milvus Documentation

Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search

45,617 stars Go Go 1 file ยท ~9,197 tokens #anns#cloud-native#diskann#distributed#embedding-database#embedding-similarity#embedding-store#faiss
RAW Doc

Docker & Self-Hosted Deployment Verified OCI

Deploy milvus on any server, homelab, or cloud container platform.

1-Click Terminal Command
bash (docker run) 
docker run -d --name milvus -p 4443:4443 --restart always milvusdb/etcd:3.5.5-r2
Configured Services & Ports
โš™๏ธ builder
image: ${IMAGE_REPO}/milvus-env:${OS_NAME}-${DATE_VERSION}
โš™๏ธ gpubuilder
image: ${IMAGE_REPO}/milvus-env:gpu-${OS_NAME}-${GPU_DATE_VERSION}
โš™๏ธ etcd
image: milvusdb/etcd:3.5.5-r2
โš™๏ธ pulsar
image: apachepulsar/pulsar:2.8.2
โš™๏ธ minio
image: milvusdb/minio:RELEASE.2024-12-18T13-15-44Z
โš™๏ธ azurite
image: mcr.microsoft.com/azure-storage/azurite
โš™๏ธ jaeger
image: jaegertracing/all-in-one:latest
โš™๏ธ gcpnative
image: fsouza/fake-gcs-server
๐Ÿ”Œ Ports: 4443:4443
docker-compose.yml
yaml (docker-compose.yml) 
version: '3.5'

x-ccache: &ccache
  CCACHE_COMPILERCHECK: content
  CCACHE_COMPRESS: 1
  CCACHE_COMPRESSLEVEL: 5
  CCACHE_MAXSIZE: 2G
  CCACHE_DIR: /ccache

services:
  builder:
    image: ${IMAGE_REPO}/milvus-env:${OS_NAME}-${DATE_VERSION}
    # Build devcontainer
    build:
      context: .
      dockerfile: build/docker/builder/cpu/${OS_NAME}/Dockerfile
      args:
        TARGETARCH: ${IMAGE_ARCH}
      cache_from:
        - ${IMAGE_REPO}/milvus-env:${OS_NAME}-${LATEST_DATE_VERSION}
    platform: linux/${IMAGE_ARCH}
    shm_size: 2G
    # expose 19530 port so we can directly access milvus inside build container
    # ports:
    #  - "19530:19530"
    environment:
      <<: *ccache
      OS_NAME: ${OS_NAME}
      PULSAR_ADDRESS: ${PULSAR_ADDRESS}
      ETCD_ENDPOINTS: ${ETCD_ENDPOINTS}
      MINIO_ADDRESS: ${MINIO_ADDRESS}
      CONAN_HOME: /home/milvus/.conan2
      AZURE_STORAGE_CONNECTION_STRING: ${AZURITE_CONNECTION_STRING}
      ENABLE_GCP_NATIVE: ${ENABLE_GCP_NATIVE}
      USE_ASAN: ${USE_ASAN}
    volumes: &builder-volumes
      - .:/go/src/github.com/milvus-io/milvus:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker}/${IMAGE_ARCH}-${OS_NAME}-ccache:/ccache:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker}/${IMAGE_ARCH}-${OS_NAME}-go-mod:/go/pkg/mod:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker}/${IMAGE_ARCH}-${OS_NAME}-vscode-extensions:/home/milvus/.vscode-server/extensions:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker}/${IMAGE_ARCH}-${OS_NAME}-conan2:/home/milvus/.conan2:delegated
    working_dir: '/go/src/github.com/milvus-io/milvus'
    depends_on:
      - etcd
      - minio
      - pulsar
      - azurite
      - gcpnative
    # Command
    command: &builder-command >
      /bin/bash -c "
        make check-proto-product && make verifiers && make unittest"

