langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-21 17:45:23 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

Error when in Workflow with Azure AI Studio's DeepSeek-R1 Model #31

New Issue
Closed
opened 2026-02-16 10:17:49 -05:00 by yindo · 4 comments
yindo commented 2026-02-16 10:17:49 -05:00
Owner
Copy Link
Copy Source

Originally created by @orzmoe on GitHub (Mar 1, 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

Version 1.0.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Failed to add messages, and encountered a runtime error

Image

1 validation error for LLMNodeData model.mode Field required [type=missing, input_value={'completion_params': {'t...studio/azure_ai_studio'}, input_type=dict] For further information visit https://errors.pydantic.dev/2.9/v/missing

✔️ Expected Behavior

Normal usage Azure AI Studio's DeepSeek-R1 Model

❌ Actual Behavior

Execution failed

Originally created by @orzmoe on GitHub (Mar 1, 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 Version 1.0.0 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce Failed to add messages, and encountered a runtime error ![Image](https://github.com/user-attachments/assets/60becb01-5294-4fed-9e7e-7c053090919e) ``` 1 validation error for LLMNodeData model.mode Field required [type=missing, input_value={'completion_params': {'t...studio/azure_ai_studio'}, input_type=dict] For further information visit https://errors.pydantic.dev/2.9/v/missing ``` ### ✔️ Expected Behavior Normal usage Azure AI Studio's DeepSeek-R1 Model ### ❌ Actual Behavior Execution failed
yindo closed this issue 2026-02-16 10:17:49 -05:00
yindo commented 2026-02-16 10:17:49 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Mar 1, 2025):

Hey @orzmoe! 👋 I'm here to help you with your bug report. I can assist with solving bugs, answering questions, and even becoming a contributor. Let's tackle this together!

To resolve the validation error in the LLMNodeData model's completion_params dictionary when using Azure AI Studio's DeepSeek-R1 Model in a self-hosted Docker environment, ensure that the completion_params dictionary is correctly structured according to the validation rules. Specifically, the completion_params must include a stop key with a list value containing fewer than 4 elements. Here's an example of a valid completion_params dictionary:

completion_params = {
    "stop": ["\n", "END", "STOP"]
}

Additionally, verify that the model configuration is properly set up, including ensuring that the single_retrieval_config is not None, and that the model name, provider, and credentials are correctly specified and initialized [1][2].

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 (Mar 1, 2025): <!-- Greeting --> Hey @orzmoe! 👋 I'm here to help you with your bug report. I can assist with solving bugs, answering questions, and even becoming a contributor. Let's tackle this together! <!-- Answer --> To resolve the validation error in the `LLMNodeData` model's `completion_params` dictionary when using Azure AI Studio's DeepSeek-R1 Model in a self-hosted Docker environment, ensure that the `completion_params` dictionary is correctly structured according to the validation rules. Specifically, the `completion_params` must include a `stop` key with a list value containing fewer than 4 elements. Here's an example of a valid `completion_params` dictionary: ```python completion_params = { "stop": ["\n", "END", "STOP"] } ``` Additionally, verify that the model configuration is properly set up, including ensuring that the `single_retrieval_config` is not `None`, and that the model name, provider, and credentials are correctly specified and initialized <sup>[[1]](https://github.com/langgenius/dify/blob/main/api/core/app/app_config/easy_ui_based_app/model_config/manager.py)</sup><sup>[[2]](https://github.com/langgenius/dify/blob/main/api/core/workflow/nodes/knowledge_retrieval/knowledge_retrieval_node.py)</sup>. <!-- 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/d9357684-aaf6-43b2-b853-5d3ff91b1968?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/d9357684-aaf6-43b2-b853-5d3ff91b1968?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/d9357684-aaf6-43b2-b853-5d3ff91b1968?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/d9357684-aaf6-43b2-b853-5d3ff91b1968?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/d9357684-aaf6-43b2-b853-5d3ff91b1968?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/d9357684-aaf6-43b2-b853-5d3ff91b1968?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/d9357684-aaf6-43b2-b853-5d3ff91b1968?feedback_type=other)</sup>
yindo commented 2026-02-16 10:17:49 -05:00
Author
Owner
Copy Link
Copy Source

@orzmoe commented on GitHub (Mar 1, 2025):

It appears that the issue has been resolved in PR langgenius/dify#13325. However, after updating to version 1.0.0, the Azure AI Studio plugin does not seem to have been updated.

@orzmoe commented on GitHub (Mar 1, 2025): It appears that the issue has been resolved in [PR langgenius/dify#13325](https://github.com/langgenius/dify/pull/13325). However, after updating to version 1.0.0, the Azure AI Studio plugin does not seem to have been updated.
yindo commented 2026-02-16 10:17:49 -05:00
Author
Owner
Copy Link
Copy Source

@bcat95 commented on GitHub (Mar 28, 2025):

confirm it still bug in version 1.1.3
deepseek, llma
Image

@bcat95 commented on GitHub (Mar 28, 2025): confirm it still bug in version 1.1.3 deepseek, llma ![Image](https://github.com/user-attachments/assets/0f75a896-003f-4d37-b2ea-270b9d2ae5a7)
yindo commented 2026-02-16 10:17:49 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Aug 20, 2025):

Hi, @orzmoe. 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 a runtime error in Dify v1.0.0 related to the Azure AI Studio DeepSeek-R1 model due to a missing "mode" field in LLMNodeData.
  • I suggested checking the completion_params dictionary for a valid "stop" key and correct model setup.
  • You mentioned the issue was fixed in PR #13325, but the Azure AI Studio plugin was not updated in v1.0.0.
  • Another user confirmed the bug still exists in version 1.1.3, indicating the fix may not have been fully applied.

Next Steps:

  • Please confirm if this issue is still relevant with the latest version of the dify-official-plugins repository by commenting here.
  • If I don’t hear back within 5 days, this issue will be automatically closed.

Thanks for your understanding and contribution!

@dosubot[bot] commented on GitHub (Aug 20, 2025): Hi, @orzmoe. 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 a runtime error in Dify v1.0.0 related to the Azure AI Studio DeepSeek-R1 model due to a missing "mode" field in LLMNodeData. - I suggested checking the completion_params dictionary for a valid "stop" key and correct model setup. - You mentioned the issue was fixed in PR #13325, but the Azure AI Studio plugin was not updated in v1.0.0. - Another user confirmed the bug still exists in version 1.1.3, indicating the fix may not have been fully applied. **Next Steps:** - Please confirm if this issue is still relevant with the latest version of the dify-official-plugins repository by commenting here. - If I don’t hear back within 5 days, this issue will be automatically closed. Thanks 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#31
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?