Skip to content

Conversation

blefo
Copy link
Member

@blefo blefo commented Aug 25, 2025

This PR adds multimodal support to the chat completion endpoint

  • The chat completion endpoint now accepts images in base64 format, enabling text + image model inputs.
  • The request body format aligns with the OpenAI client specification.
  • Web search is updated to support both web search and multimodal inputs.

Copy link
Member

@jcabrero jcabrero left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

You need to check the API Model changes as they break tool calling and make them more similar to what OpenAI support for image_url is.

The PR is overall good 👍 Good job.

Comment on lines -11 to -12
class Message(ChatCompletionMessage):
role: Literal["system", "user", "assistant", "tool"] # type: ignore
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

class Message (ChatCompletionMessageParam):
    pass

@jcabrero jcabrero linked an issue Oct 8, 2025 that may be closed by this pull request
3 tasks
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.

Add new models to the catalogue

2 participants