Skip to content

M
milvus

milvus / milvus
10 个月 前同步成功

通知 260
Star 22476
Fork 2472
M
milvus

前往新版Gitcode，体验更适合开发者的 AI 搜索 >>

未验证 提交 deb937a1 编写于 作者: L LocoRichard 提交者： GitHub
浏览文件
操作

[skip ci] update readme (#5833) 

* [skip ci] update readme
Signed-off-by: NLocoRichard <lichen.wang@zilliz.com>

* [skip ci] update readme
Signed-off-by: NLocoRichard <lichen.wang@zilliz.com>
上级 8912fe5c
隐藏空白更改
内联 并排
Showing with 388 addition and 138 deletion
README.md
浏览文件 @ deb937a1
......@@ -11,6 +11,7 @@
</div>
<div class="column" align="middle">
<a href="https://internal.zilliz.com:18080/jenkins/job/milvus-ha-ci/job/master/badge/">
<img src="https://internal.zilliz.com:18080/jenkins/job/milvus-ha-ci/job/master/badge/icon" />
......@@ -27,6 +28,7 @@
</div>
<br />
## What is Milvus?
......@@ -38,40 +40,42 @@ Both Milvus Standalone and Milvus Cluster are available.
Milvus was released under the [open-source Apache License 2.0](https://github.com/milvus-io/milvus/blob/master/LICENSE) in October 2019. It is currently a graduate project under [LF AI & Data Foundation](https://lfaidata.foundation/).
## 产品亮点
## Key features
### Millisecond search on trillion vector datasets
Average latency measured in milliseconds on trillion vector datasets.
### Simplified unstructured data management
- Rich APIs designed for data science workflows.
- Consistent user experience across laptop, local cluster, and cloud.
<details>
<summary><b>Millisecond search on trillion vector datasets</b></summary>
Average latency measured in milliseconds on trillion vector datasets.
</details>
- Embed real-time search and analytics into virtually any application.
<details>
<summary><b>Simplified unstructured data management</b></summary>
<li>Rich APIs designed for data science workflows.</li><li>Consistent user experience across laptop, local cluster, and cloud.</li><li>Embed real-time search and analytics into virtually any application.</li>
</details>
### Reliable, always on vector database
<details>
<summary><b>Reliable, always on vector database</b></summary>
Milvus’ built-in replication and failover/failback features ensure data and applications can maintain business continuity in the event of a disruption.
</details>
Milvus’ built-in replication and failover/failback features ensure data and applications can maintain business continuity in the event of a disruption.
<details>
<summary><b>Highly scalable and elastic</b></summary>
Component-level scalability makes it possible to scale up and down on demand. Milvus can autoscale at a component level according to the load type, making resource scheduling much more efficient.
</details>
### Highly scalable and elastic
<details>
<summary><b>Hybrid search</b></summary>
In addition to vectors, Milvus supports data types such as Boolean, integers, floating-point numbers, and more. A collection in Milvus can hold multiple fields for accommodating different data features or properties. By complementing scalar filtering to vector similarity search, Milvus makes modern search much more flexible than ever.
</details>
Component-level scalability makes it possible to scale up and down on demand. Milvus can autoscale at a component level according to the load type, making resource scheduling much more efficient.
<details>
<summary><b>Unified Lambda structure</b></summary>
Milvus combines stream and batch processing for data storage to balance timeliness and efficiency. Its unified interface makes vector similarity search a breeze.
</details>
### Hybrid search
In addition to vectors, Milvus supports data types such as Boolean, integers, floating-point numbers, and more. A collection in Milvus can hold multiple fields for accommodating different data features or properties. By complementing scalar filtering to vector similarity search, Milvus makes modern search much more flexible than ever.
### Unified Lambda structure
Milvus combines stream and batch processing for data storage to balance timeliness and efficiency. Its unified interface makes vector similarity search a breeze.
### Community supported, industry recognized
With over 1,000 enterprise users, 6,000+ stars on GitHub, and an active open-source community, you’re not alone when you use Milvus. As a graduate project under the LF AI & Data Foundation, Milvus has institutional support.
<details>
<summary><b>Community supported, industry recognized</b></summary>
With over 1,000 enterprise users, 6,000+ stars on GitHub, and an active open-source community, you’re not alone when you use Milvus. As a graduate project under the <a href="https://lfaidata.foundation/">LF AI & Data Foundation</a>, Milvus has institutional support.
