-
Notifications
You must be signed in to change notification settings - Fork 4.5k
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
0.68 dify use xinference rerank model,not get the right result #4432
Comments
To address the issue with the xinference rerank model not producing the expected results after updating to Dify version 0.6.8, ensure the model is correctly installed and configured in your Docker self-hosted setup. Follow these steps:
Consider external factors that might affect the model's performance, such as network issues, server availability, and compatibility with your hardware. Review any specific error messages or logs for clues to the problem. If the issue persists, providing more details like specific error messages, input data, and scenarios where the model fails can help pinpoint the problem. For more detailed guidance, refer to the Dify documentation.
|
the rerank model in xinference is just on running,because when i use the dify 0.6.7,the rerank model has good rag result,but when i update the dify to the 0.6.8,then use the rerank model ,the rag result is not right. |
To resolve the issue with the rerank model in Xinference not producing the expected results after updating Dify to version 0.6.8, consider the following steps:
If these steps do not resolve the issue, you might consider temporarily rolling back to Dify 0.6.7, where the rerank model was working as expected, while investigating further or seeking support from the Dify or Xinference communities. For more detailed troubleshooting, providing specific error messages or scenarios where the model fails could be helpful.
|
Self Checks
Dify version
0.6.8
Cloud or Self Hosted
Self Hosted (Docker)
Steps to reproduce
the dify updated from 0.6.7 to 0.6.8
in 0.6.7 ,the answer returns ok
✔️ Expected Behavior
return the answer
❌ Actual Behavior
the result is wrong
The text was updated successfully, but these errors were encountered: