使用 Claude 模型要求預測

您可以使用 Anthropic 的 SDK 或 curl 指令，透過下列模型名稱，將要求傳送至 Gemini Enterprise Agent Platform 端點：

• 如要在 Google Cloud 使用 Anthropic 的 Claude Sonnet 5.5，請使用 claude-sonnet-5-5
• 如要在 Google Cloud 使用 Anthropic 的 Claude Fable 5.1，請使用 claude-fable-5-1
• 如要使用 Google Cloud 上的 Anthropic Claude Sonnet 5，請使用 claude-sonnet-5
• 如要在 Google Cloud 使用 Anthropic 的 Claude Opus 5.5，請使用 claude-opus-5-5
• 如要在 Google Cloud 使用 Anthropic 的 Claude Opus 5，請使用 claude-opus-5
• 如要在 Google Cloud 使用 Anthropic 的 Claude Fable 5，請使用 claude-fable-5
• 如要在 Google Cloud 使用 Anthropic 的 Claude Opus 4.8，請使用 claude-opus-4-8
• 如要在 Google Cloud 使用 Anthropic 的 Claude Opus 4.7，請使用 claude-opus-4-7
• 如要在 Google Cloud 使用 Anthropic 的 Claude Opus 4.6，請使用 claude-opus-4-6
• 如要在 Google Cloud 使用 Anthropic 的 Claude Sonnet 4.6，請使用 claude-sonnet-4-6
• 如要在 Google Cloud 使用 Anthropic 的 Claude Opus 4.5，請使用 claude-opus-4-5
• 如要在 Google Cloud 使用 Anthropic 的 Claude Sonnet 4.5，請使用 claude-sonnet-4-5
• 如要在 Google Cloud 使用 Claude 3.7 Sonnet，請使用 claude-3-7-sonnet
• 如要在 Google Cloud 使用 Claude 3.5 Sonnet v2，請使用 claude-3-5-sonnet-v2
• 如要在 Google Cloud 使用 Anthropic 的 Claude Haiku 5.5，請使用 claude-haiku-5-5
• 如要在 Google Cloud 使用 Anthropic 的 Claude Haiku 4.5，請使用 claude-haiku-4-5
• 如要在 Google Cloud 使用 Claude 3.5 Haiku，請使用 claude-3-5-haiku
• 如要在 Google Cloud 使用 Claude 3.5 Sonnet，請使用 claude-3-5-sonnet
• 如要在 Google Cloud 使用 Claude 3 Opus，請使用 claude-3-opus
• 如要在 Google Cloud 使用 Claude 3 Haiku，請使用 claude-3-haiku

事前準備

Anthropic 實施政策，禁止特定經銷商轉售其產品。如果您的 Cloud de Confiance by S3NS 帳單帳戶是由受禁經銷商管理，您將無法接受《服務條款》或啟用 Claude 模型。如果發生這種情況，請直接與經銷商聯絡。

如要透過 Gemini Enterprise Agent Platform 使用 Anthropic Claude 模型，請務必完成下列步驟。必須啟用 Agent Platform API (aiplatform.googleapis.com)，才能使用 Gemini Enterprise Agent Platform。如果已有專案啟用 Agent Platform API，則可直接使用，不必建立新專案。

請確認您具備必要權限，可啟用及使用合作夥伴模型。詳情請參閱「授予必要權限」。

1. In the Cloud de Confiance console, on the project selector page, select or create a Cloud de Confiance 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

2. Verify that billing is enabled for your Cloud de Confiance project.

3. Enable the Gemini Enterprise Agent Platform API, if it is not already enabled.

   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

4. 前往下列其中一個 Model Garden 模型資訊卡，然後按一下「Enable」(啟用)：
   • 前往 Google Cloud 的 Anthropic Claude Sonnet 5.5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Fable 5.1 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Sonnet 5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Opus 5.5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Opus 5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Fable 5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Opus 4.8 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Opus 4.7 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Opus 4.6 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Sonnet 4.6 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Opus 4.5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Sonnet 4.5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Haiku 5.5 模型資訊卡
   • 前往 Google Cloud 的 Anthropic Claude Haiku 4.5 模型資訊卡
   • 前往 Google Cloud 的 Claude 3.5 Haiku 模型資訊卡

Anthropic 建議您啟用 30 天的提示和完成活動記錄功能，記錄任何模型濫用行為。如要啟用記錄功能，請參閱「記錄要求和回應」。

使用 Anthropic SDK

您可以使用 Anthropic Claude SDK，向 Anthropic Claude 模型發出 API 要求。如要瞭解詳情，請參閱下列資源：

• Claude Messages API 參考資料
• Anthropic Python API 程式庫
• Anthropic Gemini Enterprise Agent Platform TypeScript API 程式庫

使用 Anthropic Vertex SDK 對 Claude 模型發出串流呼叫

下列程式碼範例使用 Anthropic Vertex SDK，對 Claude 模型執行串流呼叫。

# 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 對 Claude 模型發出一元呼叫

下列程式碼範例使用 Anthropic Vertex SDK，對 Claude 模型執行一元呼叫。

# 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 指令

您可以使用 curl 指令，向 Gemini Enterprise Agent Platform 端點發出要求。curl 指令會指定要使用的 Claude 支援模型。

下列主題說明如何建立 curl 指令，並提供 curl 指令範例。

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 (呼叫函式)

Anthropic Claude 模型支援工具和函式呼叫，可強化模型功能。詳情請參閱 Anthropic 說明文件中的工具使用總覽。Gemini Enterprise Agent Platform 適用的 Claude 模型支援用戶端工具，但不支援伺服器工具。

下列範例說明如何使用 SDK 或 curl 指令來使用工具。範例會搜尋舊金山附近營業中的餐廳。

# 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
  }
}

使用 Gemini Enterprise Agent Platform 的 Agent Studio

對於部分 Anthropic Claude 模型，您可以使用 Gemini Enterprise Agent Platform 的 Agent Studio，在 Cloud de Confiance 控制台快速建立生成式 AI 模型原型並進行測試。舉例來說，您可以使用 Gemini Enterprise Agent Platform 的 Agent Studio，比較 Claude 模型與其他支援模型 (例如 Google Gemini) 的回覆。

詳情請參閱「快速入門導覽課程：使用 Gemini Enterprise Agent Platform 的 Agent Studio 向 Gemini 傳送文字提示詞」。