</details>
> **IMPORTANT** The master branch is for the development of Milvus v2.0. On March 9th, 2021, we released Milvus v1.0, the first stable version of Milvus with long-term support. To use Milvus v1.0, switch to [branch 1.0](https://github.com/milvus-io/milvus/tree/1.0).
......@@ -84,95 +88,130 @@ With over 1,000 enterprise users, 6,000+ stars on GitHub, and an active open-sou
Install with Docker-Compose
```
```bash
$ cd milvus/deployments/docker/standalone
$ sudo docker-compose up -d
```
Install with Helm
```
```bash
$ helm install -n milvus --set image.all.repository=registry.zilliz.com/milvus/milvus --set image.all.tag=master-latest milvus milvus-helm-charts/charts/milvus-ha
```
Build from source code
```bash
# Clone github repository.
$ cd /home/$USER/
$ git clone https://github.com/milvus-io/milvus.git
# Install third-party dependencies.
$ cd /home/$USER/milvus/
$ ./scripts/install_deps.sh
# Compile Milvus standalone.
$ make standalone
```
### Install Milvus Cluster
Install with Docker-Compose
```
```bash
$ cd milvus/deployments/docker/distributed
$ sudo docker-compose up -d
```
Install with Helm
```
```bash
$ helm install -n milvus --set image.all.repository=registry.zilliz.com/milvus/milvus --set image.all.tag=master-latest --set standalone.enabled=false milvus milvus-helm-charts/charts/milvus-ha
```
## Make Milvus
You can also build Milvus from source code.
### Prerequisites
Install the following before building Milvus from source code.
- [Git](https://git-scm.com/book/en/v2/Getting-Started-Installing-Git) for version control.
- [Golang](https://golang.org/doc/install) version 1.15 or higher and associated toolkits.
- [CMake](https://cmake.org/install/) version 3.14 or higher for compilation.
- [OpenBLAS](https://github.com/xianyi/OpenBLAS/wiki/Installation-Guide) (Basic Linear Algebra Subprograms) library version 0.3.9 or higher for matrix operations.
Build from source code
### Make Milvus Standalone
```
# Clone github repository
$ cd /home/$USER/
$ git clone https://github.com/milvus-io/milvus.git
# Install third-party dependencies
$ cd /home/$USER/milvus/
$ ./scripts/install_deps.sh
# Compile Milvus standalone
$ make standalone
```
### Make Milvus Cluster
```
# Clone github repository
```bash
# Clone github repository.
$ cd /home/$USER
$ git clone https://github.com/milvus-io/milvus.git
# Install third-party dependencies
# Install third-party dependencies.
$ cd milvus
$ ./scripts/install_deps.sh
# Compile Milvus Cluster
# Compile Milvus Cluster.
$ make milvus
```
## Milvus 2.0 is better than Milvus 1.x
| | **Milvus 1.x** | **Milvus 2.0** |
| ------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ |
| **Architecture** | Shared storage | Cloud native |
| **Scalability** | 1 - 32 read-only nodes with only one write node. | 500+ nodes |
| **Durability** | Local diskNetwork file system (NFS) | Object storage service (OSS)Distributed file system (DFS) |
| **Availability** | 99% | 99.9% |
| **Data consistency** | Eventual consistency | Three levels of consistency: StrongSessionConsistent prefix |
| **Data types supported** | Vectors | VectorsFixed-length scalars String and text (in planning) |
| **Basic operations supported** | Data insertionData deletionApproximate nearest neighbor (ANN) Search | Data insertionData deletion (in planning)Data queryApproximate nearest neighbor (ANN) SearchRecurrent neural network (RNN) search (in planning) |
