langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

{"arxiv_search": "tool invoke error: Model models/Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4/ is disabled."} #6513

New Issue
Closed
opened 2026-02-21 18:16:04 -05:00 by yindo · 1 comment
yindo commented 2026-02-21 18:16:04 -05:00
Owner
Copy Link
Copy Source

Originally created by @yyf0910 on GitHub (Nov 2, 2024).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

0.10.2

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

I used xinference for large model deployment with the model qwen2.5-32b-gptq-int4-instruct. My custom-made tool works fine for invocation, but using the built-in tool results in an error.
屏幕截图 2024-11-02 194903
{"arxiv_search": "tool invoke error: Model models/Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4/ is disabled."}

✔️ Expected Behavior

Using the tool to retrieve papers from the paper database.

❌ Actual Behavior

Error indicating model abnormality

Originally created by @yyf0910 on GitHub (Nov 2, 2024). ### Self Checks - [X] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [X] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [X] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [X] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [X] Please do not modify this template :) and fill in all the required fields. ### Dify version 0.10.2 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce I used xinference for large model deployment with the model qwen2.5-32b-gptq-int4-instruct. My custom-made tool works fine for invocation, but using the built-in tool results in an error. ![屏幕截图 2024-11-02 194903](https://github.com/user-attachments/assets/da96572f-f7da-4776-b774-1fa5dde7734e) {"arxiv_search": "tool invoke error: Model models/Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4/ is disabled."} ### ✔️ Expected Behavior Using the tool to retrieve papers from the paper database. ### ❌ Actual Behavior Error indicating model abnormality
yindo added the 🐞 bug label 2026-02-21 18:16:04 -05:00
yindo closed this issue 2026-02-21 18:16:04 -05:00
yindo commented 2026-02-21 18:16:04 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Nov 2, 2024):

@yyf0910 Hello there! I'm here to help you with any bugs, questions, or contributions. Let's work together to solve the issue you're experiencing.

The error message you're encountering, "Model models/Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4/ is disabled," suggests that the model is marked as 'disabled' in your Dify setup. This can happen if the hosting provider for the model is not enabled. Dify uses a configuration system to manage model availability, and a model can be marked as 'disabled' if the corresponding hosting provider is not enabled through specific configuration flags [1].

To resolve this issue, you should:

  1. Check Configuration Flags: Ensure that the necessary configuration flags for enabling the hosting provider are set correctly. For example, flags like HOSTED_AZURE_OPENAI_ENABLED, HOSTED_OPENAI_TRIAL_ENABLED, or similar should be set to enable the provider.

  2. Verify Model Deployment: Make sure that the model is correctly deployed and accessible. This involves checking the network configuration and ensuring that the Dify container can access the Xinference endpoint where the model is hosted [2].

  3. Model UID and Settings: Double-check that the model UID and other settings in Dify are correctly configured to match the deployed model.

If these steps do not resolve the issue, you might want to look into any logs or error messages from the Dify setup or Xinference to gather more details on why the model is being marked as disabled.

To continue talking to Dosu, mention @dosu.

@dosubot[bot] commented on GitHub (Nov 2, 2024): <!-- Greeting --> @yyf0910 Hello there! I'm here to help you with any bugs, questions, or contributions. Let's work together to solve the issue you're experiencing. <!-- Answer --> The error message you're encountering, "Model models/Qwen/Qwen2.5-32B-Instruct-GPTQ-Int4/ is disabled," suggests that the model is marked as 'disabled' in your Dify setup. This can happen if the hosting provider for the model is not enabled. Dify uses a configuration system to manage model availability, and a model can be marked as 'disabled' if the corresponding hosting provider is not enabled through specific configuration flags <sup>[[1]](https://github.com/langgenius/dify/blob/main/api/core/hosting_configuration.py)</sup>. To resolve this issue, you should: 1. **Check Configuration Flags**: Ensure that the necessary configuration flags for enabling the hosting provider are set correctly. For example, flags like `HOSTED_AZURE_OPENAI_ENABLED`, `HOSTED_OPENAI_TRIAL_ENABLED`, or similar should be set to enable the provider. 2. **Verify Model Deployment**: Make sure that the model is correctly deployed and accessible. This involves checking the network configuration and ensuring that the Dify container can access the Xinference endpoint where the model is hosted <sup>[[2]](https://github.com/langgenius/dify-docs/blob/main/en/development/models-integration/xinference.md)</sup>. 3. **Model UID and Settings**: Double-check that the model UID and other settings in Dify are correctly configured to match the deployed model. If these steps do not resolve the issue, you might want to look into any logs or error messages from the Dify setup or Xinference to gather more details on why the model is being marked as disabled. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.*
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#6513
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?