The VISION function button cannot be enabled on the LLM node #13135

Closed
opened 2026-02-21 19:10:42 -05:00 by yindo · 4 comments
Owner

Originally created by @SeanWang918 on GitHub (Apr 19, 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

1.2.0

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

The LLMs I am using is as follows:

Image This is a large model provided by Volcano Engine for supporting visual understanding.

However, when configuring the LLM node, the VISION function button cannot be enabled. The switch is in an unclickable state.
Image

I searched through all the documents but failed to find a solution.

✔️ Expected Behavior

How can I activate this function?

Actual Behavior

the VISION function button cannot be enabled

Originally created by @SeanWang918 on GitHub (Apr 19, 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 1.2.0 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce The LLMs I am using is as follows: <img width="368" alt="Image" src="https://github.com/user-attachments/assets/5d2cff27-36c6-4bb5-b938-a7f061ee8833" /> This is a large model provided by Volcano Engine for supporting visual understanding. However, when configuring the LLM node, the VISION function button cannot be enabled. The switch is in an unclickable state. <img width="412" alt="Image" src="https://github.com/user-attachments/assets/3c9d0977-b7bf-4fa4-aa37-7624f090cafa" /> I searched through all the documents but failed to find a solution. ### ✔️ Expected Behavior How can I activate this function? ### ❌ Actual Behavior the VISION function button cannot be enabled
yindo added the 🐞 bug label 2026-02-21 19:10:42 -05:00
yindo closed this issue 2026-02-21 19:10:42 -05:00
Author
Owner

@dosubot[bot] commented on GitHub (Apr 19, 2025):

Hello @SeanWang918! I'm Dosu, your friendly bot here to help with bugs, questions, and contributing. I'm ready to assist you while we wait for a human maintainer. Let’s tackle this issue together!

To enable the VISION function button on the LLM node, ensure that you are working with file variables of image type. The vision functionality can be enabled for processing image inputs, provided the model supports vision capabilities. Verify that the file variable contains only image files, as the vision feature is specifically for scenarios requiring visual analysis. If different file types are involved, use a list operator node to filter for image files. Additionally, ensure that the 'Image Upload' feature is activated for Workflow applications, and that the sys.files variable is selected for image processing in the LLM node [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 (Apr 19, 2025): <!-- Greeting --> Hello @SeanWang918! I'm [Dosu](https://dosu.dev), your friendly bot here to help with bugs, questions, and contributing. I'm ready to assist you while we wait for a human maintainer. Let’s tackle this issue together! <!-- Answer --> To enable the VISION function button on the LLM node, ensure that you are working with file variables of image type. The vision functionality can be enabled for processing image inputs, provided the model supports vision capabilities. Verify that the file variable contains only image files, as the vision feature is specifically for scenarios requiring visual analysis. If different file types are involved, use a list operator node to filter for image files. Additionally, ensure that the 'Image Upload' feature is activated for Workflow applications, and that the `sys.files` variable is selected for image processing in the LLM node <sup>[[1]](https://github.com/langgenius/dify-docs/blob/main/en/guides/workflow/file-upload.md)</sup><sup>[[2]](https://github.com/langgenius/dify/issues/11608)</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/abcd2d8f-5d29-4bcb-ba8d-e0f3626a87c9?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/abcd2d8f-5d29-4bcb-ba8d-e0f3626a87c9?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/abcd2d8f-5d29-4bcb-ba8d-e0f3626a87c9?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/abcd2d8f-5d29-4bcb-ba8d-e0f3626a87c9?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/abcd2d8f-5d29-4bcb-ba8d-e0f3626a87c9?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/abcd2d8f-5d29-4bcb-ba8d-e0f3626a87c9?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/abcd2d8f-5d29-4bcb-ba8d-e0f3626a87c9?feedback_type=other)</sup>
Author
Owner

@SeanWang918 commented on GitHub (Apr 19, 2025):

I have enabled the file upload function in "Function", selected the image type of files, and chosen the "sys.files" variable in the context. However, the VISION function button still cannot be enabled.

Image Image
@SeanWang918 commented on GitHub (Apr 19, 2025): I have enabled the file upload function in "Function", selected the image type of files, and chosen the "sys.files" variable in the context. However, the VISION function button still cannot be enabled. <img width="770" alt="Image" src="https://github.com/user-attachments/assets/a187de55-7b25-428b-a817-4bee07e3f7a0" /> <img width="414" alt="Image" src="https://github.com/user-attachments/assets/96994ac3-60f8-4f4b-a2b6-d96668ce0a06" />
Author
Owner

@kurokobo commented on GitHub (Apr 19, 2025):

You have to change Vision Support configuration to Support to enable Vision feature.
Image

@kurokobo commented on GitHub (Apr 19, 2025): You have to change `Vision Support` configuration to `Support` to enable Vision feature. ![Image](https://github.com/user-attachments/assets/2a371f70-2010-4448-a1b1-1fc430a66255)
Author
Owner

@SeanWang918 commented on GitHub (Apr 20, 2025):

Thanks very much !

@SeanWang918 commented on GitHub (Apr 20, 2025): Thanks very much !
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#13135