| **Advanced features** | MishardsMilvus DM | Scalar filteringTime TravelMulti-site deployment and multi-cloud integrationData management tools |
| **Index types and libraries** | FaissAnnoyHnswlibRNSG | FaissAnnoyHnswlibRNSGScaNN (in planning)On-disk index (in planning) |
| **SDKs** | PythonJava,GoRESTfulC++ | PythonGo (in planning)RESTful (in planning)C++ (in planning) |
| **Release status** | Long-term support (LTS) | Release candidate. A stable version will be released in August. |
## Milvus 2.0 is better than Milvus 1.x
<table class="comparison">
<tr>
<th>&nbsp;</th>
<th><b>Milvus 1.x</b></th>
<th><b>Milvus 2.0</b></th>
</tr>
<tr>
<td><b>Architecture</b></td>
<td>Shared storage</td>
<td>Cloud native</td>
</tr>
<tr>
<td><b>Scalability</b></td>
<td>1 to 32 read nodes with only one write node</td>
<td>500+ nodes</td>
</tr>
<tr>
<td><b>Durability</b></td>
<td><li>Local disk</li><li>Network file system (NFS)</li></td>
<td><li>Object storage service (OSS)</li><li>Distributed file system (DFS)</li></td>
</tr>
<tr>
<td><b>Availability</b></td>
<td>99%</td>
<td>99.9%</td>
</tr>
<tr>
<td><b>Data consistency</b></td>
<td>Eventual consistency</td>
<td>Three levels of consistency:<li>Strong</li><li>Session</li><li>Consistent prefix</li></td>
</tr>
<tr>
<td><b>Data types supported</b></td>
<td>Vectors</td>
<td><li>Vectors</li><li>Fixed-length scalars</li><li>String and text (in planning)</li></td>
</tr>
<tr>
<td><b>Basic operations supported</b></td>
<td><li>Data insertion</li><li>Data deletion</li><li>Approximate nearest neighbor (ANN) Search</li></td>
<td><li>Data insertion</li><li>Data deletion (in planning)</li><li>Data query</li><li>Approximate nearest neighbor (ANN) Search</li><li>Recurrent neural network (RNN) search (in planning)</li></td>
</tr>
<tr>
<td><b>Advanced features</b></td>
<td><li>Mishards</li><li>Milvus DM</li></td>
<td><li>Scalar filtering</li><li>Time Travel</li><li>Multi-site deployment and multi-cloud integration</li><li>Data management tools</li></td>
</tr>
<tr>
<td><b>Index types and libraries</b></td>
<td><li>Faiss</li><li>Annoy</li><li>Hnswlib</li><li>RNSG</li></td>
<td><li>Faiss</li><li>Annoy</li><li>Hnswlib</li><li>RNSG</li><li>ScaNN (in planning)</li><li>On-disk index (in planning)</li></td>
</tr>
<tr>
<td><b>SDKs</b></td>
<td><li>Python</li><li>Java</li><li>Go</li><li>RESTful</li><li>C++</li></td>
<td><li>Python</li><li>Go (in planning)</li><li>RESTful (in planning)</li><li>C++ (in planning)</li></td>
</tr>
<tr>
<td><b>Release status</b></td>
<td>Long-term support (LTS)</td>
<td>Release candidate. A stable version will be released in August.</td>
</tr>
</table>
## Getting Started
......@@ -210,7 +249,6 @@ $ make milvus
</table>
- [Image Search](https://zilliz.com/milvus-demos)
Images made searchable. Instantaneously return the most similar images from a massive database.
......@@ -278,3 +316,4 @@ Milvus adopts dependencies from the following:
- Thank [etcd](https://github.com/coreos/etcd) for providing some great open-source tools.
- Thank [Pulsar](https://github.com/apache/pulsar) for its great distributed information pub/sub platform.
- Thank [RocksDB](https://github.com/facebook/rocksdb) for the powerful storage engines.
