Esta página foi traduzida pela API Cloud Translation.
Switch to English

Como analisar documentos

Depois de criar (treinar) um modelo, solicite as previsões dele. Uma previsão ocorre quando você envia um documento ao modelo e solicita que ele o analise de acordo com o objetivo desse modelo (classificação, extração de entidade ou análise de sentimento).

O AutoML Natural Language é compatível com a previsão on-line, em que você envia um único documento e o modelo retorna a análise de maneira síncrona e por previsão, em que você envia uma coleção de documentos analisados de maneira assíncrona.

Predição on-line

Para fazer uma previsão usando a interface do usuário do AutoML Natural Language:

  1. Clique no ícone de lâmpada na barra de navegação esquerda para exibir os modelos disponíveis.

    Para ver os modelos de outro projeto, selecione o projeto na lista suspensa na parte superior direita da barra de título.

  2. Clique na linha do modelo que você quer usar para analisar o documento.

  3. Clique na guia Testar e usar logo abaixo da barra de título.

  4. Digite o texto que quer analisar na caixa de texto ou clique em Selecione um arquivo no Cloud Storage e digite o caminho do Cloud Storage para um arquivo PDF ou TIFF.

  5. Clique em Previsão.

Amostras de código

Classificação

REST e linha de comando

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-id: ID do projeto
  • location-id: o local do recurso, us-central1 para o local Global ou eu para a União Europeia
  • model-id: o ID do modelo

Método HTTP e URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

Corpo JSON da solicitação:

{
  "payload" : {
    "textSnippet": {
      "content": "Google, headquartered in Mountain View, unveiled the new Android phone at the Consumer Electronic Show.  Sundar Pichai said in his keynote that users love their new Android phones.",
        "mime_type": "text/plain"
      },
  }
}

Para enviar a solicitação, expanda uma destas opções:

Você receberá uma resposta JSON semelhante a esta:

{
  "payload": [
    {
      "displayName": "Technology",
      "classification": {
        "score": 0.8989502
      }
    },
    {
      "displayName": "Automobiles",
      "classification": {
        "score": 0.10098731
      }
    }
  ]
}

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print(u"Predicted class name: {}".format(annotation_payload.display_name))
    print(
        u"Predicted class score: {}".format(annotation_payload.classification.score)
    )

Java

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageTextClassificationPredict {

  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Predicted class name: %s\n", annotationPayload.getDisplayName());
        System.out.format(
            "Predicted sentiment score: %.2f\n\n",
            annotationPayload.getClassification().getScore());
      }
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'test/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(`Predicted class name: ${annotationPayload.displayName}`);
    console.log(
      `Predicted class score: ${annotationPayload.classification.score}`
    );
  }
}

predict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// languageTextClassificationPredict does a prediction for text classification.
func languageTextClassificationPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TCN123456789..."
	// content := "text to classify"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %v", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Predicted class name: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Predicted class score: %v\n", payload.GetClassification().GetScore())
	}

	return nil
}

Outros idiomas

C# : Siga as instruções: Instruções de configuração do C# na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para .NET.

PHP : Siga as instruções: Instruções de configuração do PHP na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para PHP.

Raquel : Siga as instruções: Instruções de configuração do Ruby na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para Ruby.

Extração de entidade

REST e linha de comando

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-id: ID do projeto
  • location-id: o local do recurso, us-central1 para o local Global ou eu para a União Europeia
  • model-id: o ID do modelo

Método HTTP e URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

Corpo JSON da solicitação:

{
  "payload" : {
    "textSnippet": {
      "content": "The Wilms tumor-suppressor gene, WT1, plays a key role in urogenital development, and WT1 dysfunction is implicated in both neoplastic and nonneoplastic (glomerulosclerosis) disease. The analysis of diseases linked specifically with WT1 mutations, such as Denys-Drash syndrome (DDS), can provide valuable insight concerning the role of WT1 in development and disease.  We report that heterozygosity for a targeted murine Wt1 allele, Wt1 (tmT396), which truncates ZF3 at codon 396, induces mesangial sclerosis characteristic of DDS in adult heterozygous and chimeric mice. Male genital defects also were evident and there was a single case of Wilms tumor in which the transcript of the nontargeted allele showed an exon 9 skipping event, implying a causal link between Wt1 dysfunction and Wilms tumorigenesis in mice. However, the mutant WT1 (tmT396) protein accounted for only 5% of WT1 in both heterozygous embryonic stem cells and the WT. This has implications regarding the mechanism by which the mutant allele exerts its effect.",
      "mime_type": "text/plain"
      },
   }
}

Para enviar a solicitação, expanda uma destas opções:

