Skip to content

feat(example): support server video inputs and Gemma text tool calls#2291

Open
abetlen wants to merge 1 commit into
mainfrom
feat/server-video-inputs
Open

feat(example): support server video inputs and Gemma text tool calls#2291
abetlen wants to merge 1 commit into
mainfrom
feat/server-video-inputs

Conversation

@abetlen

@abetlen abetlen commented Jun 8, 2026

Copy link
Copy Markdown
Owner

Adds server video input support and fixes Gemma text tool call normalization.

  • Adds input_video/video_url media parsing for MTMD requests.
  • Keeps upstream MTMD video contexts alive through tokenization and caches video frame embeddings separately.
  • Normalizes parsed Gemma text-tool arguments into raw text tool inputs.

@abetlen abetlen force-pushed the feat/server-video-inputs branch from 888ba5f to 99cc9d0 Compare June 8, 2026 15:28
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.

1 participant