README_CN.md
浏览文件 @ deb937a1
<img src="https://zillizstorage.blob.core.windows.net/zilliz-assets/zilliz-assets/assets/readme_ch_962480ccfb.png" alt="Milvus banner">
![Milvuslogo](https://github.com/milvus-io/docs/blob/master/v0.9.1/assets/milvus_logo.png)
[![Slack](https://img.shields.io/badge/Join-Slack-orange)](https://join.slack.com/t/milvusio/shared_invite/zt-e0u4qu3k-bI2GDNys3ZqX1YCJ9OM~GQ)
![GitHub](https://img.shields.io/github/license/milvus-io/milvus)
![Docker pulls](https://img.shields.io/docker/pulls/milvusdb/milvus)
[![Build Status](https://internal.zilliz.com:18080/jenkins/job/milvus-ha-ci/job/master/badge/icon)](https://internal.zilliz.com:18080/jenkins/job/milvus-ha-ci/job/master/badge/)
[![CII Best Practices](https://bestpractices.coreinfrastructure.org/projects/3563/badge)](https://bestpractices.coreinfrastructure.org/projects/3563)
[![codecov](https://codecov.io/gh/milvus-io/milvus/branch/master/graph/badge.svg)](https://codecov.io/gh/milvus-io/milvus)
[![codebeat badge](https://codebeat.co/badges/e030a4f6-b126-4475-a938-4723d54ec3a7?style=plastic)](https://codebeat.co/projects/github-com-milvus-io-milvus-master)
[![Codacy Badge](https://api.codacy.com/project/badge/Grade/c4bb2ccfb51b47f99e43bfd1705edd95)](https://app.codacy.com/gh/milvus-io/milvus?utm_source=github.com&utm_medium=referral&utm_content=milvus-io/milvus&utm_campaign=Badge_Grade_Dashboard)
[English](README.md) | 中文版
<div class="column" align="middle">
<a href="https://join.slack.com/t/milvusio/shared_invite/zt-e0u4qu3k-bI2GDNys3ZqX1YCJ9OM~GQ">
<img src="https://img.shields.io/badge/Join-Slack-orange" /></a>
<img src="https://img.shields.io/github/license/milvus-io/milvus" />
<img src="https://img.shields.io/docker/pulls/milvusdb/milvus" />
</div>
# 欢迎来到 Milvus
## Milvus 是什么
Milvus 是一款开源的特征向量数据库，具有使用方便、实用可靠、稳定高效和搜索迅速等特点，在全球范围内被六百家余组织和机构所采用。Milvus 已经被广泛应用于多个领域，其中包括图像处理、机器视觉、自然语言处理、语音识别、推荐系统以及新药发现等。
Milvus 的架构如下：
![arch](https://github.com/milvus-io/docs/blob/master/v0.10.5/assets/milvus_arch.png)
<div class="column" align="middle">
<a href="https://internal.zilliz.com:18080/jenkins/job/milvus-ha-ci/job/master/badge/">
<img src="https://internal.zilliz.com:18080/jenkins/job/milvus-ha-ci/job/master/badge/icon" />
</a>
<a href="https://bestpractices.coreinfrastructure.org/projects/3563">
<img src="https://bestpractices.coreinfrastructure.org/projects/3563/badge" />
</a>
<a href="https://codecov.io/gh/milvus-io/milvus">
<img src="https://codecov.io/gh/milvus-io/milvus/branch/master/graph/badge.svg" />
</a>
<a href="https://app.codacy.com/gh/milvus-io/milvus?utm_source=github.com&utm_medium=referral&utm_content=milvus-io/milvus&utm_campaign=Badge_Grade_Dashboard">
<img src="https://api.codacy.com/project/badge/Grade/c4bb2ccfb51b47f99e43bfd1705edd95" />
</a>
</div>
若要了解 Milvus 详细介绍和整体架构，请访问 [Milvus 简介](https://www.milvus.io/docs/overview.md)。你可以通过 [版本发布说明](https://www.milvus.io/docs/release_notes.md) 获取最新版本的功能和更新。
Milvus 是一个 [LF AI & Data 基金会](https://lfaidata.foundation/) 的孵化项目。获取更多，请访问 [lfai.foundation](https://lfaidata.foundation/)。
## Milvus 快速上手
<br />
### 安装 Milvus
请参阅 [Milvus 安装指南](https://www.milvus.io/docs/install_milvus.md) 使用 Docker 容器安装 Milvus。若要基于源码编译，请访问 [源码安装](INSTALL.md)。