Você receberá uma resposta JSON semelhante a esta:

{
  "annotations": [
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 67,
          "start_offset": 62
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 158,
          "start_offset": 141
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 330,
          "start_offset": 290
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 337,
          "start_offset": 332
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 627,
          "start_offset": 610
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 754,
          "start_offset": 749
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 875,
          "start_offset": 865
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 968,
          "start_offset": 951
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1553,
          "start_offset": 1548
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1652,
          "start_offset": 1606
        }
      },
      "display_name": "CompositeMention"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1833,
          "start_offset": 1826
        }
      },
      "display_name": "DiseaseClass"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1860,
          "start_offset": 1843
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 1930,
          "start_offset": 1913
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2129,
          "start_offset": 2111
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2188,
          "start_offset": 2160
        }
      },
      "display_name": "SpecificDisease"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2260,
          "start_offset": 2243
        }
      },
      "display_name": "Modifier"
    },
    {
      "text_extraction": {
        "text_segment": {
          "end_offset": 2356,
          "start_offset": 2339
        }
      },
      "display_name": "Modifier"
    }
  ],
}

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print("Text Extract Entity Types: {}".format(annotation_payload.display_name))
    print("Text Score: {}".format(annotation_payload.text_extraction.score))
    text_segment = annotation_payload.text_extraction.text_segment
    print("Text Extract Entity Content: {}".format(text_segment.content))
    print("Text Start Offset: {}".format(text_segment.start_offset))
    print("Text End Offset: {}".format(text_segment.end_offset))

Java

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSegment;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageEntityExtractionPredict {

  static void predict() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
                  .setContent(content)
                  .setMimeType("text/plain") // Types: text/plain, text/html
                  .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Text Extract Entity Type: %s\n", annotationPayload.getDisplayName());
        System.out.format("Text score: %.2f\n", annotationPayload.getTextExtraction().getScore());
        TextSegment textSegment = annotationPayload.getTextExtraction().getTextSegment();
        System.out.format("Text Extract Entity Content: %s\n", textSegment.getContent());
        System.out.format("Text Start Offset: %s\n", textSegment.getStartOffset());
        System.out.format("Text End Offset: %s\n\n", textSegment.getEndOffset());
      }
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'test/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(
      `Text Extract Entity Types: ${annotationPayload.displayName}`
    );
    console.log(`Text Score: ${annotationPayload.textExtraction.score}`);
    const textSegment = annotationPayload.textExtraction.textSegment;
    console.log(`Text Extract Entity Content: ${textSegment.content}`);
    console.log(`Text Start Offset: ${textSegment.startOffset}`);
    console.log(`Text End Offset: ${textSegment.endOffset}`);
  }
}

predict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// languageEntityExtractionPredict does a prediction for text entity extraction.
func languageEntityExtractionPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TEN123456789..."
	// content := "text to extract entities"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %v", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Text extract entity types: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Text score: %v\n", payload.GetTextExtraction().GetScore())
		textSegment := payload.GetTextExtraction().GetTextSegment()
		fmt.Fprintf(w, "Text extract entity content: %v\n", textSegment.GetContent())
		fmt.Fprintf(w, "Text start offset: %v\n", textSegment.GetStartOffset())
		fmt.Fprintf(w, "Text end offset: %v\n", textSegment.GetEndOffset())
	}

	return nil
}

Outros idiomas

C# : Siga as instruções: Instruções de configuração do C# na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para .NET.

PHP : Siga as instruções: Instruções de configuração do PHP na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para PHP.

Raquel : Siga as instruções: Instruções de configuração do Ruby na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para Ruby.

Análise de sentimento

REST e linha de comando

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-id: ID do projeto
  • location-id: o local do recurso, us-central1 para o local Global ou eu para a União Europeia
  • model-id: o ID do modelo

Método HTTP e URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:predict

Corpo JSON da solicitação:

{
  "payload" : {
    "textSnippet": {
      "content": "Enjoy your vacation!",
         "mime_type": "text/plain"
       },
  }
}

Para enviar a solicitação, expanda uma destas opções:

Você receberá um código de status bem-sucedido (2xx) e uma resposta vazia.

