使用 Claude 模型请求预测

您可以使用 Anthropic 的 SDK 或 curl 命令通过以下模型名称向 Gemini Enterprise Agent Platform 端点发送请求：

• 对于 Google Cloud 上的 Claude Sonnet 5，请使用 claude-sonnet-5
• 对于 Google Cloud 上的 Claude Opus 5，请使用 claude-opus-5
• 对于 Google Cloud 上的 Claude Fable 5，请使用 claude-fable-5
• 对于 Google Cloud 上的 Claude Opus 4.8，请使用 claude-opus-4-8
• 对于 Google Cloud 上的 Claude Opus 4.7，请使用 claude-opus-4-7
• 对于 Google Cloud 上的 Claude Opus 4.6，请使用 claude-opus-4-6
• 对于 Google Cloud 上的 Claude Sonnet 4.6，请使用 claude-sonnet-4-6
• 对于 Google Cloud 上的 Claude Opus 4.5，请使用 claude-opus-4-5
• 对于 Google Cloud 上的 Claude Opus 4.1，请使用 claude-opus-4-1
• 对于 Google Cloud 上的 Claude Opus 4，请使用 claude-opus-4
• 对于 Google Cloud 上的 Claude Sonnet 4.5，请使用 claude-sonnet-4-5
• 对于 Google Cloud 上的 Claude Sonnet 4，请使用 claude-sonnet-4
• 对于 Google Cloud 上的 Claude 3.7 Sonnet，请使用 claude-3-7-sonnet
• 对于 Google Cloud 上的 Claude 3.5 Sonnet v2，请使用 claude-3-5-sonnet-v2
• 对于 Google Cloud 上的 Claude Haiku 4.5，请使用 claude-haiku-4-5
• 对于 Google Cloud 上的 Claude 3.5 Haiku，请使用 claude-3-5-haiku
• 对于 Google Cloud 上的 Claude 3.5 Sonnet，请使用 claude-3-5-sonnet
• 对于 Google Cloud 上的 Claude 3 Opus，请使用 claude-3-opus
• 对于 Google Cloud 上的 Claude 3 Haiku，请使用 claude-3-haiku

准备工作

Anthropic 实施了相关政策，禁止某些经销商转售其产品。如果您的 Google Cloud 结算账号由禁止的经销商管理，您将无法接受服务条款或启用 Claude 模型。如果出现这种情况，请直接与您的转销商联系。

如需将 Anthropic Claude 模型与 Gemini Enterprise Agent Platform 搭配使用，您必须执行以下步骤。必须启用 Agent Platform API (aiplatform.googleapis.com) 才能使用 Gemini Enterprise Agent Platform。如果您已有启用了 Agent Platform API 的项目，则可以使用该项目，而无需创建新项目。

确保您拥有启用和使用合作伙伴模型所需的权限。如需了解详情，请参阅授予所需权限。

登录您的 Google Cloud 账号。如果您是 Google Cloud新手，请 创建一个账号来评估我们的产品在实际场景中的表现。新客户还可获享 $300 赠金，用于运行、测试和部署工作负载。

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Gemini Enterprise Agent Platform API.

Roles required to enable APIs

To enable APIs, you need the serviceusage.services.enable permission. If you created the project, then you likely already have this permission through the Owner role (roles/owner). Otherwise, you can get this permission through the Service Usage Admin role (roles/serviceusage.serviceUsageAdmin). Learn how to grant roles.

Enable the API

In the Google Cloud console, on the project selector page, select or create a Google Cloud project.

Roles required to select or create a project

• Select a project: Selecting a project doesn't require a specific IAM role—you can select any project that you've been granted a role on.
• Create a project: To create a project, you need the Project Creator role (roles/resourcemanager.projectCreator), which contains the resourcemanager.projects.create permission. Learn how to grant roles.

Go to project selector

Verify that billing is enabled for your Google Cloud project.

Enable the Gemini Enterprise Agent Platform API.

Roles required to enable APIs

To enable APIs, you need the serviceusage.services.enable permission. If you created the project, then you likely already have this permission through the Owner role (roles/owner). Otherwise, you can get this permission through the Service Usage Admin role (roles/serviceusage.serviceUsageAdmin). Learn how to grant roles.

Enable the API

1. 前往以下 Model Garden 模型卡片之一，然后点击启用：
   • 前往 Google Cloud 上的 Claude Sonnet 5 模型卡片
   • 前往 Google Cloud 上的 Claude Opus 5 模型卡片
   • 前往 Google Cloud 上的 Claude Fable 5 模型卡片
   • 前往 Google Cloud 上的 Claude Opus 4.8 模型卡片
   • 前往 Google Cloud 上的 Claude Opus 4.7 模型卡片
   • 前往 Google Cloud 上的 Claude Opus 4.6 模型卡片
   • 前往 Google Cloud 上的 Claude Sonnet 4.6 模型卡片
   • 前往 Google Cloud 上的 Claude Opus 4.5 模型卡片
   • 前往 Google Cloud 上的 Claude Opus 4.1 模型卡片
   • 前往 Google Cloud 上的 Claude Opus 4 模型卡片
   • 前往 Google Cloud 上的 Claude Sonnet 4.5 模型卡片
   • 前往 Google Cloud 上的 Claude Sonnet 4 模型卡片
   • 前往 Google Cloud 上的 Claude Haiku 4.5 模型卡片
   • 前往 Google Cloud 上的 Claude 3.5 Haiku 模型卡片