# 欢迎来到 Milvus
### 尝试示例代码
## Milvus 是什么
你可以尝试用 [Python](https://www.milvus.io/docs/example_code.md)，[Java](https://github.com/milvus-io/milvus-sdk-java/tree/master/examples)，[Go](https://github.com/milvus-io/milvus-sdk-go/tree/master/examples)，或者 [C++](https://github.com/milvus-io/milvus/tree/master/sdk/examples) 运行 Milvus 示例代码。
Milvus 是一款全球领先的开源向量数据库，赋能 AI 应用和向量相似度搜索，加速非结构化数据检索。用户在任何部署环境中均可获得始终如一的用户体验。
## 支持的客户端
Milvus 提供单机版与分布式版：
- [Go](https://github.com/milvus-io/milvus-sdk-go)
- [Python](https://github.com/milvus-io/pymilvus)
- [Java](https://github.com/milvus-io/milvus-sdk-java)
- [C++](https://github.com/milvus-io/milvus/tree/1.x/sdk)
- [RESTful API](https://github.com/milvus-io/milvus/tree/1.x/core/src/server/web_impl)
- [Node.js](https://www.npmjs.com/package/@arkie-ai/milvus-client) (由 [arkie](https://www.arkie.cn/) 提供)
## 应用场景
Milvus 基于 [Apache 2.0 License](https://github.com/milvus-io/milvus/blob/master/LICENSE) 协议发布，于 2019 年 10 月正式开源，是 [LF AI & Data 基金会](https://lfaidata.foundation/) 的毕业项目。
Milvus 可以应用于多种 AI 场景。你可以访问 [Milvus 应用场景](https://milvus.io/scenarios) 体验在线场景展示。你也可以访问 [Milvus 训练营](https://github.com/milvus-io/bootcamp) 了解更详细的应用场景和解决方案。
## 产品亮点
## 性能基准测试
<details>
<summary><b>针对万亿级向量的毫秒级搜索</b></summary>
完成万亿条向量数据搜索的平均延迟以毫秒计。
</details>
关于 Milvus 性能基准的更多信息，请参考 [测试报告](https://github.com/milvus-io/milvus/tree/master/docs)。
<details>
<summary><b>简化的非结构化数据管理</b></summary>
<li>一整套专为数据科学工作流设计的 API。</li><li>消除笔记本、本地集群、云服务器之间的使用差异，提供始终如一的跨平台用户体验。</li><li>可以在任何场景下实现实时搜索与分析。</li>
</details>
## 路线图
<details>
<summary><b>稳定可靠的用户体验</b></summary>
Milvus 具有故障转移和故障恢复的机制，即使服务中断，也能确保数据和应用的业务连续性。
</details>
你可以参考我们的 [路线图](https://github.com/milvus-io/milvus/milestones)，了解 Milvus 即将实现的新特性。
<details>
<summary><b>高度可扩展，弹性伸缩</b></summary>
组件级别的高扩展性，支持精准扩展。
</details>
路线图尚未完成，并且可能会存在合理改动。我们欢迎各种针对路线图的意见、需求和建议。
<details>
<summary><b>混合查询</b></summary>
除了向量以外，Milvus还支持布尔值、整型、浮点型等数据类型。在 Milvus 中，一个 collection 可以包含多个字段来代表数据特征或属性。Milvus 还支持在向量相似度检索过程中进行标量字段过滤。
</details>
## 贡献者指南
<details>
<summary><b>基于 Lambda 架构的流批一体式数据存储</b></summary>
Milvus 在存储数据时支持流处理和批处理两种方式，兼顾了流处理的时效性和批处理的效率。统一的对外接口使得向量相似度查询更为便捷。
</details>
我们由衷欢迎你推送贡献。关于贡献流程的详细信息，请参阅 [贡献者指南](https://github.com/milvus-io/milvus/blob/master/CONTRIBUTING.md)。本项目遵循 Milvus [行为准则](https://github.com/milvus-io/milvus/blob/master/CODE_OF_CONDUCT.md)。如果你希望参与本项目，请遵守该准则的内容。
<details>
<summary><b>广受社区支持和业界认可</b></summary>
Milvus 项目在 GitHub 上获星超 6000，拥有逾 1000 家企业用户，还有活跃的开源社区。Milvus 由 <a href="https://lfaidata.foundation/">LF AI & Data 基金会</a> 背书，是该基金会的毕业项目。
</details>
我们使用 [GitHub issues](https://github.com/milvus-io/milvus/issues) 追踪问题和补丁。若你希望提出问题或进行讨论，请加入我们的社区。
> **注意** 主分支用于 Milvus v2.0 代码开发。Milvus v1.0 于 2021 年 3 月 9 日发布，是 Milvus 的首个长期支持（LTS）版本。如需使用 Milvus 1.0，请切换至 [1.0 分支](https://github.com/milvus-io/milvus/tree/1.0)。
## 加入 Milvus 社区
## 安装
欢迎加入我们的 [Slack 频道](https://join.slack.com/t/milvusio/shared_invite/zt-e0u4qu3k-bI2GDNys3ZqX1YCJ9OM~GQ)以便与其他用户和贡献者进行交流。
### 安装 Milvus 单机版
## 加入 Milvus 技术交流微信群
使用 Docker-Compose 安装
![qrcode](https://github.com/milvus-io/docs/blob/master/v1.0.0/assets/qrcode.png)
```bash
$ cd milvus/deployments/docker/standalone
$ sudo docker-compose up -d
```
使用 Helm Chart 安装
```bash
$ helm install -n milvus --set image.all.repository=registry.zilliz.com/milvus/milvus --set image.all.tag=master-latest milvus milvus-helm-charts/charts/milvus-ha
