Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

making TextMessage take a list[dict[str, str | dict[str, Any]]] as value because MultimodalConversableAgent was breaking while processing images. #560

Conversation

shriyanshagnihotri
Copy link
Collaborator

making TextMessage take a list[dict[str, str | dict[str, Any]]] as value because MultimodalConversableAgent was breaking while processing images.

Why are these changes needed?

making TextMessage take a list[dict[str, str | dict[str, Any]]] as value because MultimodalConversableAgent was breaking while processing images. Now with TextMessage taking dict with object value this should not breaking existing functionality of MultimodalConversableAgent

Related issue number

#558

Checks

…lues can be another nested dict representing image url, hence both str and dict should be allowed issue ag2ai#558
@davorrunje
Copy link
Collaborator

The test is broken due to the new version of CrewAI, I'll fix it in a separate PR soon. This is good to go 👍

@davorrunje davorrunje self-requested a review January 20, 2025 20:44
@marklysze
Copy link
Collaborator

marklysze commented Jan 20, 2025

The test is broken due to the new version of CrewAI, I'll fix it in a separate PR soon. This is good to go 👍

I have merged a PR for it :), #562

@davorrunje davorrunje added this pull request to the merge queue Jan 20, 2025
Merged via the queue into ag2ai:main with commit 8d29269 Jan 20, 2025
220 of 226 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants