/Reidddddd) [](https://github.com/ReigenAraka) [](https://github.com/Rijin-N) [](https://github.com/RosieZhang12) [](https://github.com/RyanWei) [](https://github.com/SCKCZJ2018) [](https://github.com/SarthakJain26) [](https://github.com/Shawnzheng011019) [](https://github.com/SimFG) [](https://github.com/SkyYang) [](https://github.com/SnowyOwl-KHY) [](https://github.com/SpadeA-Tang) [](https://github.com/Sunt-ing) [](https://github.com/SwaggySong) [](https://github.com/TheShubhendra) [](https://github.com/Thor-ChenBiao) [](https://github.com/ThreadDao) [](https://github.com/ThyeeZz) [](https://github.com/Tlincy) [](https://github.com/Tumao727) [](https://github.com/UnyieldingOrca) [](https://github.com/Writer-X) [](https://github.com/Writtic) [](https://github.com/Wuzhengda55) [](https://github.com/XTxxxx) [](https://github.com/Xieql) [](https://github.com/XuPeng-SH) [](https://github.com/XuanYang-cn) [](https://github.com/YannFollet) [](https://github.com/YidaHu) [](https://github.com/Yinwei-Yu) [](https://github.com/YiyunNi) [](https://github.com/Yougigun) [](https://github.com/Yukikaze-CZR) [](https://github.com/Zach41) [](https://github.com/ZhaoBQ) [](https://github.com/aaronjin2010) [](https://github.com/abd-770) [](https://github.com/akihoni) [](https://github.com/alexanderguzhva) [](https://github.com/alwayslove2013) [](https://github.com/anchun) [](https://github.com/andrii-shchur) [](https://github.com/any35) [](https://github.com/aoiasd) [](https://github.com/arijit-chowdhury-genea) [](https://github.com/ashkrisk) [](https://github.com/ashyshyshyman) [](https://github.com/avats-dev) [](https://github.com/avsolatorio) [](https://github.com/balloon1995) [](https://github.com/become-nice) [](https://github.com/bigsheeper) [](https://github.com/binbin12580) [](https://github.com/binbinlv) [](https://github.com/bjzhjing) [](https://github.com/bo-huang) [](https://github.com/brandonbiggs) [](https://github.com/brcarry) [](https://github.com/brunocfnba) [](https://github.com/bryanwux) [](https://github.com/caesarjuly) [](https://github.com/caosiyang) [](https://github.com/carawaylj) [](https://github.com/charleskakumanu) [](https://github.com/charlspjohn) [](https://github.com/chasingegg) [](https://github.com/chengpu) [](https://github.com/chenxingqiang) [](https://github.com/chinamcafee) [](https://github.com/chuangfengwang) [](https://github.com/chyezh) [](https://github.com/cjrh) [](https://github.com/claireyuw) [](https://github.com/codacy-badger) [](https://github.com/codenoid) [](https://github.com/codingjaguar) [](https://github.com/congqixia) [](https://github.com/corest) [](https://github.com/counter2015) [](https://github.com/cqy123456) [](https://github.com/cuishuang) [](https://github.com/cxie) [](https://github.com/cxytz01) [](https://github.com/cydrain) [](https://github.com/czpmango) [](https://github.com/czs007) [](https://github.com/dandv) [](https://github.com/dariocurr) [](https://github.com/datenhahn) [](https://github.com/dd-He) [](https://github.com/dddddai) [](https://github.com/del-zhenwu) [](https://github.com/dengxiaohai) [](https://github.com/disflyer) [](https://github.com/divyaruhil) [](https://github.com/donno2048) [](https://github.com/drow931) [](https://github.com/dvzubarev) [](https://github.com/dyhyfu) [](https://github.com/eddumelendez) [](https://github.com/ehooi) [](https://github.com/elfisworking) [](https://github.com/eli-b) [](https://github.com/elstic) [](https://github.com/eltociear) [](https://github.com/emmanuel-ferdman) [](https://github.com/eolivelli) [](https://github.com/erdustiggen) [](https://github.com/feisiyicl) [](https://github.com/fengjun2016) [](https://github.com/filip-halt) [](https://github.com/filipecaixeta) [](https://github.com/fishpenguin) [](https://github.com/forsaken628) [](https://github.com/foxspy) [](https://github.com/franciscojavierarceo) [](https://github.com/freestsoul) [](https://github.com/gcmutator) [](https://github.com/ggaaooppeenngg) [](https://github.com/gifi-siby) [](https://github.com/git-hulk) [](https://github.com/godchen0212) [](https://github.com/gracezzzzz) [](https://github.com/grtoverflow) [](https://github.com/gruebel) [](https://github.com/guimou) [](https://github.com/gujun720) [](https://github.com/guoxiangzhou) [](https://github.com/hadim) [](https://github.com/haorenfsa) [](https://github.com/hedane) [](https://github.com/henryoswald) [](https://github.com/hishope) [](https://github.com/huanghaoyuanhhy) [](https://github.com/huangjincheng2022) [](https://github.com/ibrahimhaddad) [](https://github.com/im-ajaymeena) [](https://github.com/ireneontheway5) [](https://github.com/iynewz) [](https://github.com/izapolsk) [](https://github.com/jackyu2020) [](https://github.com/jaelgu) [](https://github.com/jaime0815) [](https://github.com/jeffoverflow) [](https://github.com/jenkoon) [](https://github.com/jennyli-z) [](https://github.com/jfwm2) [](https://github.com/jhonroxton) [](https://github.com/jiangke-sr) [](https://github.com/jiangyinzuo) [](https://github.com/jiaoew1991) [](https://github.com/jiaqizho) [](https://github.com/jielinxu) [](https://github.com/jingkl) [](https://github.com/jjaikumar-xyla) [](https://github.com/jjyaoao) [](https://github.com/jkx8fc) [](https://github.com/joeyjooste) [](https://github.com/john-h-luo) [](https://github.com/jperez999) [](https://github.com/juliens) [](https://github.com/junjiejiangjjj) [](https://github.com/jvirgovic) [](https://github.com/jyc4617) [](https://github.com/kartikcho) [](https://github.com/kateshaowanjou) [](https://github.com/klboke) [](https://github.com/laipz8200) [](https://github.com/laurazhao0611) [](https://github.com/lee-eve) [](https://github.com/lee-taejun) [](https://github.com/lentitude2tk) [](https://github.com/leonardokidd) [](https://github.com/letian-jiang) [](https://github.com/letme5) [](https://github.com/leykun10) [](https://github.com/lhotari) [](https://github.com/liliu-z) [](https://github.com/linhgao) [](https://github.com/liyun95) [](https://github.com/lmzzzzz1) [](https://github.com/locustbaby) [](https://github.com/loguo) [](https://github.com/longjiquan) [](https://github.com/lowener) [](https://github.com/lsgrep) [](https://github.com/lwglgy) [](https://github.com/madogar) [](https://github.com/maksspace) [](https://github.com/marcelo-cjl) [](https://github.com/matchyc) [](https://github.com/matrixji) [](https://github.com/mausch) [](https://github.com/mcamou) [](https://github.com/michaelkl) [](https://github.com/mihailyanchev) [](https://github.com/mileyzjq) [](https://github.com/milvus-ci-robot) [](https://github.com/mimoning) [](https://github.com/moe-of-faith) [](https://github.com/mohitreddy1996) [](https://github.com/nameczz) [](https://github.com/natoka) [](https://github.com/ncover21) [](https://github.com/nexttonever) [](https://github.com/neza2017) [](https://github.com/nianliuu) [](https://github.com/nish112022) [](https://github.com/nustiueudinastea) [](https://github.com/op-hunter) [](https://github.com/ownbylichaobao) [](https://github.com/panjf2000) [](https://github.com/phantom8548) [](https://github.com/pingliu) [](https://github.com/pj1987111) [](https://github.com/ponponon) [](https://github.com/preetham) [](https://github.com/proost) [](https://github.com/psc0606) [](https://github.com/punkerpunker) [](https://github.com/qbzenker) [](https://github.com/qixuan0212) [](https://github.com/rahulmistri1997) [](https://github.com/rashgaroth) [](https://github.com/richzw) [](https://github.com/ronnie-llamado) [](https://github.com/sachitolani) [](https://github.com/sageanya) [](https://github.com/saisona) [](https://github.com/saivarunk) [](https://github.com/sangheee) [](https://github.com/sarah-inkeep) [](https://github.com/scipe) [](https://github.com/scsven) [](https://github.com/seo-jinBro) [](https://github.com/septemberfd) [](https://github.com/shana0325) [](https://github.com/shanghaikid) [](https://github.com/shaoting-huang) [](https://github.com/shengjh) [](https://github.com/shengjun1985) [](https://github.com/shiyu09) [](https://github.com/shiyu22) [](https://github.com/shunjiezhao) [](https://github.com/siddarth99) [](https://github.com/sileht) [](https://github.com/simonwei97) [](https://github.com/siriusctrl) [](https://github.com/slobentanzer) [](https://github.com/smackfu) [](https://github.com/smdsbz) [](https://github.com/smellthemoon) [](https://github.com/snyk-bot) [](https://github.com/songxianj) [](https://github.com/soothing-rain) [](https://github.com/soulteary) [](https://github.com/sparknack) [](https://github.com/sre-ci-robot) [](https://github.com/sre-ro) [](https://github.com/sreyan-ghosh) [](https://github.com/ss892714028) [](https://github.com/stacyli-0601) [](https://github.com/stephen37) [](https://github.com/stevetracvc) [](https://github.com/stuartjing) [](https://github.com/sunby) [](https://github.com/sutcalag) [](https://github.com/sworddish) [](https://github.com/talentAN) [](https://github.com/tasty-gumi) [](https://github.com