langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-23 04:55:28 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

need support hunyuan-turbo #5597

New Issue
Closed
opened 2026-02-21 18:11:48 -05:00 by yindo · 3 comments
yindo commented 2026-02-21 18:11:48 -05:00
Owner
Copy Link
Copy Source

Originally created by @xiandan-erizo on GitHub (Sep 13, 2024).

Self Checks

  • 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.

1. Is this request related to a challenge you're experiencing? Tell me about your story.

Yes, I need to use the Hunyuan-Turbo model, but it is currently not supported.

2. Additional context or comments

No response

3. Can you help us with this feature?

  • I am interested in contributing to this feature.
Originally created by @xiandan-erizo on GitHub (Sep 13, 2024). ### Self Checks - [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. ### 1. Is this request related to a challenge you're experiencing? Tell me about your story. Yes, I need to use the Hunyuan-Turbo model, but it is currently not supported. ### 2. Additional context or comments _No response_ ### 3. Can you help us with this feature? - [X] I am interested in contributing to this feature.
yindo added the 💪 enhancement label 2026-02-21 18:11:48 -05:00
yindo closed this issue 2026-02-21 18:11:48 -05:00
yindo commented 2026-02-21 18:11:49 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Sep 13, 2024):

Hey @xiandan-erizo! 👋 I'm here to help you with any bugs, questions, or contributions you might have regarding the Hunyuan-Turbo model. I'm an AI bot and I can assist you while you wait for a human maintainer. Let me know how I can help!

I found some relevant information that might help you with integrating the Hunyuan-Turbo model into Dify.

To support a new model like Hunyuan-Turbo, the specific requirements or dependencies include:

  1. Model Type: The model should be of type llm.
  2. Features: The model should support the following features:
    • agent-thought
    • tool-call
    • multi-tool-call
    • stream-tool-call
  3. Model Properties:
    • Mode: chat
    • Context Size: 256000
  4. Parameter Rules:
    • temperature: Use the template temperature.
    • top_p: Use the template top_p.
    • max_tokens: Use the template max_tokens, with a default of 1024, minimum of 1, and maximum of 256000.
    • enable_enhance: A boolean parameter to enable enhancement features like external search, with a default value of true. This feature allows the model to perform external searches to enhance the generation results, which can reduce response latency, especially for the initial token in streaming outputs. However, in some scenarios, the response quality might decrease when this feature is disabled [1][2][3].

Additionally, Dify has a modular architecture that facilitates the addition of new models. The "Model Runtime" module provides an interface for invoking and authenticating various models, decoupling models from upstream and downstream processes, and allowing for horizontal expansion for developers. This architecture supports the addition of new models by defining them in the backend without needing to modify frontend logic [4][5].

For detailed steps on how to add a new provider and models, you can refer to the documentation here [6].

I hope this helps! If you need further assistance, feel free to ask.

To continue talking to Dosu, mention @dosu.

@dosubot[bot] commented on GitHub (Sep 13, 2024): <!-- Greeting --> Hey @xiandan-erizo! 👋 I'm here to help you with any bugs, questions, or contributions you might have regarding the Hunyuan-Turbo model. I'm an AI bot and I can assist you while you wait for a human maintainer. Let me know how I can help! <!-- Answer --> I found some relevant information that might help you with integrating the Hunyuan-Turbo model into Dify. To support a new model like Hunyuan-Turbo, the specific requirements or dependencies include: 1. **Model Type**: The model should be of type `llm`. 2. **Features**: The model should support the following features: - `agent-thought` - `tool-call` - `multi-tool-call` - `stream-tool-call` 3. **Model Properties**: - Mode: `chat` - Context Size: `256000` 4. **Parameter Rules**: - `temperature`: Use the template `temperature`. - `top_p`: Use the template `top_p`. - `max_tokens`: Use the template `max_tokens`, with a default of `1024`, minimum of `1`, and maximum of `256000`. - `enable_enhance`: A boolean parameter to enable enhancement features like external search, with a default value of `true`. This feature allows the model to perform external searches to enhance the generation results, which can reduce response latency, especially for the initial token in streaming outputs. However, in some scenarios, the response quality might decrease when this feature is disabled <sup>[[1]](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-pro.yaml)</sup><sup>[[2]](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-standard.yaml)</sup><sup>[[3]](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/model_providers/hunyuan/llm/hunyuan-standard-256k.yaml)</sup>. Additionally, Dify has a modular architecture that facilitates the addition of new models. The "Model Runtime" module provides an interface for invoking and authenticating various models, decoupling models from upstream and downstream processes, and allowing for horizontal expansion for developers. This architecture supports the addition of new models by defining them in the backend without needing to modify frontend logic <sup>[[4]](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/README.md)</sup><sup>[[5]](https://github.com/langgenius/dify/blob/main/api/core/model_runtime/docs/en_US/provider_scale_out.md)</sup>. For detailed steps on how to add a new provider and models, you can refer to the documentation [here](https://github.com/langgenius/dify-docs/blob/main/en/guides/model-configuration/new-provider.md) <sup>[[6]](https://github.com/langgenius/dify-docs/blob/main/en/guides/model-configuration/new-provider.md)</sup>. I hope this helps! If you need further assistance, feel free to ask. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.*
yindo commented 2026-02-21 18:11:49 -05:00
Author
Owner
Copy Link
Copy Source

@xiandan-erizo commented on GitHub (Sep 13, 2024):

pr link https://github.com/langgenius/dify/pull/8372

@xiandan-erizo commented on GitHub (Sep 13, 2024): pr link [ https://github.com/langgenius/dify/pull/8372](url)
yindo commented 2026-02-21 18:11:49 -05:00
Author
Owner
Copy Link
Copy Source

@xiandan-erizo commented on GitHub (Sep 13, 2024):

#8372

@xiandan-erizo commented on GitHub (Sep 13, 2024): #8372
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 💪 enhancement
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#5597
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?