langgenius/dify-official-plugins
1
0
Fork 0
mirror of https://github.com/langgenius/dify-official-plugins.git synced 2026-07-22 10:05:23 -04:00
Code Issues 54 Packages Projects Releases Wiki Activity

[Feature]: OpenAI API Compatible: support video modal type #831

New Issue
Closed
opened 2026-02-16 10:20:39 -05:00 by yindo · 3 comments
yindo commented 2026-02-16 10:20:39 -05:00
Owner
Copy Link
Copy Source

Originally created by @AkiraVoid on GitHub (Nov 25, 2025).

Self Checks

  • I have read the Contributing Guide and Language Policy.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report, otherwise it will be closed.
  • 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.

I am using OpenAI API Compatible 0.0.25 and tried to upload file through Vision field and User Prompt, non of them being properly analyzed.

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 @AkiraVoid on GitHub (Nov 25, 2025). ### Self Checks - [x] I have read the [Contributing Guide](https://github.com/langgenius/dify/blob/main/CONTRIBUTING.md) and [Language Policy](https://github.com/langgenius/dify/issues/1542). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify-official-plugins/issues), including closed ones. - [x] I confirm that I am using English to submit this report, otherwise it will be closed. - [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. I am using OpenAI API Compatible 0.0.25 and tried to upload file through Vision field and User Prompt, non of them being properly analyzed. ### 2. Additional context or comments _No response_ ### 3. Can you help us with this feature? - [ ] I am interested in contributing to this feature.
yindo added the enhancement label 2026-02-16 10:20:39 -05:00
yindo closed this issue 2026-02-16 10:20:39 -05:00
yindo commented 2026-02-16 10:20:39 -05:00
Author
Owner
Copy Link
Copy Source

@AkiraVoid commented on GitHub (Dec 1, 2025):

@dosubot

@AkiraVoid commented on GitHub (Dec 1, 2025): @dosubot
yindo commented 2026-02-16 10:20:39 -05:00
Author
Owner
Copy Link
Copy Source

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

Here’s what’s happening: the OpenAI API Compatible plugin (oaicompat_dify_app) currently only supports plain text in the 'content' field and doesn’t handle structured or multimodal data like images or videos. This means file uploads through Vision or User Prompt fields aren’t analyzed as you’d expect—especially for video, which is only supported by a few providers (those with a video icon), and even then, not via base64 transfer like images are. There’s no built-in workaround for true multimodal support in this plugin right now; you’d need to preprocess files to plain text or use image URLs in your prompts if possible details video limitation.

If you need OpenAI-compatible API support with vision or multimodal models, check out alternative plugins like Regolo.ai, which support some vision models reference. For image uploads, make sure vision/image upload is enabled in both your app and model/provider configs, as misconfiguration can also cause silent failures troubleshooting.

If you can share whether your main need is for video, image, or both, I can help with more targeted troubleshooting or configuration steps.

To reply, just mention @dosu.

How did I do? Good | Irrelevant | Incorrect | Verbose | Hallucination | Report 🐛 | Other

