在 JSON 架构中指定受控生成枚举值

在 JSON 架构中指定响应枚举值列表。模型从架构中定义的值列表中选择一个枚举值。

代码示例

Go

在尝试此示例之前，请按照《Vertex AI 快速入门：使用客户端库》中的 Go 设置说明执行操作。 如需了解详情，请参阅 Vertex AI Go API 参考文档。

如需向 Vertex AI 进行身份验证，请设置应用默认凭证。 如需了解详情，请参阅为本地开发环境设置身份验证。

import (
	"context"
	"errors"
	"fmt"
	"io"

	"cloud.google.com/go/vertexai/genai"
)

// controlledGenerationResponseSchemaEnum demonstrates how to constrain model responses
// to a predefined set of enum values for genre classification.
func controlledGenerationResponseSchemaEnum(w io.Writer, projectID, location, modelName string) error {
	// location = "us-central1"
	// modelName = "gemini-2.0-flash-001"
	ctx := context.Background()
	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("failed to create GenAI client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	model.GenerationConfig.ResponseMIMEType = "text/x.enum"
	model.GenerationConfig.ResponseSchema = &genai.Schema{
		Type: genai.TypeString,
		Enum: []string{"drama", "comedy", "documentary"},
	}

	prompt := `
The film aims to educate and inform viewers about real-life subjects, events, or people.
It offers a factual record of a particular topic by combining interviews, historical footage,
and narration. The primary purpose of a film is to present information and provide insights
into various aspects of reality.
`

	res, err := model.GenerateContent(ctx, genai.Text(prompt))
	if err != nil {
		return fmt.Errorf("failed to generate content: %w", err)
	}

	if len(res.Candidates) == 0 || len(res.Candidates[0].Content.Parts) == 0 {
		return errors.New("got empty response from model")
	}

	fmt.Fprintf(w, "Candidate label: %q", res.Candidates[0].Content.Parts[0])
	// Example response:
	// Candidate label: "documentary"

	return nil
}

后续步骤

如需搜索和过滤其他 Google Cloud 产品的代码示例，请参阅Google Cloud 示例浏览器。