Anthropic 建议您启用提示和完成活动的 30 天日志记录，以记录任何模型滥用行为。如需启用日志记录，请参阅记录请求和响应。

使用 Anthropic SDK

您可以使用 Anthropic Claude SDK 向 Anthropic Claude 模型发出 API 请求。如需了解详情，请参阅以下内容：

• Claude Messages API 参考文档
• Anthropic Python API 库
• Anthropic Gemini Enterprise Agent Platform TypeScript API 库

使用 Anthropic Vertex SDK 对 Claude 模型进行流式调用

以下代码示例使用 Anthropic Vertex SDK 对 Claude 模型执行流式调用。

# TODO(developer): Vertex AI SDK - uncomment below & run
# pip3 install --upgrade --user google-cloud-aiplatform
# gcloud auth application-default login
# pip3 install -U 'anthropic[vertex]'

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

from anthropic import AnthropicVertex

client = AnthropicVertex(project_id=PROJECT_ID, region="us-east5")
result = []

with client.messages.stream(
    model="claude-3-5-sonnet-v2@20241022",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Send me a recipe for banana bread.",
        }
    ],
) as stream:
    for text in stream.text_stream:
        print(text, end="", flush=True)
        result.append(text)

# Example response:
# Here's a simple recipe for delicious banana bread:
# Ingredients:
# - 2-3 ripe bananas, mashed
# - 1/3 cup melted butter
# ...
# ...
# 8. Bake for 50-60 minutes, or until a toothpick inserted into the center comes out clean.
# 9. Let cool in the pan for a few minutes, then remove and cool completely on a wire rack.

使用 Anthropic Vertex SDK 对 Claude 模型进行一元调用

以下代码示例使用 Anthropic Vertex SDK 对 Claude 模型执行一元调用。

# TODO(developer): Vertex AI SDK - uncomment below & run
# pip3 install --upgrade --user google-cloud-aiplatform
# gcloud auth application-default login
# pip3 install -U 'anthropic[vertex]'

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

from anthropic import AnthropicVertex

client = AnthropicVertex(project_id=PROJECT_ID, region="us-east5")
message = client.messages.create(
    model="claude-3-5-sonnet-v2@20241022",
    max_tokens=1024,
    messages=[
        {
            "role": "user",
            "content": "Send me a recipe for banana bread.",
        }
    ],
)
print(message.model_dump_json(indent=2))
# Example response:
# {
#   "id": "msg_vrtx_0162rhgehxa9rvJM5BSVLZ9j",
#   "content": [
#     {
#       "text": "Here's a simple recipe for delicious banana bread:\n\nIngredients:\n- 2-3 ripe bananas...
#   ...

使用 curl 命令

您可以使用 curl 命令向 Gemini Enterprise Agent Platform 端点发出请求。curl 命令指定要使用的受支持的 Claude 模型。

以下主题介绍如何创建 curl 命令并包含示例 curl 命令。

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/MODEL:streamRawPredict

{
  "anthropic_version": "vertex-2023-10-16",
  "messages": [
   {
    "role": "ROLE",
    "content": "CONTENT"
   }],
  "max_tokens": MAX_TOKENS,
  "stream": STREAM,
  "thinking": {
    "type": "TYPE",
    "budget_tokens": BUDGET_TOKENS
  }
}

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/anthropic/models/MODEL:streamRawPredict"

$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/anthropic/models/MODEL:streamRawPredict" | Select-Object -Expand Content

{
  "id":"msg_012NDLxqh6LsztWCU7zTb14C",
  "type":"message",
  "role":"assistant",
  "content":[{
    "type":"text",
    "text":"Hello! Nice to meet you."
  }],
  "model":"claude-2.1",
  "stop_reason":"end_turn",
  "stop_sequence":null,
  "usage":{
    "input_tokens":11,
    "output_tokens":11
  }
}

MODEL_ID="MODEL"
LOCATION="us-central1"
PROJECT_ID="PROJECT_ID"

curl \
-X POST \
-H "Authorization: Bearer $(gcloud auth print-access-token)" \
-H "Content-Type: application/json" \
https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/anthropic/models/${MODEL_ID}:streamRawPredict -d \
'{
  "anthropic_version": "vertex-2023-10-16",
  "messages": [{
    "role": "user",
    "content": "Hello!"
  }],
  "max_tokens": 50,
  "stream": true}'

工具使用（函数调用）

Anthropic Claude 模型支持工具和函数调用，以增强模型的功能。如需了解详情，请参阅 Anthropic 文档中的工具使用概览。Gemini Enterprise Agent Platform 上的 Claude 模型支持客户端工具，但不支持服务器工具。