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# content = "text to predict"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = automl.AutoMlClient.model_path(project_id, "us-central1", model_id)

# Supported mime_types: 'text/plain', 'text/html'
# https://cloud.google.com/automl/docs/reference/rpc/google.cloud.automl.v1#textsnippet
text_snippet = automl.TextSnippet(content=content, mime_type="text/plain")
payload = automl.ExamplePayload(text_snippet=text_snippet)

response = prediction_client.predict(name=model_full_id, payload=payload)

for annotation_payload in response.payload:
    print("Predicted class name: {}".format(annotation_payload.display_name))
    print(
        "Predicted sentiment score: {}".format(
            annotation_payload.text_sentiment.sentiment
        )
    )

Java

import com.google.cloud.automl.v1.AnnotationPayload;
import com.google.cloud.automl.v1.ExamplePayload;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.PredictRequest;
import com.google.cloud.automl.v1.PredictResponse;
import com.google.cloud.automl.v1.PredictionServiceClient;
import com.google.cloud.automl.v1.TextSnippet;
import java.io.IOException;

class LanguageSentimentAnalysisPredict {

  static void predict() throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String content = "text to predict";
    predict(projectId, modelId, content);
  }

  static void predict(String projectId, String modelId, String content) throws IOException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);

      // For available mime types, see:
      // https://cloud.google.com/automl/docs/reference/rest/v1/projects.locations.models/predict#textsnippet
      TextSnippet textSnippet =
          TextSnippet.newBuilder()
              .setContent(content)
              .setMimeType("text/plain") // Types: text/plain, text/html
              .build();
      ExamplePayload payload = ExamplePayload.newBuilder().setTextSnippet(textSnippet).build();
      PredictRequest predictRequest =
          PredictRequest.newBuilder().setName(name.toString()).setPayload(payload).build();

      PredictResponse response = client.predict(predictRequest);

      for (AnnotationPayload annotationPayload : response.getPayloadList()) {
        System.out.format("Predicted class name: %s\n", annotationPayload.getDisplayName());
        System.out.format(
            "Predicted sentiment score: %d\n", annotationPayload.getTextSentiment().getSentiment());
      }
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const content = 'text to predict'

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function predict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    payload: {
      textSnippet: {
        content: content,
        mimeType: 'text/plain', // Types: 'test/plain', 'text/html'
      },
    },
  };

  const [response] = await client.predict(request);

  for (const annotationPayload of response.payload) {
    console.log(`Predicted class name: ${annotationPayload.displayName}`);
    console.log(
      `Predicted sentiment score: ${annotationPayload.textSentiment.sentiment}`
    );
  }
}

predict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// languageSentimentAnalysisPredict does a prediction for text sentiment analysis.
func languageSentimentAnalysisPredict(w io.Writer, projectID string, location string, modelID string, content string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "TST123456789..."
	// content := "text to analyze sentiment"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.PredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		Payload: &automlpb.ExamplePayload{
			Payload: &automlpb.ExamplePayload_TextSnippet{
				TextSnippet: &automlpb.TextSnippet{
					Content:  content,
					MimeType: "text/plain", // Types: "text/plain", "text/html"
				},
			},
		},
	}

	resp, err := client.Predict(ctx, req)
	if err != nil {
		return fmt.Errorf("Predict: %v", err)
	}

	for _, payload := range resp.GetPayload() {
		fmt.Fprintf(w, "Predicted class name: %v\n", payload.GetDisplayName())
		fmt.Fprintf(w, "Predicted sentiment score: %v\n", payload.GetTextSentiment().GetSentiment())
	}

	return nil
}

Outros idiomas

C# : Siga as instruções: Instruções de configuração do C# na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para .NET.

PHP : Siga as instruções: Instruções de configuração do PHP na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para PHP.

Raquel : Siga as instruções: Instruções de configuração do Ruby na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para Ruby.

Previsão em lote

Se você quiser usar seu modelo para fazer a previsão assíncrona de alta capacidade em um corpus de documentos, use o método batchPredict. Os métodos de previsão em lote exigem que você especifique URIs de entrada e saída que apontam para locais nos buckets do Cloud Storage.

O URI de entrada aponta para um arquivo CSV ou JSONL, que especifica o conteúdo a ser analisado. Use um arquivo CSV para classificação e análise de sentimento. Use um arquivo JSONL para extração de entidade. A saída especifica um local em que o AutoML Natural Language salva os resultados da previsão em lote.

Para classificação e análise de sentimento, crie um arquivo CSV com uma única coluna que liste os arquivos de entrada para classificar, um arquivo por linha. O arquivo CSV e cada arquivo de entrada precisam ser armazenados no seu bucket do Cloud Storage.

gs://folder/text1.txt
gs://folder/text2.pdf

Para a extração de entidades, você precisa preparar um arquivo JSONL que contenha todo o conteúdo a ser analisado, seja ele in-line ou como links para arquivos armazenados em um bucket do Cloud Storage. O exemplo a seguir mostra o conteúdo in-line incluído no arquivo JSONL. Cada item precisa incluir um ID exclusivo.

