Skip to content
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

Jump to bottom

embedding模型接口调用后名称发生变化 #2751

Open
1 of 3 tasks
sliontc opened this issue Jan 10, 2025 · 5 comments · May be fixed by #2779
Open
1 of 3 tasks

embedding模型接口调用后名称发生变化 #2751

sliontc opened this issue Jan 10, 2025 · 5 comments · May be fixed by #2779
Milestone
v1.x

Comments

@sliontc
Copy link

sliontc commented Jan 10, 2025

System Info / 系統信息

Python 3.10
Ubuntu 22.04

Running Xinference with Docker? / 是否使用 Docker 运行 Xinfernece？

  • docker / docker
  • pip install / 通过 pip install 安装
  • installation from source / 从源码安装

Version info / 版本信息

Release: v0.15.4

The command used to start Xinference / 用以启动 xinference 的命令

xinference-local -h 0.0.0.0

Reproduction / 复现过程

1.运行部署xinference，然后launch bge-m3 embedding
微信截图_20250110092117

2.用curl测试：curl -X POST "http://dev.xxx.cn:9997/v1/embeddings" -H "accept: application/json" -H "Content-Type: application/json" -d "{"model":"bge-m3","input":"What is the capital of China?"}"
3.返回结果：

{"object":"list","model":"bge-m3-1-0","data":[{"index":0,"object":"embedding","embedding":[-0.031030265614390373,0.035563819110393524,-0.04539928585290909,-0.010311655700206757,0.006988677196204662,0.05363959074020386,-0.025254059582948685,-0.008242975920438766,-0.0012899866560474038,-0.016217537224292755,0.0019480991177260876,0.05430838093161583,-0.009749211370944977,0.02197396382689476,-0.0310926772654056...]

Expected behavior / 期待表现

接口返回的model名字应该bge-m3
@XprobeBot XprobeBot added this to the v1.x milestone Jan 10, 2025
@codingl2k1
Copy link
Contributor

This is the model replica name. If we return the model name instead of the model replica name, we won't know which model replica serves this request. Perhaps we can extend a field to include {"model": "bge-m3", "model_replica": "bge-m3-1-0"}?

@qinxuye

@sliontc
Copy link
Author

sliontc commented Jan 14, 2025

Yes, it's a good idea. Since some third-party may use the returned model info to continue work.

@qinxuye
Copy link
Contributor

qinxuye commented Jan 14, 2025

That's a solution, we can let the user know the model and exact replica.

@github-actions GitHub Actions
Copy link

This issue is stale because it has been open for 7 days with no activity.

@github-actions github-actions bot added the stale label Jan 21, 2025
@amumu96 amumu96 linked a pull request Jan 22, 2025 that will close this issue
FEAT: create_embedding add field model_replica #2779
Open
@github-actions GitHub Actions
Copy link

This issue was closed because it has been inactive for 5 days since being marked as stale.

@github-actions github-actions bot closed this as not planned Won't fix, can't repro, duplicate, stale Jan 26, 2025
@codingl2k1 codingl2k1 reopened this Jan 27, 2025
@github-actions github-actions bot removed the stale label Jan 27, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
v1.x
Development

Successfully merging a pull request may close this issue.

FEAT: create_embedding add field model_replica zhoudelong/inference
4 participants
@qinxuye @sliontc @XprobeBot @codingl2k1