fix: preserve multimodal message format for DashScope Qwen-VL models #14711
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
|
|
| if isinstance(message.get("content"), list): | ||
| transformed_messages.append(message) | ||
| else: | ||
| transformed_messages.append({ |
There was a problem hiding this comment.
your else statement removes the logic to convent content list to string @stonyme
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The default
_transform_messagesinOpenAIGPTConfigflattens messagecontent, causing Qwen-VL models on DashScope to lose image inputs when
text and images are sent together.
This patch overrides
_transform_messagesinDashScopeChatConfigto:qwen-vl.contentso that text–imagemultimodal messages are passed through unchanged.
This ensures Qwen-VL models can correctly process combined text and image
inputs as intended.
#14631