使用 countTokens API

本页介绍了如何使用 countTokens API 获取提示的词元数和计费字符数。

支持的模型

以下多模态模型支持获取提示词元数的估算值:

  • gemini-1.5-flash-002
  • gemini-1.5-pro-002
  • gemini-1.0-pro-002
  • gemini-1.0-pro-vision-001

如需详细了解模型版本,请参阅 Gemini 模型版本和生命周期

获取提示的词元数

您可以使用 Vertex AI API 获取提示的词元数估计值和计费字符数。

Python

如需了解如何安装或更新 Vertex AI SDK for Python,请参阅安装 Vertex AI SDK for Python。 如需了解详情,请参阅 Python API 参考文档

import vertexai
from vertexai.generative_models import GenerativeModel

# TODO (developer): update project_id
vertexai.init(project=PROJECT_ID, location="us-central1")

model = GenerativeModel("gemini-1.5-flash-002")

prompt = "Why is the sky blue?"
# Prompt tokens count
response = model.count_tokens(prompt)
print(f"Prompt Token Count: {response.total_tokens}")
print(f"Prompt Character Count: {response.total_billable_characters}")

# Send text to Gemini
response = model.generate_content(prompt)

# Response tokens count
usage_metadata = response.usage_metadata
print(f"Prompt Token Count: {usage_metadata.prompt_token_count}")
print(f"Candidates Token Count: {usage_metadata.candidates_token_count}")
print(f"Total Token Count: {usage_metadata.total_token_count}")

Java

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 Java 设置说明执行操作。 如需了解详情,请参阅 Vertex AI Java API 参考文档

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

import com.google.cloud.vertexai.VertexAI;
import com.google.cloud.vertexai.api.CountTokensResponse;
import com.google.cloud.vertexai.api.GenerateContentResponse;
import com.google.cloud.vertexai.generativeai.GenerativeModel;
import java.io.IOException;

public class GetTokenCount {
  public static void main(String[] args) throws IOException {
    // TODO(developer): Replace these variables before running the sample.
    String projectId = "your-google-cloud-project-id";
    String location = "us-central1";
    String modelName = "gemini-1.5-flash-001";

    getTokenCount(projectId, location, modelName);
  }

  // Gets the number of tokens for the prompt and the model's response.
  public static int getTokenCount(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)) {
      GenerativeModel model = new GenerativeModel(modelName, vertexAI);

      String textPrompt = "Why is the sky blue?";
      CountTokensResponse response = model.countTokens(textPrompt);

      int promptTokenCount = response.getTotalTokens();
      int promptCharCount = response.getTotalBillableCharacters();

      System.out.println("Prompt token Count: " + promptTokenCount);
      System.out.println("Prompt billable character count: " + promptCharCount);

      GenerateContentResponse contentResponse = model.generateContent(textPrompt);

      int tokenCount = contentResponse.getUsageMetadata().getPromptTokenCount();
      int candidateTokenCount = contentResponse.getUsageMetadata().getCandidatesTokenCount();
      int totalTokenCount = contentResponse.getUsageMetadata().getTotalTokenCount();

      System.out.println("Prompt token Count: " + tokenCount);
      System.out.println("Candidate Token Count: " + candidateTokenCount);
      System.out.println("Total token Count: " + totalTokenCount);

      return promptTokenCount;
    }
  }
}

Node.js

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 Node.js 设置说明执行操作。 如需了解详情,请参阅 Vertex AI Node.js API 参考文档

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

const {VertexAI} = require('@google-cloud/vertexai');

/**
 * TODO(developer): Update these variables before running the sample.
 */
async function countTokens(
  projectId = 'PROJECT_ID',
  location = 'us-central1',
  model = 'gemini-1.5-flash-001'
) {
  // Initialize Vertex with your Cloud project and location
  const vertexAI = new VertexAI({project: projectId, location: location});

  // Instantiate the model
  const generativeModel = vertexAI.getGenerativeModel({
    model: model,
  });

  const req = {
    contents: [{role: 'user', parts: [{text: 'How are you doing today?'}]}],
  };

  // Prompt tokens count
  const countTokensResp = await generativeModel.countTokens(req);
  console.log('Prompt tokens count: ', countTokensResp);

  // Send text to gemini
  const result = await generativeModel.generateContent(req);

  // Response tokens count
  const usageMetadata = result.response.usageMetadata;
  console.log('Response tokens count: ', usageMetadata);
}

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,请设置应用默认凭据。 如需了解详情,请参阅为本地开发环境设置身份验证

import (
	"context"
	"fmt"
	"io"

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

// countTokens returns the number of tokens for this prompt.
func countTokens(w io.Writer, projectID, location, modelName string) error {
	// location := "us-central1"
	// modelName := "gemini-1.5-flash-001"

	ctx := context.Background()
	prompt := genai.Text("Why is the sky blue?")

