PyPI 官网下载 | gnes-0.0.29.tar.gz

<p align="center"> <a href="https://gnes.ai"> <img src=".github/gnes-github-banner.png?raw=true" alt="GNES Generic Neural Elastic Search, logo made by Han Xiao"> </a> </p> <p align="center"> <a href="https://cloud.drone.io/gnes-ai/gnes"> <img src="https://cloud.drone.io/api/badges/gnes-ai/gnes/status.svg" /> </a> <a href="https://pypi.org/project/gnes/"> <img alt="PyPI" src="https://img.shields.io/pypi/v/gnes.svg"> </a> <a href='https://doc.gnes.ai/'> <img src='https://readthedocs.org/projects/gnes/badge/?version=latest' alt='Documentation Status' /> </a> <a href="https://www.codacy.com/app/gnes-ai/gnes?utm_source=github.com&amp;utm_medium=referral&amp;utm_content=gnes-ai/gnes&amp;utm_campaign=Badge_Grade"> <img src="https://api.codacy.com/project/badge/Grade/a9ce545b9f3846ba954bcd449e090984"/> </a> <a href="https://codecov.io/gh/gnes-ai/gnes"> <img src="https://codecov.io/gh/gnes-ai/gnes/branch/master/graph/badge.svg" /> </a> <a href='https://github.com/gnes-ai/gnes/blob/master/LICENSE'> <img alt="PyPI - License" src="https://img.shields.io/pypi/l/gnes.svg"> </a> </p> <p align="center"> <a href="#highlights">Highlights</a> • <a href="#overview">Overview</a> • <a href="#install-gnes">Install</a> • <a href="#getting-started">Getting Started</a> • <a href="#documentation">Documentation</a> • <a href="#tutorial">Tutorial</a> • <a href="#contributing">Contributing</a> • <a href="./CHANGELOG.md">Release Notes</a> • <a href="https://hanxiao.github.io/2019/07/29/Generic-Neural-Elastic-Search-From-bert-as-service-and-Go-Way-Beyond/">Blog</a> </p> <h2 align="center">What is it</h2> GNES [<i>jee-nes</i>] is **Generic Neural Elastic Search**, a cloud-native semantic search system based on deep neural network. GNES enables large-scale index and semantic search for **text-to-text**, **image-to-image**, **video-to-video** and *any-to-any* content form. <h2 align="center">Highlights</h2> <p align="center"> <a href="https://hanxiao.github.io/2019/07/29/Generic-Neural-Elastic-Search-From-bert-as-service-and-Go-Way-Beyond/">💭 To know more about the key tenets of GNES, read this blog post</a> </p> <center> <table> <tr> <th><h3>☁️</h3><h3>Cloud-Native & Elastic</h3></th> <th><h3>🐣</h3><h3>Easy-to-Use</h3></th> <th><h3>🔬</h3><h3>State-of-the-Art</h3></th> </tr> <tr> <td width="33%">_{GNES is <i>all-in-microservice</i>! Encoder, indexer, preprocessor and router are all running in their own containers. They communicate via versioned APIs and collaborate under the orchestration of Docker Swarm/Kubernetes etc. Scaling, load-balancing, automated recovering, they come off-the-shelf in GNES.}</td> <td width="33%">_{How long would it take to deploy a change that involves just switching a layer in VGG? In GNES, this is just one line change in a YAML file. We abstract the encoding and indexing logic to a YAML config, so that you can change or stack encoders and indexers without even touching the codebase.}</td> <td width="33%">_{Taking advantage of fast-evolving AI/ML/NLP/CV communities, we learn from best-of-breed deep learning models and plug them into GNES, making sure you always enjoy the state-of-the-art performance.}</td> </tr> <tr> <th><h3>🌌</h3><h3>Generic & Universal</h3></th> <th><h3>📦</h3><h3>Model as Plugin</h3></th> <th><h3>💯</h3><h3>Best Practice</h3></th> </tr> <tr> <td width="33%">_{Searching for texts, image or even short-videos? Using Python/C/Java/Go/HTTP as the client? Doesn't matter which content form you have or which language do you use, GNES can handle them all.}</td> <td width="33%">_{When built-in models do not meet your requirments, simply build your own with <i>one Python file and one YAML file</i>. No need to rebuilt GNES framework, as your models will be loaded as plugins and directly rollout online.