  gpubuilder:
    image: ${IMAGE_REPO}/milvus-env:gpu-${OS_NAME}-${GPU_DATE_VERSION}
    # Build devcontainer
    build:
      context: .
      dockerfile: build/docker/builder/gpu/${OS_NAME}/Dockerfile
      args:
        TARGETARCH: ${IMAGE_ARCH}
      cache_from:
        - ${IMAGE_REPO}/milvus-env:gpu-${OS_NAME}-${LATEST_GPU_DATE_VERSION}
    # user: {{ CURRENT_ID }}
    shm_size: 2G
    # expose 19530 port so we can directly access milvus inside build container
    # ports:
    #  - "19530:19530"
    environment:
      <<: *ccache
      OS_NAME: ${OS_NAME}
      PULSAR_ADDRESS: ${PULSAR_ADDRESS}
      ETCD_ENDPOINTS: ${ETCD_ENDPOINTS}
      MINIO_ADDRESS: ${MINIO_ADDRESS}
      CONAN_HOME: /home/milvus/.conan2
      AZURE_STORAGE_CONNECTION_STRING: ${AZURITE_CONNECTION_STRING}
      ENABLE_GCP_NATIVE: ${ENABLE_GCP_NATIVE}
    volumes: &builder-volumes-gpu
      - .:/go/src/github.com/milvus-io/milvus:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker-gpu}/${OS_NAME}-ccache:/ccache:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker-gpu}/${OS_NAME}-go-mod:/go/pkg/mod:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker-gpu}/${OS_NAME}-vscode-extensions:/home/milvus/.vscode-server/extensions:delegated
      - ${DOCKER_VOLUME_DIRECTORY:-.docker-gpu}/${OS_NAME}-conan2:/home/milvus/.conan2:delegated
    working_dir: '/go/src/github.com/milvus-io/milvus'
    depends_on:
      - etcd
      - minio
      - pulsar
      - azurite
      - gcpnative
    # Command
    command: &builder-command-gpu >
      /bin/bash -c "
        make check-proto-product && make verifiers && make unittest"

  etcd:
    image: milvusdb/etcd:3.5.5-r2
    environment:
      - ALLOW_NONE_AUTHENTICATION=yes
      - ETCD_AUTO_COMPACTION_MODE=revision
      - ETCD_AUTO_COMPACTION_RETENTION=1000
      - ETCD_QUOTA_BACKEND_BYTES=4294967296
      - ETCD_SNAPSHOT_COUNT=50000
    healthcheck:
      test: [ 'CMD', '/opt/bitnami/scripts/etcd/healthcheck.sh' ]
      interval: 30s
      timeout: 20s
      retries: 3

  pulsar:
    image: apachepulsar/pulsar:2.8.2
    command: |
      /bin/bash -c \
      "bin/apply-config-from-env.py conf/standalone.conf && \
      exec bin/pulsar standalone --no-functions-worker --no-stream-storage"
    environment:
      # 10MB
      - PULSAR_PREFIX_maxMessageSize=10485760
      # this is 104857600 + 10240 (padding)
      - nettyMaxFrameSizeBytes=104867840
      - PULSAR_GC=-XX:+UseG1GC

  minio:
    image: milvusdb/minio:RELEASE.2024-12-18T13-15-44Z
    environment:
      MINIO_ACCESS_KEY: minioadmin
      MINIO_SECRET_KEY: minioadmin
    command: minio server /minio_data
    healthcheck:
      test: [ 'CMD', 'mc', 'ready', 'local' ]
      interval: 30s
      timeout: 20s
      retries: 3

  azurite:
    image: mcr.microsoft.com/azure-storage/azurite
    command: azurite-blob --blobHost 0.0.0.0

  jaeger:
    image: jaegertracing/all-in-one:latest

  gcpnative:
    image: fsouza/fake-gcs-server
    command: -scheme http -public-host storage.gcs.127.0.0.1.nip.io:4443 -external-url "http://storage.gcs.127.0.0.1.nip.io:4443"
    hostname: storage.gcs.127.0.0.1.nip.io
    ports:
      - "4443:4443"

networks:
  default:
    name: milvus_dev

1. Project Overview & Quickstart (milvus-io/milvus)

File: README.md








What is Milvus?

๐Ÿฆ Milvus 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.

๐Ÿง‘โ€๐Ÿ’ป 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, 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 for single machine deployment. Milvus Lite is a lightweight version good for quickstart in python with pip install.

Want to use Milvus with zero setup? Try out Zilliz Cloud โ˜๏ธ for free. Milvus is available as a fully managed service on Zilliz Cloud, with Serverless, Dedicated and BYOC options available.

For questions about how to use Milvus, join the community on Discord to get help. For reporting problems, file bugs and feature requests in GitHub Issues or ask in Discussions.