	client, err := genai.NewClient(ctx, projectID, location)
	if err != nil {
		return fmt.Errorf("unable to create client: %w", err)
	}
	defer client.Close()

	model := client.GenerativeModel(modelName)

	resp, err := model.CountTokens(ctx, prompt)
	if err != nil {
		return err
	}

	fmt.Fprintf(w, "Number of tokens for the prompt: %d\n", resp.TotalTokens)

	resp2, err := model.GenerateContent(ctx, prompt)
	if err != nil {
		return err
	}
	fmt.Fprintf(w, "Number of tokens for the prompt: %d\n", resp2.UsageMetadata.PromptTokenCount)
	fmt.Fprintf(w, "Number of tokens for the candidates: %d\n", resp2.UsageMetadata.CandidatesTokenCount)
	fmt.Fprintf(w, "Total number of tokens: %d\n", resp2.UsageMetadata.TotalTokenCount)

	return nil
}

REST

如需使用 Vertex AI API 获取提示的词元数和计费字符数,请向发布者模型端点发送 POST 请求。

在使用任何请求数据之前,请先进行以下替换:

  • LOCATION:处理请求的区域。可用的选项包括:

    点击即可展开可用区域的部分列表

    • us-central1
    • us-west4
    • northamerica-northeast1
    • us-east4
    • us-west1
    • asia-northeast3
    • asia-southeast1
    • asia-northeast1
  • PROJECT_ID:您的项目 ID
  • MODEL_ID:您要使用的多模态模型 ID。
  • ROLE:与内容关联的对话中的角色。即使在单轮应用场景中,也需要指定角色。 可接受的值包括:
    • USER:指定由您发送的内容。
  • TEXT:要包含在提示中的文本说明。
  • NAME:要调用的函数名称。
  • DESCRIPTION:函数的说明和用途。

HTTP 方法和网址:

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:countTokens

请求 JSON 正文:

{
  "contents": [{
    "role": "ROLE",
    "parts": [{
      "text": "TEXT"
    }]
  }],
  "system_instruction": {
    "role": "ROLE",
    "parts": [{
      "text": "TEXT"
    }]
  }
  "tools": [{
    "function_declarations": [
      {
        "name": "NAME",
        "description": "DESCRIPTION",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "location": {
              "type": "TYPE",
              "description": "DESCRIPTION"
            }
          },
          "required": [
            "location"
          ]
        }
      }
    ]
  }]
}

如需发送请求,请选择以下方式之一:

curl

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

curl -X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json; charset=utf-8" \
-d @request.json \
"https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:countTokens"

PowerShell

将请求正文保存在名为 request.json 的文件中,然后执行以下命令:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `
-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/google/models/MODEL_ID:countTokens" | Select-Object -Expand Content

您应该收到类似以下内容的 JSON 响应。

控制台

如需在 Google Cloud 控制台中使用 Vertex AI Studio 获取提示的词元数,请执行以下步骤:

  1. 在 Google Cloud 控制台的“Vertex AI”部分,进入 Vertex AI Studio 页面。

    进入 Vertex AI Studio

  2. 点击打开自由格式模式打开聊天工具
  3. 系统会在您在 Prompt 窗格中输入内容时计算并显示词元数。其中包含所有输入文件中的词元数。
  4. 如需了解更多详情,请点击 <count> 个词元以打开提示词元化器
    • 如需在文本提示中查看词元(使用不同颜色标记每个词元 ID 的边界进行突出显示),请点击词元 ID 转换为文本。不支持媒体词元。
    • 如需查看词元 ID,请点击词元 ID

      要关闭词元化器工具窗格,请点击 X,或点击窗格外部。

包含图片或视频的文本的 curl 命令示例:

MODEL_ID="gemini-1.0-pro-vision"
PROJECT_ID="my-project"
TEXT="Provide a summary with about two sentences for the following article."
REGION="us-central1"

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${REGION}/publishers/google/models/${MODEL_ID}:countTokens -d \
$'{
    "contents": [{
      "role": "user",
      "parts": [
        {
          "file_data": {
            "file_uri": "gs://cloud-samples-data/generative-ai/video/pixel8.mp4",
            "mime_type": "video/mp4"
          }
        },
        {
          "text": "'"$TEXT"'"
        }]
    }]
 }'

纯文本的 curl 命令示例:

MODEL_ID="gemini-1.0-pro-vision"
PROJECT_ID="my-project"
TEXT="Provide a summary with about two sentences for the following article."
REGION="us-central1"

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${REGION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${REGION}/publishers/google/models/${MODEL_ID}:countTokens -d \
$'{
  "contents": [{
      "role": "user",
      "parts": [{
        "text": "'"$TEXT"'"
      }]
    }]
 }'

价格和配额

使用 CountTokens API 无需付费或配额限制。CountTokens API 的配额上限为每分钟 3000 个请求。

后续步骤