/taydy) [](https://github.com/tbickford) [](https://github.com/tedxu) [](https://github.com/tedyu) [](https://github.com/testwill) [](https://github.com/thywdy) [](https://github.com/timothycarambat) [](https://github.com/tinkerlin) [](https://github.com/tinswzy) [](https://github.com/topikachu) [](https://github.com/trovwu) [](https://github.com/tsonglew) [](https://github.com/tuwchia) [](https://github.com/ulovecode) [](https://github.com/uncle-cyh) [](https://github.com/unfode) [](https://github.com/vladwa) [](https://github.com/vsanna) [](https://github.com/vtereshyn) [](https://github.com/wangting0128) [](https://github.com/water32) [](https://github.com/wayblink) [](https://github.com/weiliu1031) [](https://github.com/weishuo2) [](https://github.com/wg1026688210) [](https://github.com/wh201906) [](https://github.com/wscxyey) [](https://github.com/wwx441476) [](https://github.com/wxyucs) [](https://github.com/wxywb) [](https://github.com/wzymumon) [](https://github.com/xaxys) [](https://github.com/xiangzhouguo) [](https://github.com/xiaocai2333) [](https://github.com/xiaofan-luan) [](https://github.com/xiaohu4313888) [](https://github.com/xiaowshi) [](https://github.com/xiedeyantu) [](https://github.com/xige-16) [](https://github.com/xiyichan) [](https://github.com/xlyslr) [](https://github.com/xudalin0609) [](https://github.com/xuqiwe) [](https://github.com/xzshinan) [](https://github.com/yah01) [](https://github.com/yahorbarkouski) [](https://github.com/yamasite) [](https://github.com/yanbinyang) [](https://github.com/yanliang567) [](https://github.com/yellow-shine) [](https://github.com/yelusion2) [](https://github.com/yhmo) [](https://github.com/yiuluchen) [](https://github.com/yiwangdr) [](https://github.com/yiwen92) [](https://github.com/yongpengli-z) [](https://github.com/youny626) [](https://github.com/yuyicai) [](https://github.com/yxm1536) [](https://github.com/zander-bobronnikov) [](https://github.com/zc2638) [](https://github.com/zc277584121) [](https://github.com/zengxy) [](https://github.com/zerowe-seven) [](https://github.com/zhagnlu) [](https://github.com/zhang787jun) [](https://github.com/zhanshuyou) [](https://github.com/zhanxu33) [](https://github.com/zhengbuqian) [](https://github.com/zhenwu-cn) [](https://github.com/zhikunyao) [](https://github.com/zhoubo0317) [](https://github.com/zhuwenxing) [](https://github.com/zhuyaguang) [](https://github.com/zjjzyl) [](https://github.com/zxf2017) --- ## File: docs/README.md # Milvus repository documentation This directory contains documentation that must stay close to the Milvus source tree. Public product documentation belongs in the [`milvus-io/milvus-docs`](https://github.com/milvus-io/milvus-docs) repository. ## Directory map | Path | Purpose | Status | | --- | --- | --- | | [`agent_guides/`](agent_guides/) | Code-backed subsystem architecture, invariants, and debugging guidance | Current | | [`dev/`](dev/) | Contributor-facing engineering rules and development procedures | Current | | [`design-docs/`](design-docs/) | Design records and their supporting assets | Current and historical | | [`archive/`](archive/) | Superseded documentation retained for historical context | Historical, non-normative | Documentation that belongs to one component may remain next to that component. Other repository-wide documentation should use one of the directories above. ## 2. Official Technical Reference & Guides (milvus-io/milvus-docs) ## File: README.md # Milvus Documentation Welcome to Milvus documentation! This repository contains technical documentation for [Milvus](https://github.com/milvus-io/milvus), the world's most advanced open-source vector database. Visit [Milvus.io](https://milvus.io/docs) or [Web content repo](https://github.com/milvus-io/web-content) for fully rendered documents. Each branch corresponds to a Milvus release by name. We've set the branch of the latest Milvus release as the default branch. For documentation of a different Milvus release, switch to the corresponding branch. ## Index - [Suggest changes](#suggest-changes) - [Contribute to Milvus docs](#contribute-to-milvus-docs) - [Active Milvus releases](#active-milvus-releases) - [Other contributing channels](#other-contributing-channels) - [Reference](#reference) - [Get in touch](#get-in-touch) ## Suggest changes Have a new topic that you want to include in the docs? Need additional instructions or clarifications? Spot a broken link? Please [open an issue](https://github.com/milvus-io/milvus-docs/issues/new/choose). ## Contribute