以下示例演示了如何使用 SDK 或 curl 命令来使用工具。这些示例会搜索旧金山附近正在营业的餐厅。

# TODO(developer): Vertex AI SDK - uncomment below & run
# pip3 install --upgrade --user google-cloud-aiplatform
# gcloud auth application-default login
# pip3 install -U 'anthropic[vertex]'
from anthropic import AnthropicVertex

# TODO(developer): Update and un-comment below line
# PROJECT_ID = "your-project-id"

client = AnthropicVertex(project_id=PROJECT_ID, region="us-east5")
message = client.messages.create(
    model="claude-3-5-sonnet-v2@20241022",
    max_tokens=1024,
    tools=[
        {
            "name": "text_search_places_api",
            "description": "returns information about a set of places based on a string",
            "input_schema": {
                "type": "object",
                "properties": {
                    "textQuery": {
                        "type": "string",
                        "description": "The text string on which to search",
                    },
                    "priceLevels": {
                        "type": "array",
                        "description": "Price levels to query places, value can be one of [PRICE_LEVEL_INEXPENSIVE, PRICE_LEVEL_MODERATE, PRICE_LEVEL_EXPENSIVE, PRICE_LEVEL_VERY_EXPENSIVE]",
                    },
                    "openNow": {
                        "type": "boolean",
                        "description": "whether those places are open for business.",
                    },
                },
                "required": ["textQuery"],
            },
        }
    ],
    messages=[
        {
            "role": "user",
            "content": "What are some affordable and good Italian restaurants open now in San Francisco??",
        }
    ],
)
print(message.model_dump_json(indent=2))
# Example response:
# {
#   "id": "msg_vrtx_018pk1ykbbxAYhyWUdP1bJoQ",
#   "content": [
#     {
#       "text": "To answer your question about affordable and good Italian restaurants
#       that are currently open in San Francisco....
# ...

POST https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/LOCATION/publishers/anthropic/models/MODEL:rawPredict

{
  "anthropic_version": "vertex-2023-10-16",
  "max_tokens": MAX_TOKENS,
  "stream": STREAM,
  "tools": [
    {
      "name": "text_search_places_api",
      "description": "Returns information about a set of places based on a string",
      "input_schema": {
        "type": "object",
        "properties": {
          "textQuery": {
            "type": "string",
            "description": "The text string on which to search"
          },
          "priceLevels": {
            "type": "array",
            "description": "Price levels to query places, value can be one of [PRICE_LEVEL_INEXPENSIVE, PRICE_LEVEL_MODERATE, PRICE_LEVEL_EXPENSIVE, PRICE_LEVEL_VERY_EXPENSIVE]",
          },
          "openNow": {
            "type": "boolean",
            "description": "Describes whether a place is open for business at
            the time of the query."
          },
        },
        "required": ["textQuery"]
      }
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": "What are some affordable and good Italian restaurants that are open now in San Francisco??"
    }
  ]
}

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/anthropic/models/MODEL:rawPredict"

$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/anthropic/models/MODEL:rawPredict" | Select-Object -Expand Content

{
  "id": "msg_vrtx_01ErR7VMNQdnvDt3n7Nmc4ER",
  "type": "message",
  "role": "assistant",
  "model": "claude-3-opus-20240229",
  "content": [
    {
      "type": "text",
      "text": "\nTo find affordable and good Italian restaurants that are currently open in San Francisco, the text_search_places_api tool seems most relevant. \n\nThe required textQuery parameter can be inferred as \"Italian restaurants in San Francisco\", since the user specified Italian restaurants and the location of San Francisco.\n\nTwo optional parameters are also relevant:\nopenNow - this should be set to true, since the user specified they want restaurants open now\npriceLevels - to find affordable restaurants, this can be set to [PRICE_LEVEL_INEXPENSIVE, PRICE_LEVEL_MODERATE]\n\nWith the textQuery provided and the two optional parameters that can help narrow the results to match the user's criteria, we have enough information to make a good call to the text_search_places_api tool to try to answer the user's request.\n"
    },
    {
      "type": "tool_use",
      "id": "toolu_vrtx_01TAJCTkxe8HhRoaQ69N4ouP",
      "name": "text_search_places_api",
      "input": {
        "textQuery": "Italian restaurants in San Francisco",
        "openNow": true,
        "priceLevels": [
          "PRICE_LEVEL_INEXPENSIVE",
          "PRICE_LEVEL_MODERATE"
        ]
      }
    }
  ],
  "stop_reason": "tool_use",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 727,
    "output_tokens": 308
  }
}

在 Gemini Enterprise Agent Platform 上使用 Agent Studio

对于某些 Anthropic Claude 模型，您可以使用 Gemini Enterprise Agent Platform 上的 Agent Studio 在 Google Cloud 控制台中快速对生成式 AI 模型进行原型开发和测试。例如，您可以使用 Gemini Enterprise Agent Platform 上的 Agent Studio 将 Claude 模型的回答与其他受支持的模型（例如 Google Gemini）的回答进行比较。

如需了解详情，请参阅快速入门：使用 Gemini Enterprise Agent Platform 上的 Agent Studio 向 Gemini 发送文本提示。