Types for Google Cloud Aiplatform V1beta1 Schema Predict Instance v1beta1 API

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.ImageClassificationPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Image Classification.

content()

The image bytes or Cloud Storage URI to makethe prediction on.

mime_type()

The MIME type of the content of the image.Only the images in below listed MIME types aresupported.

  • image/jpeg
  • image/gif
  • image/png
  • image/webp
  • image/bmp
  • image/tiff

  • image/vnd.microsoft.icon

  • Type

    str

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.ImageObjectDetectionPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Image Object Detection.

content()

The image bytes or Cloud Storage URI to makethe prediction on.

mime_type()

The MIME type of the content of the image.Only the images in below listed MIME types aresupported.

  • image/jpeg
  • image/gif
  • image/png
  • image/webp
  • image/bmp
  • image/tiff

  • image/vnd.microsoft.icon

  • Type

    str

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.ImageSegmentationPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Image Segmentation.

content()

The image bytes to make the predictions on.

mime_type()

The MIME type of the content of the image.Only the images in below listed MIME types aresupported.

  • image/jpeg

  • image/png

  • Type

    str

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.TextClassificationPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Text Classification.

content()

The text snippet to make the predictions on.

mime_type()

The MIME type of the text snippet. Thesupported MIME types are listed below.

  • text/plain

  • Type

    str

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.TextExtractionPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Text Extraction.

content()

The text snippet to make the predictions on.

mime_type()

The MIME type of the text snippet. Thesupported MIME types are listed below.

  • text/plain

  • Type

    str

key()

This field is only used for batch prediction.If a key is provided, the batch predictionresult will by mapped to this key. If omitted,then the batch prediction result will containthe entire input instance. Vertex AI will notcheck if keys in the request are duplicates, soit is up to the caller to ensure the keys areunique.

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

key(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.TextSentimentPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Text Sentiment.

content()

The text snippet to make the predictions on.

mime_type()

The MIME type of the text snippet. Thesupported MIME types are listed below.

  • text/plain

  • Type

    str

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.VideoActionRecognitionPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Video Action Recognition.

content()

The Google Cloud Storage location of thevideo on which to perform the prediction.

mime_type()

The MIME type of the content of the video.Only the following are supported: video/mp4video/avi video/quicktime

time_segment_start()

The beginning, inclusive, of the video’s timesegment on which to perform the prediction.Expressed as a number of seconds as measuredfrom the start of the video, with “s” appendedat the end. Fractions are allowed, up to amicrosecond precision.

time_segment_end()

The end, exclusive, of the video’s timesegment on which to perform the prediction.Expressed as a number of seconds as measuredfrom the start of the video, with “s” appendedat the end. Fractions are allowed, up to amicrosecond precision, and “inf” or “Infinity”is allowed, which means the end of the video.

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

time_segment_end(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

time_segment_start(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.VideoClassificationPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Video Classification.

content()

The Google Cloud Storage location of thevideo on which to perform the prediction.

mime_type()

The MIME type of the content of the video.Only the following are supported: video/mp4video/avi video/quicktime

time_segment_start()

The beginning, inclusive, of the video’s timesegment on which to perform the prediction.Expressed as a number of seconds as measuredfrom the start of the video, with “s” appendedat the end. Fractions are allowed, up to amicrosecond precision.

time_segment_end()

The end, exclusive, of the video’s timesegment on which to perform the prediction.Expressed as a number of seconds as measuredfrom the start of the video, with “s” appendedat the end. Fractions are allowed, up to amicrosecond precision, and “inf” or “Infinity”is allowed, which means the end of the video.

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

time_segment_end(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

time_segment_start(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

class google.cloud.aiplatform.v1beta1.schema.predict.instance_v1beta1.types.VideoObjectTrackingPredictionInstance(mapping=None, *, ignore_unknown_fields=False, **kwargs)

Bases:proto.message.Message

Prediction input format for Video Object Tracking.

content()

The Google Cloud Storage location of thevideo on which to perform the prediction.

mime_type()

The MIME type of the content of the video.Only the following are supported: video/mp4video/avi video/quicktime

time_segment_start()

The beginning, inclusive, of the video’s timesegment on which to perform the prediction.Expressed as a number of seconds as measuredfrom the start of the video, with “s” appendedat the end. Fractions are allowed, up to amicrosecond precision.

time_segment_end()

The end, exclusive, of the video’s timesegment on which to perform the prediction.Expressed as a number of seconds as measuredfrom the start of the video, with “s” appendedat the end. Fractions are allowed, up to amicrosecond precision, and “inf” or “Infinity”is allowed, which means the end of the video.

content(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

mime_type(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

time_segment_end(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

time_segment_start(: [str](https://python.readthedocs.io/en/latest/library/stdtypes.html#str )

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-10-30 UTC.