to Milvus docs Want to be a contributor to the docs? See [CONTRIBUTING](CONTRIBUTING.md) for details about setting yourself up and getting started. ## Active Milvus releases Currently, we are maintaining the following versions of Milvus documentation in different branches: | `v2.1.x` branch | 2.1.x version (the default and latest branch) | | --------------- | --------------------------------------------- | | `v2.0.x` branch | 2.0.x version | | `v1.1.1` branch | 1.1.1 version | | `v1.1.0` branch | 1.1.0 version | | `v1.0.0` branch | 1.0.0 version (first with long-term support) | > **Note:** > The latest branch is set as the default working branch. > Milvus releases prior to v1.0.0 are no longer supported, but you can still find their documentation in the corresponding branch. ## Other contributing channels Not all content rendered on [milvus.io](https://milvus.io/docs) is hosted in this repository. ### Contribute to API docs To contribute to the Milvus SDK documentation, visit the language-specific repositories listed below: - [PyMilvus](https://github.com/milvus-io/pymilvus) - [GO](https://github.com/milvus-io/milvus-sdk-go) - [Java](https://github.com/milvus-io/milvus-sdk-java) - [Node.js](https://github.com/milvus-io/milvus-sdk-node) ### Contribute to community content If you would like to write an article for our [blog](https://medium.com/unstructured-data-service), please [file an issue](https://github.com/milvus-io/community/issues/new) in the [Milvus community repository](https://github.com/milvus-io/community) or contact community@zilliz.com. Feel free to submit either a completed draft or article ideas. All submissions will be reviewed as quickly as possible. If your article or idea seems like a good fit for our blog, we will reach out to you directly. > In your title/subject line, please put in [blog submission] to make sure your email does not get buried. ## Reference Reference to cite when you use Milvus in a research paper: ``` @inproceedings{2021milvus, title={Milvus: A Purpose-Built Vector Data Management System}, author={Wang, Jianguo and Yi, Xiaomeng and Guo, Rentong and Jin, Hai and Xu, Peng and Li, Shengjun and Wang, Xiangyu and Guo, Xiangzhou and Li, Chengming and Xu, Xiaohai and others}, booktitle={Proceedings of the 2021 International Conference on Management of Data}, pages={2614--2627}, year={2021} } ``` ## Get in touch Join the Milvus community on [Discord](https://discord.com/invite/8uyFbECzPX) to share your suggestions, advice, or questions with our engineering team. Subscribe to Milvus's mailing lists: - [Technical Steering Committee](https://lists.lfai.foundation/g/milvus-tsc) - [Technical Discussions](https://lists.lfai.foundation/g/milvus-technical-discuss) - [Announcement](https://lists.lfai.foundation/g/milvus-announce) Follow Milvus on social media: - [Medium](https://medium.com/@milvusio) - [Twitter](https://twitter.com/milvusio) - [LinkedIn](https://www.linkedin.com/company/the-milvus-project) --- ## File: site/zh-CN/getstarted/README.md # Milvus 用户手册 - 快速入门 - 安装 Milvus - [安装概述](get_started/install_milvus/install_milvus.md) - [安装 CPU 版 Milvus](get_started/install_milvus/cpu_milvus_docker.md) - [安装 GPU 版 Milvus](get_started/install_milvus/gpu_milvus_docker.md) - [运行示例程序](get_started/example_code.md) - [了解 Milvus 操作](milvus_operation.md) - [选择距离计算方式](metric.md) - [索引类型](index.md) - [监控与报警](monitor.md) - [故障诊断](troubleshoot.md) --- ## File: site/zh-CN/about/README.md # 向量数据库简介 - [Milvus Overview](overview.md) - [Feature Vector](vector.md) - [Traditional Database](traditional_db.md) - [Vector Indexing Methods](index_method.md) - [Feature Vector Database](vector_db.md) --- ## File: site/en/getstarted/README.md # Milvus User Guide - Get Started - Install Milvus - [Installation Overview](get_started/install_milvus/install_milvus.md) - [Install CPU-only Milvus](get_started/install_milvus/cpu_milvus_docker.md) - [Install GPU-enabled Milvus](get_started/install_milvus/gpu_milvus_docker.md) - [Try an Example Program](get_started/example_code.md) - [Learn Milvus Operations](milvus_operation.md) - [Selecting Metrics](metric.md) - [Milvus indexes](index.md) - [Monitoring and Alerting](monitor.md) - [Troubleshoot](troubleshoot.md) --- ## File: site/en/about/README.md # About Milvus - [Milvus Overview](overview.md) - [Feature Vector](vector.md) - [Traditional Database](traditional_db.md) - [Vector Search Methods](index_method.md) - [Other Feature Vector Search Tools](vector_db.md)