mirror of
https://github.com/langgenius/dify-official-plugins.git
synced 2026-07-21 17:45:23 -04:00
Agent node cannot run successfully when the model was configured as a local LLM service #52
Reference in New Issue
Block a user
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?
Originally created by @panys-aircas on GitHub (Mar 10, 2025).
Self Checks
Dify version
1.0.0
Cloud or Self Hosted
Self Hosted (Docker)
Steps to reproduce
I test run the agent node, it return messages as below:
状态
FAIL
运行时间
0.089s
总 token 数
0 Tokens
Failed to transform agent message: PluginInvokeError: {"args":{},"error_type":"ValidationError","message":"1 validation error for ReActParams\nmodel.entity\n Input should be a valid dictionary or instance of AIModelEntity [type=model_type, input_value=None, input_type=NoneType]\n For further information visit https://errors.pydantic.dev/2.8/v/model_type"}
It seems the entity was null that address to this error.
✔️ Expected Behavior
No response
❌ Actual Behavior
No response
@dosubot[bot] commented on GitHub (Mar 10, 2025):
Hey @panys-aircas! 👋 I'm here to help you with bug fixes, answer questions, and even guide you on how to contribute. Let's squash those bugs together!
I found two similar unsolved discussions that might be relevant to your issue:
For the "ValidationError" you're encountering when the model is configured as a local LLM service in a self-hosted Dify version 1.0.0 setup, a potential solution is to switch from the doubao-pro-128k model to the Deepseek model. This change should prevent the validation error from occurring while maintaining the same workflow configuration [3].
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
@panys-aircas commented on GitHub (Mar 11, 2025):
how to solve this problem
@HZJprince commented on GitHub (Mar 19, 2025):
same
@xiaoleijian commented on GitHub (Mar 20, 2025):
+1
@SushiRoll53 commented on GitHub (Apr 1, 2025):
This problem still happening in 1.1.3 in both platforms, self-hosted and cloud. On the agent node using gpt-4o-mini with the model
Azure OpenAI Service Model@haobin-ihealth commented on GitHub (Apr 7, 2025):
yes, when i used version 1.13 with azure openai gpt4-o-mini model, it return same error. but when i used gpt4-o , it successful.
@Nov1c444 commented on GitHub (Apr 18, 2025):
Could you please provider your agent plugin's version? Maybe update the plugin's version could solve the issue
@SushiRoll53 commented on GitHub (Apr 18, 2025):
Updating the agent strategy to the most recent version, worked for me 👍
@Nov1c444 commented on GitHub (Apr 20, 2025):
Does this solution resolve your issue? If so, could you please close the Issue? @panys-aircas