Controlled generation JSON output with predefined schema

This code sample demonstrates how to use the `response_mime_type` and `response_schema` parameters to get a response that follows the JSON format and schema that you've defined.

Code sample

C#

Before trying this sample, follow the C# setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI C# API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

public async Task<string> GenerateContentWithResponseSchema2(
    string projectId = "your-project-id",
    string location = "us-central1",
    string publisher = "google",
    string model = "gemini-2.0-flash-001")
{

    var predictionServiceClient = new PredictionServiceClientBuilder
    {
        Endpoint = $"{location}-aiplatform.googleapis.com"
    }.Build();

    var responseSchema = new OpenApiSchema
    {
        Type = Type.Array,
        Items = new()
        {
            Type = Type.Object,
            Properties =
            {
                ["rating"] = new() { Type = Type.Integer },
                ["flavor"] = new() { Type = Type.String }
            },
            Required = { "rating", "flavor" }
        }
    };

    string prompt = @"
        Reviews from our social media:

        - ""Absolutely loved it! Best ice cream I've ever had."" Rating: 4, Flavor: Strawberry Cheesecake
        - ""Quite good, but a bit too sweet for my taste."" Rating: 1, Flavor: Mango Tango";

    var generateContentRequest = new GenerateContentRequest
    {
        Model = $"projects/{projectId}/locations/{location}/publishers/{publisher}/models/{model}",
        Contents =
        {
            new Content
            {
                Role = "USER",
                Parts =
                {
                    new Part { Text = prompt }
                }
            }
        },
        GenerationConfig = new GenerationConfig
        {
            ResponseMimeType = "application/json",
            ResponseSchema = responseSchema
        },
    };

    GenerateContentResponse response = await predictionServiceClient.GenerateContentAsync(generateContentRequest);

    string responseText = response.Candidates[0].Content.Parts[0].Text;
    Console.WriteLine(responseText);

    return responseText;
}

Java

Before trying this sample, follow the Java setup instructions in the Vertex AI quickstart using client libraries. For more information, see the Vertex AI Java API reference documentation.

To authenticate to Vertex AI, set up Application Default Credentials. For more information, see Set up authentication for a local development environment. 

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.api.GenerationConfig;
import com.google.cloud.vertexai.api.Schema;
import com.google.cloud.vertexai.api.Type;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import com.google.cloud.vertexai.generativeai.ResponseHandler;
import java.io.IOException;
import java.util.Arrays;

public class ControlledGenerationSchema2 {
  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "genai-java-demos";
    String location = "us-central1";
    String modelName = "gemini-1.5-pro-001";

    controlGenerationWithJsonSchema2(projectId, location, modelName);
  }

  // Generate responses that are always valid JSON and comply with a JSON schema
  public static String controlGenerationWithJsonSchema2(
      String projectId, String location, String modelName)
      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.
    try (VertexAI vertexAI = new VertexAI(projectId, location)) {
      GenerationConfig generationConfig = GenerationConfig.newBuilder()
          .setResponseMimeType("application/json")
          .setResponseSchema(Schema.newBuilder()
              .setType(Type.ARRAY)
              .setItems(Schema.newBuilder()
                  .setType(Type.OBJECT)
                  .putProperties("rating", Schema.newBuilder().setType(Type.INTEGER).build())
                  .putProperties("flavor", Schema.newBuilder().setType(Type.STRING).build())
                  .addAllRequired(Arrays.asList("rating", "flavor"))
                  .build())
              .build())
          .build();

      GenerativeModel model = new GenerativeModel(modelName, vertexAI)
          .withGenerationConfig(generationConfig);

      GenerateContentResponse response = model.generateContent(
          "Reviews from our social media:\n"
              + "\"Absolutely loved it! Best ice cream I've ever had.\" "
              + "Rating: 4, Flavor: Strawberry Cheesecake\n"
              + "\"Quite good, but a bit too sweet for my taste.\" "
              + "Rating: 1, Flavor: Mango Tango"
      );

      String output = ResponseHandler.getText(response);
      System.out.println(output);
      return output;
    }
  }
}

What's next

To search and filter code samples for other Google Cloud products, see the Google Cloud sample browser.