Skip to content

Commit

Permalink
Merge pull request #211 from zilliztech/v.0.11.0_Update_CY
Browse files Browse the repository at this point in the history
v0.x taking off prior releases
  • Loading branch information
LocoRichard authored May 12, 2021
2 parents c25e817 + 7935749 commit c55f500
Show file tree
Hide file tree
Showing 190 changed files with 43 additions and 9,649 deletions.
1 change: 1 addition & 0 deletions milvus-docs
Submodule milvus-docs added at 745761
51 changes: 0 additions & 51 deletions site/en/about_milvus/milvus_distributions-cpu.md

This file was deleted.

59 changes: 0 additions & 59 deletions site/en/about_milvus/milvus_distributions-gpu.md

This file was deleted.

90 changes: 19 additions & 71 deletions site/en/about_milvus/overview.md
Original file line number Diff line number Diff line change
@@ -1,75 +1,23 @@
---
id: overview.md
keywords: Near-real-time search, Near real-time, NRT, Scalar field filtering, compound query
---

# What is Milvus

## Overview

Milvus is an embeddings similarity search engine that is highly flexible, reliable, and blazing fast. It supports adding, deleting, updating, and near-real-time search of embeddings 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 filtering of scalar data, Milvus takes the recall rate even higher and adds more flexibility to your search.


Milvus runs on the client-server model.

- The Milvus server comprises two parts: Milvus Core and Meta Store.

* Milvus Core stores and manages embeddings and scalar data.
* Meta Store stores and manages metadata in SQLite for testing or MySQL for production.

- On the client side, Milvus provides SDKs in Python, Java, Go, and C++, as well as RESTful APIs.

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](https://lfaidata.foundation/). The source code of Milvus is hosted on [GitHub](https://github.com/milvus-io/milvus).

## Overall architecture

![Milvus architecture](../../../assets/milvus_arch.png)


## Scenarios

Milvus has been used in hundreds of 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](https://www.milvus.io/scenarios/) for more information.

## Key features


#### Heterogeneous computing

- Optimizes search and indexing performance for GPU.
- Completes a search in milliseconds for datasets on a scale of trillion Bytes.
- Manages datasets in a dynamic environment.

#### Compatible with mainstream libraries, metrics, and tooling

- Encapsulates Faiss, NMSLIB, and Annoy libraries.
- Supports Quantization, Graph-based, and Tree-based indexes.
- Similarity metrics including Euclidean distance (L2), Inner Product, Hamming distance, Jaccard distance, and more.
- Prometheus and Grafana for monitoring and visualization of runtime metrics.

#### Near-real-time (NRT) search

- Inserted datasets are searchable in one second.

#### Scalar field filtering

- Supports embeddings and scalar data.
- Adds more flexibility to your search by supporting filtering of scalar data.

## Milvus distributions
<a name='distributions'></a>

{{fragments/distributions.md}}

For more information, see [Milvus Distributions](milvus_distributions-cpu.md).

## Join our community

Before joining our developer community, please take some time reading [our code contribution guidelines](https://github.com/milvus-io/milvus/blob/master/CONTRIBUTING.md#contributing-to-milvus).

If you have questions about functions or SDKs of Milvus, you can join our [GitHub Discussions](https://github.com/milvus-io/milvus/discussions) or [our Slack channel](https://join.slack.com/t/milvusio/shared_invite/zt-e0u4qu3k-bI2GDNys3ZqX1YCJ9OM~GQ).
# Prior Releases

The following prior releases are no longer supported. For detailed documentation, click the corresponding link:

- [v0.11.0](https://github.com/milvus-io/docs/tree/master/v0.11.0/site/en)
- [v0.10.6](https://github.com/milvus-io/docs/tree/master/v0.10.6/site/en)
- [v0.10.5](https://github.com/milvus-io/docs/tree/master/v0.10.5/site/en)
- [v0.10.4](https://github.com/milvus-io/docs/tree/master/v0.10.4/site/en)
- [v0.10.3](https://github.com/milvus-io/docs/tree/master/v0.10.3/site/en)
- [v0.10.2](https://github.com/milvus-io/docs/tree/master/v0.10.2/site/en)
- [v0.10.1](https://github.com/milvus-io/docs/tree/master/v0.10.1/site/en)
- [v0.10.0](https://github.com/milvus-io/docs/tree/master/v0.10.0/site/en)
- [v0.9.1](https://github.com/milvus-io/docs/tree/master/v0.9.1/site/en)
- [v0.9.0](https://github.com/milvus-io/docs/tree/master/v0.9.0/site/en)
- [v0.8.1](https://github.com/milvus-io/docs/tree/master/v0.8.1/site/en)
- [v0.8.0](https://github.com/milvus-io/docs/tree/master/v0.8.0/site/en)
- [v0.7.1](https://github.com/milvus-io/docs/tree/master/v0.7.1/site/en)
- [v0.7.0](https://github.com/milvus-io/docs/tree/master/v0.7.0/site/en)
- [v0.6.0](https://github.com/milvus-io/docs/tree/master/v0.6.0/site/en)
11 changes: 0 additions & 11 deletions site/en/deverloperTools/dt_overview.md

This file was deleted.

132 changes: 0 additions & 132 deletions site/en/faq/operational_faq.md

This file was deleted.

Loading

0 comments on commit c55f500

Please sign in to comment.