{ "id": "0", "text_snippet": { "content": "First item content to be analyzed." } }
{ "id": "1", "text_snippet": { "content": "Second item content to be analyzed." } }
...
{ "id": "n", "text_snippet": { "content": "Last item content to be analyzed." } }

No exemplo a seguir, mostramos um arquivo JSONL que contém links para arquivos de entrada, que precisam estar em intervalos do Cloud Storage.

{ "document": { "input_config": { "gcs_source": { "input_uris": [ "gs://folder/document1.pdf" ] } } } }
{ "document": { "input_config": { "gcs_source": { "input_uris": [ "gs://folder/document2.tif" ] } } } }
...

REST e LINHA DE CMD

Antes de usar os dados da solicitação abaixo, faça as substituições a seguir:

  • project-id: ID do projeto
  • location-id: o local do recurso, us-central1 para o local Global ou eu para a União Europeia
  • model-id: o ID do modelo

Método HTTP e URL:

POST https://automl.googleapis.com/v1/projects/project-id/locations/location-id/models/model-id:batchPredict

Corpo JSON da solicitação:

{
  "input_config": { "gcs_source": { "input_uris": [ "csv-file-URI"] } },
  "output_config": { "gcs_destination": { "output_uri_prefix": "dest-dir-URI" } }
 }

Para enviar a solicitação, expanda uma destas opções:

Será exibido um código semelhante a este. Você pode usar o código da operação para saber o status da tarefa. Veja um exemplo em Como saber o status de uma operação.

{
  "name": "projects/434039606874/locations/us-central1/operations/TCN8195786061721370625",
  "metadata": {
    "@type": "type.googleapis.com/google.cloud.automl.v1beta1.OperationMetadata",
    "createTime": "2019-03-13T15:37:49.972372Z",
    "updateTime": "2019-03-13T15:37:49.972372Z"
  }
}

Python

from google.cloud import automl

# TODO(developer): Uncomment and set the following variables
# project_id = "YOUR_PROJECT_ID"
# model_id = "YOUR_MODEL_ID"
# input_uri = "gs://YOUR_BUCKET_ID/path/to/your/input/csv_or_jsonl"
# output_uri = "gs://YOUR_BUCKET_ID/path/to/save/results/"

prediction_client = automl.PredictionServiceClient()

# Get the full path of the model.
model_full_id = f"projects/{project_id}/locations/us-central1/models/{model_id}"

gcs_source = automl.GcsSource(input_uris=[input_uri])

input_config = automl.BatchPredictInputConfig(gcs_source=gcs_source)
gcs_destination = automl.GcsDestination(output_uri_prefix=output_uri)
output_config = automl.BatchPredictOutputConfig(gcs_destination=gcs_destination)

response = prediction_client.batch_predict(
    name=model_full_id, input_config=input_config, output_config=output_config
)

print("Waiting for operation to complete...")
print(
    f"Batch Prediction results saved to Cloud Storage bucket. {response.result()}"
)

Java

import com.google.api.gax.longrunning.OperationFuture;
import com.google.cloud.automl.v1.BatchPredictInputConfig;
import com.google.cloud.automl.v1.BatchPredictOutputConfig;
import com.google.cloud.automl.v1.BatchPredictRequest;
import com.google.cloud.automl.v1.BatchPredictResult;
import com.google.cloud.automl.v1.GcsDestination;
import com.google.cloud.automl.v1.GcsSource;
import com.google.cloud.automl.v1.ModelName;
import com.google.cloud.automl.v1.OperationMetadata;
import com.google.cloud.automl.v1.PredictionServiceClient;
import java.io.IOException;
import java.util.concurrent.ExecutionException;

class BatchPredict {

  static void batchPredict() throws IOException, ExecutionException, InterruptedException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "YOUR_PROJECT_ID";
    String modelId = "YOUR_MODEL_ID";
    String inputUri = "gs://YOUR_BUCKET_ID/path_to_your_input_csv_or_jsonl";
    String outputUri = "gs://YOUR_BUCKET_ID/path_to_save_results/";
    batchPredict(projectId, modelId, inputUri, outputUri);
  }

  static void batchPredict(String projectId, String modelId, String inputUri, String outputUri)
      throws IOException, ExecutionException, InterruptedException {
    // Initialize client that will be used to send requests. This client only needs to be created
    // once, and can be reused for multiple requests. After completing all of your requests, call
    // the "close" method on the client to safely clean up any remaining background resources.
    try (PredictionServiceClient client = PredictionServiceClient.create()) {
      // Get the full path of the model.
      ModelName name = ModelName.of(projectId, "us-central1", modelId);
      GcsSource gcsSource = GcsSource.newBuilder().addInputUris(inputUri).build();
      BatchPredictInputConfig inputConfig =
          BatchPredictInputConfig.newBuilder().setGcsSource(gcsSource).build();
      GcsDestination gcsDestination =
          GcsDestination.newBuilder().setOutputUriPrefix(outputUri).build();
      BatchPredictOutputConfig outputConfig =
          BatchPredictOutputConfig.newBuilder().setGcsDestination(gcsDestination).build();
      BatchPredictRequest request =
          BatchPredictRequest.newBuilder()
              .setName(name.toString())
              .setInputConfig(inputConfig)
              .setOutputConfig(outputConfig)
              .build();

