New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: support /v1/rerank router #1398

Open

nongmo677 wants to merge 1 commit into songquanpeng:main from nongmo677:v1_rerank

Contributor

nongmo677 commented Apr 30, 2024

close #1397

参考如下几个项目的rerank接口做适配

Fast GPT 提供的bge-reranker-large等示例
https://github.com/labring/FastGPT/blob/a0c1320d477fd00769983d8ddcbb2b2c2f8fd3c3/python/bge-rerank/bge-reranker-large/app.py#L69
q2wxec
https://github.com/q2wxec/lang2openai?tab=readme-ov-file#4%E6%8E%A5%E5%8F%A3%E4%B8%80%E8%A7%88
api-for-open-llm
https://github.com/xusenlinzy/api-for-open-llm/blob/e46e48056a02ffbd90e0dfe4bc2f803df1e7e4e1/tests/rerank.py#L14
xinference
https://github.com/xorbitsai/inference/blob/5d55c9c791680383157dab65e0071b8ceca0c138/xinference/client/restful/restful_client.py#L166

我已确认该 PR 已自测通过，相关截图如下：
oneapi 渠道设置

渠道1 基于Fast GPT 提供接口示例测试的bge模型

渠道2 xinference 使用bcg模型

测试
bge-test测试

bcg测试

oneapi路由通过


feat: support /v1/rerank router

893c9ad

Contributor Author

nongmo677 commented Apr 30, 2024

Fast GPT rerank接入测试通过

配置

重排结果

Owner

songquanpeng commented Apr 30, 2024

ack

zhanghx0905 commented May 2, 2024

考虑支持Text embedding inference吗

Contributor Author

nongmo677 commented May 20, 2024

考虑支持Text embedding inference吗

暂时还没有，等这个过了后面再添加

Owner

songquanpeng commented May 20, 2024 •

edited

不好意思我前段时间比较忙搁置了

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment