[PR #11721] chore: the consistency of MultiModalPromptMessageContent #27337

Closed
opened 2026-02-21 20:41:19 -05:00 by yindo · 0 comments
Owner

Original Pull Request: https://github.com/langgenius/dify/pull/11721

State: closed
Merged: Yes


Summary

Tip

Close issue syntax: Fixes #<issue number> or Resolves #<issue number>, see documentation for more details.

Currently, when files are sent to various LLM, each model may require different parameters. For instance, some models expect:
{"image_url": url or base64 with mime_type}
Others might require separated mime_type and b64data, formatted as:
{"mime_type": "", "data": ""}
And some may utilize a parameter that specifies the format:
{"format": "..."}
To enhance the readability of the code and to maintain consistency across all MultiModalPromptMessageContent, it is proposed that we standardize these parameters.

Additionally, it is suggested to change the MULTIMODAL_SEND_IMAGE_FORMAT and MULTIMODAL_SEND_VIDEO_FORMAT to a unified MULTIMODAL_SEND_FORMAT, as it seems that a single environment variable would suffice for all purposes.

Screenshots

Before After
... ...

Checklist

Important

Please review the checklist below before submitting your pull request.

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods
**Original Pull Request:** https://github.com/langgenius/dify/pull/11721 **State:** closed **Merged:** Yes --- # Summary > [!Tip] > Close issue syntax: `Fixes #<issue number>` or `Resolves #<issue number>`, see [documentation](https://docs.github.com/en/issues/tracking-your-work-with-issues/linking-a-pull-request-to-an-issue#linking-a-pull-request-to-an-issue-using-a-keyword) for more details. Currently, when files are sent to various LLM, each model may require different parameters. For instance, some models expect: `{"image_url": url or base64 with mime_type}` Others might require separated mime_type and b64data, formatted as: `{"mime_type": "", "data": ""}` And some may utilize a parameter that specifies the format: {"format": "..."} To enhance the readability of the code and to maintain consistency across all MultiModalPromptMessageContent, it is proposed that we standardize these parameters. Additionally, it is suggested to change the `MULTIMODAL_SEND_IMAGE_FORMAT` and `MULTIMODAL_SEND_VIDEO_FORMAT` to a unified `MULTIMODAL_SEND_FORMAT`, as it seems that a single environment variable would suffice for all purposes. # Screenshots | Before | After | |--------|-------| | ... | ... | # Checklist > [!IMPORTANT] > Please review the checklist below before submitting your pull request. - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs) - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!) - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change. - [x] I've updated the documentation accordingly. - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods
yindo added the pull-request label 2026-02-21 20:41:19 -05:00
yindo closed this issue 2026-02-21 20:41:19 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#27337