{"id":13958365,"url":"https://github.com/Tencent/embedx","last_synced_at":"2025-07-20T23:31:18.403Z","repository":{"id":37422267,"uuid":"501947445","full_name":"Tencent/embedx","owner":"Tencent","description":"embedx 是基于 c++ 开发的、完全自研的分布式 embedding 训练和推理框架。它目前支持 图模型、深度排序、召回模型和图与排序、图与召回的联合训练模型等","archived":false,"fork":false,"pushed_at":"2024-05-27T07:41:19.000Z","size":2831,"stargazers_count":299,"open_issues_count":0,"forks_count":46,"subscribers_count":14,"default_branch":"main","last_synced_at":"2024-11-22T02:05:44.344Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Tencent.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-06-10T07:41:35.000Z","updated_at":"2024-11-19T00:44:43.000Z","dependencies_parsed_at":"2024-11-13T02:41:49.216Z","dependency_job_id":null,"html_url":"https://github.com/Tencent/embedx","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent%2Fembedx","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent%2Fembedx/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent%2Fembedx/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Tencent%2Fembedx/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Tencent","download_url":"https://codeload.github.com/Tencent/embedx/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":226845003,"owners_count":17691140,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-08T13:01:30.578Z","updated_at":"2024-11-28T01:31:52.382Z","avatar_url":"https://github.com/Tencent.png","language":"C++","readme":"![logo](docs/images/logo.png)\n\n## 简介\n\n**embedx** 是基于 c++ 开发的大规模 embedding 训练和推理系统，累计支持公司 `12 个业务`、 `30 多个团队使用`、`上线百余次`。\n\n我们在以下推荐、搜索、支付 和 风控等产品落地使用了 embedx: `微信看一看`、`微信视频号`、`微信搜一搜`、`微信支付`、`微信安全`、\n`腾讯新闻`、`应用宝`、`QQ 音乐`、`JOOX 音乐`、`腾讯课堂`、`领航平台` 和 `腾讯黑产打击` 等 ，并取得了性能和效果双丰收。\n\n更多介绍请参考[详细介绍](docs/intro_embedx.md)。\n\nEmbedX系统的论文发表在PVLDB'2023, 引用 cite：\n```\n@article{10.14778/3611540.3611546,\nauthor = {Zou, Yuanhang and Ding, Zhihao and Shi, Jieming and Guo, Shuting and Su, Chunchen and Zhang, Yafei},\ntitle = {EmbedX: A Versatile, Efficient and Scalable Platform to Embed Both Graphs and High-Dimensional Sparse Data},\nyear = {2023},\nvolume = {16},\nnumber = {12},\nurl = {https://doi.org/10.14778/3611540.3611546},\njournal = {Proc. VLDB Endow.},\npages = {3543–3556}\n}\n```\n\n## **embedx** 已经实现的模型和评测\n\n- 已经实现的模型\n\n  - 十亿级节点、千亿级边的 **图模型**\n  - 百亿级样本、百亿特征的 **深度排序、召回模型**\n  - 十亿级节点、千亿级边与百亿级样本、百亿特征的 **图与深度排序、图与深度召回的联合建模模型**\n\n- [模型以及评测](docs/model.md)\n\n## 快速上手\n\n- [编译](docs/compile.md)\n- [数据格式](docs/data_format.md)\n- [参数介绍](docs/param.md)\n- 自有集群使用\n\n  - [单机使用必读](docs/intro_to_using_single.md)\n  - [分布式使用必读](docs/intro_to_using_dist.md)\n\n- 在线推理\n\n  - 使用方法参考[在线推理](docs/inference.md)\n\n- 辅助工具\n\n  - [随机游走](docs/random_walk.md)\n  - [邻居特征平均](docs/average_feature.md)\n  - [数据编码](docs/encode.md)\n\n## Contributing\n\n- [Contributing](CONTRIBUTING.md)\n\n## 常见问题\n\n- [常见问题](docs/faq.md)\n\n## 更多问题可以联系开发者\n\n- [Authors](docs/AUTHORS.md)\n","funding_links":[],"categories":["其他_推荐系统"],"sub_categories":["网络服务_其他"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTencent%2Fembedx","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FTencent%2Fembedx","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FTencent%2Fembedx/lists"}