Skip to content

使用poetry安装依赖一直报错 Unable to find installation candidates for onnxruntime (1.20.1) #5272

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.

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

Open
2069348297 opened this issue Mar 21, 2025 · 1 comment
Labels
bug Something isn't working

Comments

@2069348297
Copy link

Image
不知道什么原因 onnxruntime版本不兼容? 但是也没提示跟什么冲突了 求大佬解读一下

@2069348297 2069348297 added the bug Something isn't working label Mar 21, 2025
Copy link

dosubot bot commented Mar 21, 2025

Hey @2069348297, I'm here to help you with any bugs, questions, or contributions. Let's dive in and tackle this issue together!

The issue you're encountering with installing onnxruntime version 1.20.1 using Poetry might be related to compatibility with your system's architecture or Python interpreter. Here are a few things to consider:

  1. Python Version Compatibility: Ensure that your Python version is compatible with onnxruntime. The Langchain-Chatchat project specifies Python versions ">=3.8.1,<3.12,!=3.9.7" [1][2]. Make sure your environment matches these requirements.

  2. Custom Package Source: The project uses a custom package source from Tsinghua University [3]. This might affect the availability of certain package versions. You could try switching to the default PyPI source to see if it resolves the issue.

  3. Dependency Conflicts: The project has a dependency on rapidocr_onnxruntime version ~1.3.8 [1]. Check if this dependency might be causing conflicts with onnxruntime version 1.20.1.

  4. Regenerate Lockfile: Try regenerating the lockfile by running poetry lock --no-cache to ensure that all dependencies are resolved correctly.

  5. Check ABI Tags: Verify that the ABI tags for the onnxruntime wheels are compatible with your system. This can be a common issue if the package doesn't have pre-built wheels for your specific environment.

By addressing these points, you should be able to identify the root cause of the installation issue.

To continue talking to Dosu, mention @dosu.


Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Bug Report | Other

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working
Projects
None yet
Development

No branches or pull requests

1 participant