```
从源码编译 Milvus
```bash
# Clone github repository.
$ cd /home/$USER/
$ git clone https://github.com/milvus-io/milvus.git
# Install third-party dependencies.
$ cd /home/$USER/milvus/
$ ./scripts/install_deps.sh
# Compile Milvus standalone.
$ make standalone
```
### 安装 Milvus 分布式版
使用 Docker-Compose 安装
```bash
$ cd milvus/deployments/docker/distributed
$ sudo docker-compose up -d
```
使用 Helm Chart 安装
```bash
$ helm install -n milvus --set image.all.repository=registry.zilliz.com/milvus/milvus --set image.all.tag=master-latest --set standalone.enabled=false milvus milvus-helm-charts/charts/milvus-ha
```
从源码编译 Milvus
```bash
# Clone github repository.
$ cd /home/$USER
$ git clone https://github.com/milvus-io/milvus.git
# Install third-party dependencies.
$ cd milvus
$ ./scripts/install_deps.sh
# Compile Milvus Cluster.
$ make milvus
```
## Milvus 2.0：功能增加、性能升级
<table class="demo">
<tr>
<th>&nbsp;</th>
<th><b>Milvus 1.x</b></th>
<th><b>Milvus 2.0</b></th>
</tr>
<tr>
<td><b>架构</b></td>
<td>共享存储</td>
<td>云原生</td>
</tr>
<tr>
<td><b>可扩展性</b></td>
<td>1 - 32 个读节点，1 个写节点</td>
<td>500+ 个节点</td>
</tr>
<tr>
<td><b>持久性</b></td>
<td><li>本地磁盘</li><li>网络文件系统 (NFS)</li></td>
<td><li>对象存储 (OSS)</li><li>分布式文件系统 (DFS)</li></td>
</tr>
<tr>
<td><b>可用性</b></td>
<td>99%</td>
<td>99.9%</td>
</tr>
<tr>
<td><b>数据一致性</b></td>
<td>最终一致</td>
<td>多种一致性<li>Strong</li><li>Session</li><li>Consistent prefix</li></td>
</tr>
<tr>
<td><b>数据类型支持</b></td>
<td>向量数据</td>
<td><li>向量数据</li><li>标量数据</li><li>字符串与文本 (开发中)</li></td>
</tr>
<tr>
<td><b>基本操作</b></td>
<td><li>插入数据</li><li>删除数据</li><li>相似最邻近（ANN）搜索</li></td>
<td><li>插入数据</li><li>删除数据 (开发中)</li><li>数据查询</li><li>相似最邻近（ANN）搜索</li><li>基于半径的最近邻算法（RNN） (开发中)</li></td>
</tr>
<tr>
<td><b>高级功能</b></td>
<td><li>Mishards</li><li>Milvus DM 数据迁移工具</li></td>
<td><li>标量字段过滤</li><li>Time Travel</li><li>多云/地域部署</li><li>数据管理工具</li></td>
</tr>
<tr>
<td><b>索引类型</b></td>
<td><li>Faiss</li><li>Annoy</li><li>Hnswlib</li><li>RNSG</li></td>
<td><li>Faiss</li><li>Annoy</li><li>Hnswlib</li><li>RNSG</li><li>ScaNN (开发中)</li><li>On-disk index (开发中)</li></td>
</tr>
<tr>
<td><b>SDK</b></td>
<td><li>Python</li><li>Java</li><li>Go</li><li>RESTful</li><li>C++</li></td>
<td><li>Python</li><li>Go (开发中)</li><li>RESTful (开发中)</li><li>C++ (开发中)</li></td>
</tr>
<tr>
<td><b>当前状态</b></td>
<td>长期支持（LTS）版本</td>
<td>预览版本。预计 2021 年 8 月发布稳定版本。</td>
</tr>
</table>
## 入门指南
### 应用场景
<table>
<tr>
<td width="30%">
<a href="https://zilliz.com/milvus-demos">
<img src="https://zillizstorage.blob.core.windows.net/zilliz-assets/zilliz-assets/assets/image_search_59a64e4f22.gif" />
</a>
</td>
<td width="30%">
<a href="https://zilliz.com/milvus-demos">