}</td> <td width="33%">_{We love to learn the best practice from the community, helping our GNES to achieve the next level of availability, resiliency, performance, and durability. If you have any ideas or suggestions, feel free to contribute.}</td> </tr> </table> </center> <h2 align="center">Overview</h2> <p align="center"> <a href="https://gnes.ai"> <img src=".github/gnes-component-overview.svg" alt="component overview"> </a> </p> <h2 align="center">Install GNES</h2> There are two ways to get GNES, either as a Docker image or as a PyPi package. **For cloud users, we highly recommend using GNES via Docker**. ### Run GNES as a Docker Container ```bash docker run gnes/gnes:latest-alpine ``` This command downloads the latest GNES image (based on [Alpine Linux](https://alpinelinux.org/)) and runs it in a container. When the container runs, it prints an informational message and exits. #### 💡 Choose the right GNES image Besides the `alpine` image optimized for the space, we also provide Buster (Debian 10.0), Ubuntu 18.04 and Ubuntu 16.04-based images. The table below summarizes [all available GNES tags](https://cloud.docker.com/u/gnes/repository/docker/gnes/gnes). One can fill in `{ver}` with `latest`, `stable` or `v0..xx`. `latest` refers to the **latest master** of this repository, which [may not be stable](./CONTRIBUTING.md#Merging-Process). We recommend you to use an official release by changing the `latest` to a version number, say `v0.0.24`, or simply using `stable` for the last release, e.g. `gnes:stable-ubuntu` <table> <tr> <th>Tag</th> <th>Size and layers</th> <th>Description</th> </tr> <tr> <td><code>{ver}-alpine</code></td> <td><a href="https://microbadger.com/images/gnes/gnes:latest-alpine" title="Get your own image badge on microbadger.com"><img src="https://images.microbadger.com/badges/image/gnes/gnes:latest-alpine.svg"></a></td> <td>based on Alpine Linux;<br>no deep learning libraries;<br>extremely lightweight and portable, enables fast scaling on even edge devices.</td> </tr> <tr> <td><code>{ver}-buster</code></td> <td><a href="https://microbadger.com/images/gnes/gnes:latest-buster" title="Get your own image badge on microbadger.com"><img src="https://images.microbadger.com/badges/image/gnes/gnes:latest-buster.svg"></a></td> <td>based on Debian 10.0;<br>no deep learning libraries;<br>recommended for building or extending a GNES-Hub image.</td> </tr> <tr> <td><code>{ver}-ubuntu18</code></td> <td><a href="https://microbadger.com/images/gnes/gnes:latest-ubuntu18" title="Get your own image badge on microbadger.com"><img src="https://images.microbadger.com/badges/image/gnes/gnes:latest-ubuntu18.svg"></a></td> <td>based on Ubuntu 18.04;<br>no deep learning libraries.</td> </tr> <tr> <td><code>{ver}-full</code></td> <td><a href="https://microbadger.com/images/gnes/gnes:latest-full" title="Get your own image badge on microbadger.com"><img src="https://images.microbadger.com/badges/image/gnes/gnes:latest-full.svg"></a></td> <td>based on Ubuntu 16.04;<br>python-3.6.8, cuda-10.0, tf1.14, pytorch1.1, faiss, multiple pretrained models; <br>heavy but self-contained, useful in testing GNES end-to-endly.</td> </tr> </table> We also provide a public mirror hosted on Tencent Cloud, from which Chinese mainland users can pull the image faster. ```bash docker login --username=xxx ccr.ccs.tencentyun.com # login to Tencent Cloud so that we can pull from it docker run ccr.ccs.tencentyun.com/gnes/gnes:latest-alpine ``` The table below shows the status of the build pipeline. <table> <tr><th>Registry</th><th>Build status</th></tr> <tr> <td>_{Docker Hub}<br><code>gnes/gnes:[tag]</code></td> <td><a href="https://drone.gnes.ai/gnes-ai/gnes"><img src="https://drone.gnes.ai/api/badges/gnes-ai/gnes/status.svg" /></a></td> </tr> <tr> <td>_{Tencent Cloud}<br><code>ccr.ccs.tencentyun.com/gnes/gnes:[tag]</code></td> <td><a href="http://193.112