Skip to content

feat(model/omni): name change input video representation_compact parameter #274

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 #274

Show file tree
Hide file tree
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
13 changes: 7 additions & 6 deletions src/main/java/com/alibaba/dashscope/audio/omni/OmniRealtimeConfig.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,10 +51,12 @@ public class OmniRealtimeConfig {
*/
@Builder.Default OmniRealtimeAudioFormatConfig outputAudio = null;
/**
* Video input representation compactness. When set, it is serialized as {@code
* video.input.representation_compactness}.
* Video input representation aggregation mode, serialized as {@code
* video.input.representation_compact}. {@code none} preserves fine-grained video input
* representations, while {@code normal} aggregates them to reduce computational overhead when
* visual details are less important.
*/
@Builder.Default Integer inputVideoRepresentationCompactness = null;
@Builder.Default String inputVideoRepresentationCompact = null;
/** enable transcription for input audio */
@Builder.Default boolean enableInputAudioTranscription = true;
/** model used for input audio transcription */
Expand Down Expand Up @@ -111,10 +113,9 @@ public JsonObject getConfig() {
config.put(OmniRealtimeConstants.INPUT_AUDIO_FORMAT, inputAudioFormat);
config.put(OmniRealtimeConstants.OUTPUT_AUDIO_FORMAT, outputAudioFormat);
}
if (inputVideoRepresentationCompactness != null) {
if (inputVideoRepresentationCompact != null) {
Map<String, Object> videoInput = new HashMap<>();
videoInput.put(
OmniRealtimeConstants.REPRESENTATION_COMPACTNESS, inputVideoRepresentationCompactness);
videoInput.put(OmniRealtimeConstants.REPRESENTATION_COMPACT, inputVideoRepresentationCompact);
Map<String, Object> video = new HashMap<>();
video.put(OmniRealtimeConstants.VIDEO_INPUT, videoInput);
config.put(OmniRealtimeConstants.VIDEO, video);
Expand Down
4 changes: 2 additions & 2 deletions src/main/java/com/alibaba/dashscope/audio/omni/OmniRealtimeConstants.java
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,10 +17,10 @@ public class OmniRealtimeConstants {
public static final String AUDIO_FORMAT = "format";
public static final String AUDIO_FORMAT_TYPE = "type";
// Video input configuration, see session.update:
// { "video": { "input": { "representation_compactness": 1 } } }
// { "video": { "input": { "representation_compact": "none" } } }
public static final String VIDEO = "video";
public static final String VIDEO_INPUT = "input";
public static final String REPRESENTATION_COMPACTNESS = "representation_compactness";
public static final String REPRESENTATION_COMPACT = "representation_compact";
public static final String INPUT_AUDIO_TRANSCRIPTION = "input_audio_transcription";
public static final String INPUT_AUDIO_TRANSCRIPTION_MODEL = "model";
public static final String INPUT_AUDIO_TRANSCRIPTION_CORPUS = "corpus";
Expand Down
Loading