9d5d49c95c
Signed-off-by: fluorinedog <fluorinedog@gmail.com> |
||
|---|---|---|
| .github | ||
| .jenkins/modules | ||
| .mergify | ||
| ci | ||
| core | ||
| deploy | ||
| docker | ||
| docs | ||
| sdk | ||
| shards | ||
| tests | ||
| .all-contributorsrc | ||
| .clang-format | ||
| .clang-tidy | ||
| .clang-tidy-ignore | ||
| .codacy.yaml | ||
| .codebeatignore | ||
| .env | ||
| .gitignore | ||
| .hadolint.yaml | ||
| CHANGELOG.md | ||
| CODEOWNERS | ||
| CODE_OF_CONDUCT.md | ||
| COMMUNITY.md | ||
| CONTRIBUTING.md | ||
| DESIGN.md | ||
| INSTALL.md | ||
| LICENSE | ||
| NOTICE.md | ||
| OSSMETADATA | ||
| README.md | ||
| README_CN.md | ||
| RELEASE.md | ||
| SECURITY.md | ||
| SUPPORT.md | ||
| codecov.yaml | ||
| docker-compose.yml | ||
README.md
Welcome to the world of Milvus
What is Milvus
Milvus is a vector similarity search engine that is highly flexible, reliable, and blazing fast. It supports adding, deleting, updating, and near-real-time search of embedding vectors on a scale of trillion bytes. By encapsulating multiple widely adopted index libraries, such as Faiss, NMSLIB, and Annoy, it provides a comprehensive set of intuitive APIs, allowing you to choose index types based on your scenario. By supporting the filtering of scalar data, Milvus takes the recall rate even higher and adds more flexibility to your search.
The Milvus architecture is as follows:
For a more detailed introduction of Milvus and its architecture, see Milvus overview. To keep up-to-date with its releases and updates, see Milvus release notes.
Milvus was released under the Apache 2.0 License and officially open sourced in October 2019. It is an incubation-stage project at LF AI & Data Foundation. The source code of Milvus is hosted on GitHub.
Get started
Install Milvus
- To install Milvus using Docker, see Milvus install guide
- To install Milvus from source code, see build from source.
Try example programs
You can use the following example code to try a Milvus example program:
Supported clients
Application scenarios
Milvus has been used by over 600 organizations and institutions worldwide mainly in the following scenarios:
- Image, video, and audio search.
- Text search, recommender system, interactive question answering system, and other text search fields.
- Drug discovery, genetic screening, and other biomedical fields.
See Scenarios for more detailed application scenarios and demos.
See Milvus Bootcamp for detailed solutions and application scenarios.
Benchmark
See our test reports for more information about performance benchmarking of different indexes in Milvus.
Roadmap
To learn what's coming up soon in Milvus, read our Roadmap.
It is a Work in Progress, and is subject to reasonable adjustments when necessary. We greatly appreciate any comments, requirements and suggestions on the Milvus roadmap.👏
Join our community
You are welcome to join our community. ❤️ We appreciate any contributions from you.
- For a detailed contribution workflow, see our contribution guidelines.
- All the contributors should follow the code of conduct of Milvus.
- To track issues and bugs, use GitHub issues.
- To connect with other users and contributors, welcome to join our Slack channel.
See our community repository to learn more about our governance and access more community resources.