The preprocessed example that AutoML actually makes prediction on. Empty if AutoML does not preprocess the input example. For AutoML Natural Language (Classification, Entity Extraction, and Sentiment Analysis), if the input is a document, the recognized text is returned in thedocument_textproperty.
Additional domain-specific prediction response metadata. AutoML Vision Object Detectionmax_bounding_box_count: (int64) The maximum number of bounding boxes to return per image. AutoML Natural Language Sentiment Analysissentiment_score: (float, deprecated) A value between -1 and 1, -1 maps to least positive sentiment, while 1 maps to the most positive one and the higher the score, the more positive the sentiment in the document is. Yet these values are relative to the training data, so e.g. if all data was positive then -1 is also positive (though the least).sentiment_scoreis not the same as "score" and "magnitude" from Sentiment Analysis in the Natural Language API.
getPayload
Prediction result.
AutoML Translation and AutoML Natural Language Sentiment Analysis
return precisely one payload.
The preprocessed example that AutoML actually makes prediction on.
Empty if AutoML does not preprocess the input example.
For AutoML Natural Language (Classification, Entity Extraction, and
Sentiment Analysis), if the input is a document, the recognized text is
returned in thedocument_textproperty.
The preprocessed example that AutoML actually makes prediction on.
Empty if AutoML does not preprocess the input example.
For AutoML Natural Language (Classification, Entity Extraction, and
Sentiment Analysis), if the input is a document, the recognized text is
returned in thedocument_textproperty.
AutoML Vision Object Detectionmax_bounding_box_count: (int64) The maximum number of bounding boxes to return per image.
AutoML Natural Language Sentiment Analysissentiment_score: (float, deprecated) A value between -1 and 1,
-1 maps to least positive sentiment, while 1 maps to the most positive
one and the higher the score, the more positive the sentiment in the
document is. Yet these values are relative to the training data, so
e.g. if all data was positive then -1 is also positive (though
the least).sentiment_scoreis not the same as "score" and "magnitude"
from Sentiment Analysis in the Natural Language API.
AutoML Vision Object Detectionmax_bounding_box_count: (int64) The maximum number of bounding boxes to return per image.
AutoML Natural Language Sentiment Analysissentiment_score: (float, deprecated) A value between -1 and 1,
-1 maps to least positive sentiment, while 1 maps to the most positive
one and the higher the score, the more positive the sentiment in the
document is. Yet these values are relative to the training data, so
e.g. if all data was positive then -1 is also positive (though
the least).sentiment_scoreis not the same as "score" and "magnitude"
from Sentiment Analysis in the Natural Language API.
[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-09-04 UTC."],[],[],null,["# Cloud AutoML V1 Client - Class PredictResponse (2.0.5)\n\nVersion latestkeyboard_arrow_down\n\n- [2.0.5 (latest)](/php/docs/reference/cloud-automl/latest/V1.PredictResponse)\n- [2.0.4](/php/docs/reference/cloud-automl/2.0.4/V1.PredictResponse)\n- [1.6.5](/php/docs/reference/cloud-automl/1.6.5/V1.PredictResponse)\n- [1.5.4](/php/docs/reference/cloud-automl/1.5.4/V1.PredictResponse)\n- [1.4.17](/php/docs/reference/cloud-automl/1.4.17/V1.PredictResponse) \nReference documentation and code samples for the Cloud AutoML V1 Client class PredictResponse.\n\nResponse message for [PredictionService.Predict](/php/docs/reference/cloud-automl/latest/V1.Client.PredictionServiceClient#_Google_Cloud_AutoMl_V1_Client_PredictionServiceClient__predict__).\n\nGenerated from protobuf message `google.cloud.automl.v1.PredictResponse`\n\nNamespace\n---------\n\nGoogle \\\\ Cloud \\\\ AutoMl \\\\ V1\n\nMethods\n-------\n\n### __construct\n\nConstructor.\n\n### getPayload\n\nPrediction result.\n\nAutoML Translation and AutoML Natural Language Sentiment Analysis\nreturn precisely one payload.\n\n### setPayload\n\nPrediction result.\n\nAutoML Translation and AutoML Natural Language Sentiment Analysis\nreturn precisely one payload.\n\n### getPreprocessedInput\n\nThe preprocessed example that AutoML actually makes prediction on.\n\nEmpty if AutoML does not preprocess the input example.\nFor AutoML Natural Language (Classification, Entity Extraction, and\nSentiment Analysis), if the input is a document, the recognized text is\nreturned in the\n[document_text](/php/docs/reference/cloud-automl/latest/V1.Document#_Google_Cloud_AutoMl_V1_Document__getDocumentText__)\nproperty.\n\n### hasPreprocessedInput\n\n### clearPreprocessedInput\n\n### setPreprocessedInput\n\nThe preprocessed example that AutoML actually makes prediction on.\n\nEmpty if AutoML does not preprocess the input example.\nFor AutoML Natural Language (Classification, Entity Extraction, and\nSentiment Analysis), if the input is a document, the recognized text is\nreturned in the\n[document_text](/php/docs/reference/cloud-automl/latest/V1.Document#_Google_Cloud_AutoMl_V1_Document__getDocumentText__)\nproperty.\n\n### getMetadata\n\nAdditional domain-specific prediction response metadata.\n\nAutoML Vision Object Detection\n`max_bounding_box_count`\n: (int64) The maximum number of bounding boxes to return per image.\nAutoML Natural Language Sentiment Analysis\n`sentiment_score`\n: (float, deprecated) A value between -1 and 1,\n-1 maps to least positive sentiment, while 1 maps to the most positive\none and the higher the score, the more positive the sentiment in the\ndocument is. Yet these values are relative to the training data, so\ne.g. if all data was positive then -1 is also positive (though\nthe least).\n`sentiment_score` is not the same as \"score\" and \"magnitude\"\nfrom Sentiment Analysis in the Natural Language API.\n\n### setMetadata\n\nAdditional domain-specific prediction response metadata.\n\nAutoML Vision Object Detection\n`max_bounding_box_count`\n: (int64) The maximum number of bounding boxes to return per image.\nAutoML Natural Language Sentiment Analysis\n`sentiment_score`\n: (float, deprecated) A value between -1 and 1,\n-1 maps to least positive sentiment, while 1 maps to the most positive\none and the higher the score, the more positive the sentiment in the\ndocument is. Yet these values are relative to the training data, so\ne.g. if all data was positive then -1 is also positive (though\nthe least).\n`sentiment_score` is not the same as \"score\" and \"magnitude\"\nfrom Sentiment Analysis in the Natural Language API."]]