      OperationFuture<BatchPredictResult, OperationMetadata> future =
          client.batchPredictAsync(request);

      System.out.println("Waiting for operation to complete...");
      BatchPredictResult response = future.get();
      System.out.println("Batch Prediction results saved to specified Cloud Storage bucket.");
    }
  }
}

Node.js

/**
 * TODO(developer): Uncomment these variables before running the sample.
 */
// const projectId = 'YOUR_PROJECT_ID';
// const location = 'us-central1';
// const modelId = 'YOUR_MODEL_ID';
// const inputUri = 'gs://YOUR_BUCKET_ID/path_to_your_input_csv_or_jsonl';
// const outputUri = 'gs://YOUR_BUCKET_ID/path_to_save_results/';

// Imports the Google Cloud AutoML library
const {PredictionServiceClient} = require('@google-cloud/automl').v1;

// Instantiates a client
const client = new PredictionServiceClient();

async function batchPredict() {
  // Construct request
  const request = {
    name: client.modelPath(projectId, location, modelId),
    inputConfig: {
      gcsSource: {
        inputUris: [inputUri],
      },
    },
    outputConfig: {
      gcsDestination: {
        outputUriPrefix: outputUri,
      },
    },
  };

  const [operation] = await client.batchPredict(request);

  console.log('Waiting for operation to complete...');
  // Wait for operation to complete.
  const [response] = await operation.promise();
  console.log(
    `Batch Prediction results saved to Cloud Storage bucket. ${response}`
  );
}

batchPredict();

Go

import (
	"context"
	"fmt"
	"io"

	automl "cloud.google.com/go/automl/apiv1"
	automlpb "google.golang.org/genproto/googleapis/cloud/automl/v1"
)

// batchPredict does a batch prediction.
func batchPredict(w io.Writer, projectID string, location string, modelID string, inputURI string, outputURI string) error {
	// projectID := "my-project-id"
	// location := "us-central1"
	// modelID := "ICN123456789..."
	// inputURI := "gs://BUCKET_ID/path_to_your_input_csv_or_jsonl"
	// outputURI := "gs://BUCKET_ID/path_to_save_results/"

	ctx := context.Background()
	client, err := automl.NewPredictionClient(ctx)
	if err != nil {
		return fmt.Errorf("NewPredictionClient: %v", err)
	}
	defer client.Close()

	req := &automlpb.BatchPredictRequest{
		Name: fmt.Sprintf("projects/%s/locations/%s/models/%s", projectID, location, modelID),
		InputConfig: &automlpb.BatchPredictInputConfig{
			Source: &automlpb.BatchPredictInputConfig_GcsSource{
				GcsSource: &automlpb.GcsSource{
					InputUris: []string{inputURI},
				},
			},
		},
		OutputConfig: &automlpb.BatchPredictOutputConfig{
			Destination: &automlpb.BatchPredictOutputConfig_GcsDestination{
				GcsDestination: &automlpb.GcsDestination{
					OutputUriPrefix: outputURI,
				},
			},
		},
		Params: map[string]string{
			"score_threshold": "0.8", // [0.0-1.0] Only produce results higher than this value
		},
	}

	op, err := client.BatchPredict(ctx, req)
	if err != nil {
		return fmt.Errorf("BatchPredict: %v", err)
	}
	fmt.Fprintf(w, "Processing operation name: %q\n", op.Name())

	resp, err := op.Wait(ctx)
	if err != nil {
		return fmt.Errorf("Wait: %v", err)
	}

	fmt.Fprintf(w, "Batch Prediction results saved to Cloud Storage bucket.\n")
	fmt.Fprintf(w, "%v", resp)

	return nil
}

Outros idiomas

C# : Siga as instruções: Instruções de configuração do C# na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para .NET.

PHP : Siga as instruções: Instruções de configuração do PHP na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para PHP.

Raquel : Siga as instruções: Instruções de configuração do Ruby na página de bibliotecas de cliente e acesse aDocumentação de referência do AutoML Natural Language para Ruby.