<img src="https://zillizstorage.blob.core.windows.net/zilliz-assets/zilliz-assets/assets/qa_df5ee7bd83.gif" />
</a>
</td>
<td width="30%">
<a href="https://zilliz.com/milvus-demos">
<img src="https://zillizstorage.blob.core.windows.net/zilliz-assets/zilliz-assets/assets/mole_search_76f8340572.gif" />
</a>
</td>
</tr>
<tr>
<th>
<a href="https://zilliz.com/milvus-demos">以图搜图系统</a>
</th>
<th>
<a href="https://zilliz.com/milvus-demos">智能问答机器人</a>
</th>
<th>
<a href="https://zilliz.com/milvus-demos">分子式检索系统</a>
</th>
</tr>
</table>
- [以图搜图系统](https://zilliz.com/milvus-demos)：从海量图片中快速检索最相似图片。
- [智能问答机器人](https://zilliz.com/milvus-demos)：交互式智能问答机器人帮助用户节省时间和用人成本。
- [分子式检索系统](https://zilliz.com/milvus-demos)：迅速检索相似化学分子式。
## 训练营
Milvus 训练营能够帮助你了解向量数据库的操作及各种应用场景。通过 Milvus 训练营探索如何进行 Milvus 性能测评，搭建智能问答机器人、推荐系统、以图搜图系统、分子式检索系统等。
## 贡献代码
欢迎向 Milvus 社区贡献你的代码。代码贡献流程或提交补丁等相关信息详见 [代码贡献准则](https://github.com/milvus-io/milvus/blob/master/CONTRIBUTING.md)。参考 [社区仓库](https://github.com/milvus-io/community) 了解社区管理准则并获取更多社区资源。
## Milvus 文档
### SDK
- [PyMilvus-ORM](https://github.com/milvus-io/pymilvus-orm)
## 社区
欢迎加入 [Slack](https://join.slack.com/t/milvusio/shared_invite/zt-e0u4qu3k-bI2GDNys3ZqX1YCJ9OM~GQ) 频道分享你的建议与问题。你也可以通过 [FAQ](https://milvus.io/cn/docs/v1.0.0/performance_faq.md) 页面，查看常见问题及解答。
订阅 Milvus 邮件：
## 相关链接
- [Milvus Technical Steering Committee](https://lists.lfai.foundation/g/milvus-tsc)
- [Milvus Technical Discussions](https://lists.lfai.foundation/g/milvus-technical-discuss)
- [Milvus Announcement](https://lists.lfai.foundation/g/milvus-announce)
- [Milvus.io](https://www.milvus.io)
关注我们的社交媒体：
- [Milvus 常见问题](https://www.milvus.io/cn/docs/faq/operational_faq.md)
- [知乎](https://zilliz.atlassian.net/wiki/spaces/TC/pages/251658753/CN%2BTranslation%2BWhat%2Bis%2BMilvus#)
- [CSDN](http://zilliz.blog.csdn.net/)
- [Bilibili](http://space.bilibili.com/478166626)
- Zilliz 技术交流微信群
- [Milvus Medium](https://medium.com/@milvusio)
<img src="https://zillizstorage.blob.core.windows.net/zilliz-assets/zilliz-assets/assets/wechat_2abac21f5a.png" alt="Wechat QR Code">
- [Milvus CSDN](https://zilliz.blog.csdn.net/)
## 加入我们
- [Milvus Twitter](https://twitter.com/milvusio)
Zilliz 是 Milvus 项目的幕后公司。我们正在 [招聘](https://app.mokahr.com/apply/zilliz/37974#/) 算法、开发和全栈工程师。欢迎加入我们，让我们携手构建下一代的开源数据基础软件。
- [Milvus Facebook](https://www.facebook.com/io.milvus.5)
## 特别感谢
- [Milvus 设计文档](DESIGN.md)
Milvus 采用了以下依赖库:
## 许可协议
- 感谢 [FAISS](https://github.com/facebookresearch/faiss) 相似性检索库。
- 感谢开源键值存储 [etcd](https://github.com/coreos/etcd)。
- 感谢分布式信息发布/订阅平台 [Pulsar](https://github.com/apache/pulsar)。
- 感谢存储引擎 [RocksDB](https://github.com/facebook/rocksdb)。
[Apache 许可协议 2.0 版](LICENSE)
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或