langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-22 20:45:26 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

LLM VISION capability CANNOT apply the HTTPS Request data to recognize #7694

New Issue
Closed
opened 2026-02-21 18:21:55 -05:00 by yindo · 1 comment
yindo commented 2026-02-21 18:21:55 -05:00
Owner
Copy Link
Copy Source

Originally created by @pychou17 on GitHub (Jan 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

0.14.2

Cloud or Self Hosted

Cloud

Steps to reproduce

  1. Add a Https Request node, and call the API which will response a binary file response.
  2. Add a LLM node afterward and enable the "Vision" capability on the node (ref image 1)
  3. Apply the "Https response.files" as the image source on the LLM Vision settings.
  4. Make the LLM read and response the summary about the files.

image
image

✔️ Expected Behavior

LLM should recognize the VISION input from the HTTPS Request and provide the correct result.

❌ Actual Behavior

LLM cannot read the files data from the https response as the VISION data.

Originally created by @pychou17 on GitHub (Jan 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 0.14.2 ### Cloud or Self Hosted Cloud ### Steps to reproduce 1. Add a Https Request node, and call the API which will response a binary file response. 2. Add a LLM node afterward and enable the "Vision" capability on the node (ref image 1) 3. Apply the "Https response.files" as the image source on the LLM Vision settings. 4. Make the LLM read and response the summary about the files. ![image](https://github.com/user-attachments/assets/3b15955c-00a1-40f4-a2cb-1c9923e7268f) ![image](https://github.com/user-attachments/assets/dc419a44-54be-4f9b-b0c2-7a0b69126918) ### ✔️ Expected Behavior LLM should recognize the VISION input from the HTTPS Request and provide the correct result. ### ❌ Actual Behavior LLM cannot read the files data from the https response as the VISION data.
yindo added the 🐞 bug label 2026-02-21 18:21:55 -05:00
yindo closed this issue 2026-02-21 18:21:55 -05:00
yindo commented 2026-02-21 18:21:55 -05:00
Author
Owner
Copy Link
Copy Source

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

Hello, @pychou17! I'm here to help you with any bugs, questions, or contributions you have. Let's tackle this issue together!

The issue you're experiencing with the LLM Vision capability not recognizing the HTTPS Request data might be related to how the binary file response is being handled. Here are a few things to consider:

  1. File Handling: Ensure that the binary file response from the HTTPS Request node is correctly converted into a format that the LLM Vision can process. The supported image formats include JPG, JPEG, PNG, GIF, WEBP, and SVG [1].

  2. Variable Configuration: Verify that the variable used to store the file from the HTTPS response is correctly referenced in the LLM Vision settings. Instead of using sys.files, consider creating a custom file-type variable in the "Start" node and referencing this variable in the LLM Vision settings for better compatibility [2].

  3. Workflow Configuration: Double-check the workflow configuration to ensure that the file is being passed correctly between nodes. The empty "files" array in the PROCESS DATA section suggests that the file might not be correctly linked or transferred between the HTTPS Request node and the LLM node.

If these steps do not resolve the issue, it might be necessary to review the specific configurations of your nodes and ensure that all settings align with the expected input and output formats.

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other

@dosubot[bot] commented on GitHub (Jan 13, 2025): <!-- Greeting --> Hello, @pychou17! I'm here to help you with any bugs, questions, or contributions you have. Let's tackle this issue together! <!-- Answer --> The issue you're experiencing with the LLM Vision capability not recognizing the HTTPS Request data might be related to how the binary file response is being handled. Here are a few things to consider: 1. **File Handling**: Ensure that the binary file response from the HTTPS Request node is correctly converted into a format that the LLM Vision can process. The supported image formats include JPG, JPEG, PNG, GIF, WEBP, and SVG <sup>[[1]](https://github.com/langgenius/dify-docs/blob/main/en/guides/workflow/file-upload.md)</sup>. 2. **Variable Configuration**: Verify that the variable used to store the file from the HTTPS response is correctly referenced in the LLM Vision settings. Instead of using `sys.files`, consider creating a custom file-type variable in the "Start" node and referencing this variable in the LLM Vision settings for better compatibility <sup>[[2]](https://github.com/langgenius/dify-docs/blob/main/jp/llms.txt)</sup>. 3. **Workflow Configuration**: Double-check the workflow configuration to ensure that the file is being passed correctly between nodes. The empty "files" array in the PROCESS DATA section suggests that the file might not be correctly linked or transferred between the HTTPS Request node and the LLM node. If these steps do not resolve the issue, it might be necessary to review the specific configurations of your nodes and ensure that all settings align with the expected input and output formats. <!-- 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/27e67ab0-3cdc-47ed-8146-292015ffc35d?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/27e67ab0-3cdc-47ed-8146-292015ffc35d?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/27e67ab0-3cdc-47ed-8146-292015ffc35d?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/27e67ab0-3cdc-47ed-8146-292015ffc35d?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/27e67ab0-3cdc-47ed-8146-292015ffc35d?feedback_type=hallucination) | [Other](https://app.dosu.dev/response-feedback/27e67ab0-3cdc-47ed-8146-292015ffc35d?feedback_type=other)</sup>
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 🐞 bug
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#7694
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?