The Milvus open-source project is
under LF AI & Data Foundation, distributed with Apache 2.0 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 or Zilliz Cloud:

    python
    client = MilvusClient(
  uri="<endpoint_of_self_hosted_milvus_or_zilliz_cloud>",
  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 that separates compute and storage. 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 from failure, ensuring high availability. The support for replicas further enhances fault tolerance and throughput by loading data segments on multiple query nodes. See benchmark 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 variations and mmap. Milvus optimizes vector search for advanced features such as metadata filtering and range search. Additionally, Milvus implements hardware acceleration to enhance vector search performance and supports GPU indexing, such as NVIDIA's CAGRA.

Flexible Multi-tenancy and Hot/Cold Storage

  • Milvus supports multi-tenancy 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 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.

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 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 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 RAG vector search
Advanced RAG Optimizations RAG vector search, full text search
Full Text Search with Milvus Text Search full text search
Hybrid Search with Milvus Hybrid Search hybrid search, multi vector, dense embedding, sparse embedding
Image Search with Milvus Semantic Search vector search, dynamic field
Multimodal Search using Multi Vectors Semantic Search multi vector, hybrid search
Movie Recommendation with Milvus Recommendation System vector search
Graph RAG with Milvus RAG graph search
Contextual Retrieval with Milvus Quickstart vector search
Vector Visualization Quickstart vector search
HDBSCAN Clustering with Milvus Quickstart vector search
Use ColPali for Multi-Modal Retrieval with Milvus Quickstart vector search
Image Search RAG Drug Discovery

Ecosystem and Integration

Milvus integrates with a comprehensive suite of AI development tools, 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], 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 for GUI-based administration, Birdwatcher for system debugging, Prometheus/Grafana for monitoring, Milvus CDC for data synchronization, VTS for data migration and data connectors for Spark, Kafka, Fivetran, and Airbyte 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. For technical milestones and enhancement proposals, check out issues on GitHub.

Contributing

The Milvus open-source project accepts contributions from everyone. See Guidelines for Contributing for details on submitting patches and the development workflow. See our community repository 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.

Community

Join the Milvus community on Discord to share your suggestions, advice, and questions with our engineering team.

To learn the latest news about Milvus, follow us on social media:

You can also check out our FAQ page to discover solutions or answers to your issues or questions, and subscribe to Milvus mailing lists:

Reference

Reference to cite when you use Milvus in a research paper:

text
@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}
}
















































































































































































































































































































































































































































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 repository.

Directory map

Path Purpose Status
agent_guides/ Code-backed subsystem architecture, invariants, and debugging guidance Current
dev/ Contributor-facing engineering rules and development procedures Current
design-docs/ Design records and their supporting assets Current and historical
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, the world's most advanced open-source vector database. Visit Milvus.io or Web content repo 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

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.

Contribute to Milvus docs

Want to be a contributor to the docs? See CONTRIBUTING 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 is hosted in this repository.

Contribute to API docs

To contribute to the Milvus SDK documentation, visit the language-specific repositories listed below:

Contribute to community content

If you would like to write an article for our blog, please file an issue in the Milvus community repository or contact [email protected]. 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:

text
@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 to share your suggestions, advice, or questions with our engineering team.

Subscribe to Milvus's mailing lists:

Follow Milvus on social media:

File: site/zh-CN/getstarted/README.md

Milvus ็”จๆˆทๆ‰‹ๅ†Œ

File: site/zh-CN/about/README.md

ๅ‘้‡ๆ•ฐๆฎๅบ“็ฎ€ไป‹

File: site/en/getstarted/README.md

Milvus User Guide

File: site/en/about/README.md

About Milvus

Explore Related Technologies & Topics

View All 9,111+ Repositories โ†’

Discover similar high-velocity repositories, agent skills, and OpenAPI specifications across the ecosystem.

#anns Browse anns catalog โ†’ #cloud-native Browse cloud-native catalog โ†’ #diskann Browse diskann catalog โ†’ #distributed Browse distributed catalog โ†’ #embedding-database Browse embedding-database catalog โ†’ #embedding-similarity Browse embedding-similarity catalog โ†’ โšก MCP Servers Model Context Protocol โ†’ ๐Ÿง  Agent Skills Prompt & rule files โ†’ ๐Ÿ”Œ OpenAPI Specs REST & Swagger schemas โ†’