langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-22 01:55:27 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

Issue happed when add whisper model from openAI compatible API #191

New Issue
Closed
opened 2026-02-16 10:18:23 -05:00 by yindo · 3 comments
yindo commented 2026-02-16 10:18:23 -05:00
Owner
Copy Link
Copy Source

Originally created by @fanfan-lucky on GitHub (Apr 13, 2025).

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

1.0.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Dify+vllm to add "whisper-large-v3-turbo" model through openAI API compatible, Dify version is 1.0.0, vllm version is 0.8.3, from dify api log, I can see error "WARNING [Dummy-5043] [provider_configuration.py:963] - get custom model schema failed, {"code":0,"message":"success","data":{"model_schema":null}}", so what could be the problem? thanks for the feedback.

✔️ Expected Behavior

No response

❌ Actual Behavior

No response

Originally created by @fanfan-lucky on GitHub (Apr 13, 2025). ### 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 1.0.0 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce Dify+vllm to add "whisper-large-v3-turbo" model through openAI API compatible, Dify version is 1.0.0, vllm version is 0.8.3, from dify api log, I can see error "WARNING [Dummy-5043] [provider_configuration.py:963] - get custom model schema failed, {"code":0,"message":"success","data":{"model_schema":null}}", so what could be the problem? thanks for the feedback. ### ✔️ Expected Behavior _No response_ ### ❌ Actual Behavior _No response_
yindo closed this issue 2026-02-16 10:18:23 -05:00
yindo commented 2026-02-16 10:18:24 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Apr 13, 2025):

The error "get custom model schema failed" in the Dify API log when adding the "whisper-large-v3-turbo" model could be due to several reasons:

  1. Credentials Issue: Ensure that the credentials used to access the model are correct and valid. Incorrect or missing credentials can lead to a failure in retrieving the model schema.

  2. Model Type or Name Mismatch: Verify that the model_type and model name for "whisper-large-v3-turbo" are correctly specified in the configuration. Any mismatch can cause the schema retrieval to fail.

  3. Exception Details: Check the specific exception message in the logs for more detailed information on the failure. The message {ex} would provide more context, but it is not included in the provided log snippet.

Additionally, there is a similar closed issue where the suggested solution was to ensure that 'function call support' is enabled in the model configuration settings through the Dify UI. For models like Ollama, this setting is configured at the model level, not in the agent settings [1]. This might be relevant if similar settings apply to the "whisper-large-v3-turbo" model.

Review these aspects to troubleshoot the issue further.

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

@dosubot[bot] commented on GitHub (Apr 13, 2025): <!-- Answer --> The error "get custom model schema failed" in the Dify API log when adding the "whisper-large-v3-turbo" model could be due to several reasons: 1. **Credentials Issue**: Ensure that the credentials used to access the model are correct and valid. Incorrect or missing credentials can lead to a failure in retrieving the model schema. 2. **Model Type or Name Mismatch**: Verify that the `model_type` and `model` name for "whisper-large-v3-turbo" are correctly specified in the configuration. Any mismatch can cause the schema retrieval to fail. 3. **Exception Details**: Check the specific exception message in the logs for more detailed information on the failure. The message `{ex}` would provide more context, but it is not included in the provided log snippet. Additionally, there is a similar closed issue where the suggested solution was to ensure that 'function call support' is enabled in the model configuration settings through the Dify UI. For models like Ollama, this setting is configured at the model level, not in the agent settings <sup>[[1]](https://github.com/langgenius/dify/issues/13151)</sup>. This might be relevant if similar settings apply to the "whisper-large-v3-turbo" model. Review these aspects to troubleshoot the issue further. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/051664bf-50ab-4a7c-ae7c-12316ead270b?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/051664bf-50ab-4a7c-ae7c-12316ead270b?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/051664bf-50ab-4a7c-ae7c-12316ead270b?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/051664bf-50ab-4a7c-ae7c-12316ead270b?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/051664bf-50ab-4a7c-ae7c-12316ead270b?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/051664bf-50ab-4a7c-ae7c-12316ead270b?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/051664bf-50ab-4a7c-ae7c-12316ead270b?feedback_type=other)</sup>
yindo commented 2026-02-16 10:18:24 -05:00
Author
Owner
Copy Link
Copy Source

@fanfan-lucky commented on GitHub (Apr 14, 2025):

I upgrade dify version to 1.2.0, issue still be there. configuration please see the attached picture

Image
who can help me? thanks!

@fanfan-lucky commented on GitHub (Apr 14, 2025): I upgrade dify version to 1.2.0, issue still be there. configuration please see the attached picture ![Image](https://github.com/user-attachments/assets/9449f821-9f95-4351-8084-fb268a34379e) who can help me? thanks!
yindo commented 2026-02-16 10:18:24 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Aug 17, 2025):

Hi, @fanfan-lucky. I'm Dosu, and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale.

Issue Summary:

  • You reported an error "get custom model schema failed" when adding the "whisper-large-v3-turbo" model via OpenAI-compatible API in Dify v1.0.0 and v1.2.0.
  • Despite success messages, the model schema returned is null, preventing proper usage.
  • I suggested verifying credentials, model type/name, and enabling function call support.
  • You confirmed the issue persists after upgrading to Dify v1.2.0 and provided a configuration screenshot.
  • No resolution or further updates have been provided since.

Next Steps:

  • Please let me know if this issue is still relevant with the latest version of dify-official-plugins by commenting here to keep the discussion open.
  • Otherwise, this issue will be automatically closed in 5 days.

Thank you for your understanding and contribution!

@dosubot[bot] commented on GitHub (Aug 17, 2025): Hi, @fanfan-lucky. I'm [Dosu](https://dosu.dev), and I'm helping the dify-official-plugins team manage their backlog and am marking this issue as stale. **Issue Summary:** - You reported an error "get custom model schema failed" when adding the "whisper-large-v3-turbo" model via OpenAI-compatible API in Dify v1.0.0 and v1.2.0. - Despite success messages, the model schema returned is null, preventing proper usage. - I suggested verifying credentials, model type/name, and enabling function call support. - You confirmed the issue persists after upgrading to Dify v1.2.0 and provided a configuration screenshot. - No resolution or further updates have been provided since. **Next Steps:** - Please let me know if this issue is still relevant with the latest version of dify-official-plugins by commenting here to keep the discussion open. - Otherwise, this issue will be automatically closed in 5 days. Thank you for your understanding and contribution!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
bug
bug
dependencies
documentation
enhancement
good first issue
invalid
pull-request
Mirrored from GitHub Pull Request
 question
stale
No Label
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-official-plugins#191
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?