Open in Cursor Join Discord Share on X

@dosubot[bot] commented on GitHub (Dec 1, 2025): <!-- Answer --> Here’s what’s happening: the OpenAI API Compatible plugin (oaicompat_dify_app) currently only supports plain text in the 'content' field and doesn’t handle structured or multimodal data like images or videos. This means file uploads through Vision or User Prompt fields aren’t analyzed as you’d expect—especially for video, which is only supported by a few providers (those with a video icon), and even then, not via base64 transfer like images are. There’s no built-in workaround for true multimodal support in this plugin right now; you’d need to preprocess files to plain text or use image URLs in your prompts if possible [details](https://github.com/langgenius/dify-official-plugins/issues/2073) [video limitation](https://github.com/langgenius/dify/issues/22115). If you need OpenAI-compatible API support with vision or multimodal models, check out alternative plugins like Regolo.ai, which support some vision models [reference](https://github.com/langgenius/dify-official-plugins/issues/1781). For image uploads, make sure vision/image upload is enabled in both your app and model/provider configs, as misconfiguration can also cause silent failures [troubleshooting](https://github.com/langgenius/dify/issues/22619). If you can share whether your main need is for video, image, or both, I can help with more targeted troubleshooting or configuration steps. <!-- Dosu Comment Footer --> *To reply, just mention [@dosu](https://go.dosu.dev/dosubot).* --- <sup>How did I do? [Good](https://app.dosu.dev/response-feedback/51b2fe20-36dc-41c8-8f48-aad9e93ef417?feedback_type=great_response) | [Irrelevant](https://app.dosu.dev/response-feedback/51b2fe20-36dc-41c8-8f48-aad9e93ef417?feedback_type=irrelevant_answer) | [Incorrect](https://app.dosu.dev/response-feedback/51b2fe20-36dc-41c8-8f48-aad9e93ef417?feedback_type=incorrect_sources) | [Verbose](https://app.dosu.dev/response-feedback/51b2fe20-36dc-41c8-8f48-aad9e93ef417?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/51b2fe20-36dc-41c8-8f48-aad9e93ef417?feedback_type=hallucination) | [Report 🐛](https://app.dosu.dev/response-feedback/51b2fe20-36dc-41c8-8f48-aad9e93ef417?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/51b2fe20-36dc-41c8-8f48-aad9e93ef417?feedback_type=other)</sup> [![Open in Cursor](https://dosu.dev/dosu-in-cursor.svg)](https://cursor.com/link/prompt?text=Here%E2%80%99s%20what%E2%80%99s%20happening%3A%20the%20OpenAI%20API%20Compatible%20plugin%20%28oaicompat_dify_app%29%20currently%20only%20supports%20plain%20text%20in%20the%20%27content%27%20field%20and%20doesn%E2%80%99t%20handle%20structured%20or%20multimodal%20data%20like%20images%20or%20videos.%20This%20means%20file%20uploads%20through%20Vision%20or%20User%20Prompt%20fields%20aren%E2%80%99t%20analyzed%20as%20you%E2%80%99d%20expect%E2%80%94especially%20for%20video%2C%20which%20is%20only%20supported%20by%20a%20few%20providers%20%28those%20with%20a%20video%20icon%29%2C%20and%20even%20then%2C%20not%20via%20base64%20transfer%20like%20images%20are.%20There%E2%80%99s%20no%20built-in%20workaround%20for%20true%20multimodal%20support%20in%20this%20plugin%20right%20now%3B%20you%E2%80%99d%20need%20to%20preprocess%20files%20to%20plain%20text%20or%20use%20image%20URLs%20in%20your%20prompts%20if%20possible%C2%A0%5Bdetails%5D%28https%3A//github.com/langgenius/dify-official-plugins/issues/2073%29%C2%A0%5Bvideo%20limitation%5D%28https%3A//github.com/langgenius/dify/issues/22115%29.%0A%0AIf%20you%20need%20OpenAI-compatible%20API%20support%20with%20vision%20or%20multimodal%20models%2C%20check%20out%20alternative%20plugins%20like%20Regolo.ai%2C%20which%20support%20some%20vision%20models%C2%A0%5Breference%5D%28https%3A//github.com/langgenius/dify-official-plugins/issues/1781%29.%20For%20image%20uploads%2C%20make%20sure%20vision/image%20upload%20is%20enabled%20in%20both%20your%20app%20and%20model/provider%20configs%2C%20as%20misconfiguration%20can%20also%20cause%20silent%20failures%C2%A0%5Btroubleshooting%5D%28https%3A//github.com/langgenius/dify/issues/22619%29.%0A%0AIf%20you%20can%20share%20whether%20your%20main%20need%20is%20for%20video%2C%20image%2C%20or%20both%2C%20I%20can%20help%20with%20more%20targeted%20troubleshooting%20or%20configuration%20steps.)&nbsp;[![Join Discord](https://img.shields.io/badge/join-5865F2?logo=discord&logoColor=white&label=)](https://go.dosu.dev/discord-bot)&nbsp;[![Share on X](https://img.shields.io/badge/X-share-black)](https://twitter.com/intent/tweet?text=%40dosu_ai%20helped%20me%20solve%20this%20issue!&url=https%3A//github.com/langgenius/dify-official-plugins/issues/2127)
yindo commented 2026-02-16 10:20:39 -05:00
Author
Owner
Copy Link
Copy Source

@AkiraVoid commented on GitHub (Dec 4, 2025):

Closed as mentioned in dify-plugin-sdks#254.

@AkiraVoid commented on GitHub (Dec 4, 2025): Closed as mentioned in [dify-plugin-sdks#254](https://github.com/langgenius/dify-plugin-sdks/issues/254).
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 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-official-plugins#831
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?