Skip to content

feat(model/omni): name change input video representation_compact parameter #199

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.

Sign up for GitHub

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

Merged
luk384090-cloud merged 1 commit into from
Sep 17, 2026
Merged

feat(model/omni): name change input video representation_compact parameter #199

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 7 additions & 10 deletions dashscope/audio/qwen_omni/omni_realtime.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -414,7 +414,7 @@ def update_session(
transcription_params: TranscriptionParams = None,
input_audio_config: AudioFormatConfig = None,
output_audio_config: AudioFormatConfig = None,
input_video_representation_compactness: int = None,
input_video_representation_compact: str = None,
**kwargs,
) -> None:
"""
Expand Down Expand Up @@ -461,11 +461,10 @@ def update_session(
type (pcm/wav) and sample rate (8000/16000/24000/48000), as well
as free extension parameters via ``extra_params``. When provided,
the request emits the ``session.audio.output.format`` structure.
input_video_representation_compactness: int
input video representation compactness. When provided, the request
emits ``session.video.input.representation_compactness``. No strict
client-side validation is performed so newly supported values can
be used without upgrading the SDK.
input_video_representation_compact: str
input video representation compact setting. When provided, the
request emits ``session.video.input.representation_compact`` and
passes the string value through without client-side validation.

Notes
-----
Expand Down Expand Up @@ -516,12 +515,10 @@ def update_session(
}
if transcription_params is not None:
self._apply_transcription_params(transcription_params)
if input_video_representation_compactness is not None:
if input_video_representation_compact is not None:
self.config["video"] = {
"input": {
"representation_compactness": (
input_video_representation_compactness
),
"representation_compact": input_video_representation_compact,
},
}
self.config.update(kwargs)
Expand Down
Loading