提示快取可加快模型推論速度

在此範例中，第一個 image 欄位提供影像給模型，第二個 text 欄位則要求模型分析影像。只要 content 物件中 cachePoint 前面的字符數量符合模型的字符數量下限，就會建立快取檢查點。

...
"messages": [
   {
        "role": "user",
        "content": [
            {
                "image": {
                    "bytes": "asfb14tscve..."
                }
            },
            {
                "text": "What's in this image?"
            },
            {
                "cachePoint": {
                    "type": "default"
                }
            }
      ]
  }
]
...

在此範例中，您會在 text 欄位中提供系統提示。此外，您可以新增 cachePoint 欄位來快取系統提示。

...
  "system": [ 
    {
        "text": "You are an app that creates play lists for a radio station that plays rock and pop music. Only return song names and the artist. "
    },
    {
        "cachePoint": {
            "type": "default"
        }
    }
  ],
...

在此範例中，您會在 toolSpec 欄位中提供工具定義。（或者，您可以呼叫先前定義的工具。 如需詳細資訊，請參閱 使用工具完成 Amazon Bedrock 模型回應。) 之後，您可以新增 cachePoint 欄位來快取工具。

...
toolConfig={
    "tools": [
        {
            "toolSpec": {
                "name": "top_song",
                "description": "Get the most popular song played on a radio station.",
                "inputSchema": {
                    "json": {
                        "type": "object",
                        "properties": {
                            "sign": {
                                "type": "string",
                                "description": "The call sign for the radio station for which you want the most popular song. Example calls signs are WZPZ and WKRP."
                            }
                        },
                        "required": [
                            "sign"
                        ]
                    }
                }
            }
        },
        {
                "cachePoint": {
                    "type": "default"
                }
        }
    ]
}
...

下列範例示範如何為 Anthropic Claude 3.5 Sonnet v2 模型建構 InvokeModel 要求的內文。請注意，InvokeModel 請求的內文其確切格式和欄位可能會因您選擇的模型而有所不同。若要查看不同模型其請求和回應內文的格式和內容，請參閱 基礎模型的推論請求參數和回應欄位。

如下所示指定所需的 ttl 值，如果未指定 ttl 值，則會套用 5 分鐘快取的預設行為。

"cache_control" : {
    "type": "ephemeral",
    "ttl" : "5m | 1h"
}

body={
        "anthropic_version": "bedrock-2023-05-31",
        "system":"Reply concisely",
        "messages": [
            {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "Describe the best way to learn programming."
                },
                {
                    "type": "text",
                    "text": "Add additional context here for the prompt that meets the minimum token requirement for your chosen model.",
                    "cache_control": {
                        "type": "ephemeral"
                    }
                }
            ]
            }
        ],
        "max_tokens": 2048,
        "temperature": 0.5,
        "top_p": 0.8,
        "stop_sequences": [
            "stop"
        ],
        "top_k": 250
}

下列範例示範如何為 Amazon Nova 模型建構 InvokeModel 請求的內文。請注意，InvokeModel 請求的內文其確切格式和欄位可能會因您選擇的模型而有所不同。若要查看不同模型其請求和回應內文的格式和內容，請參閱 基礎模型的推論請求參數和回應欄位。

{
    "system": [{
        "text": "Reply Concisely"
    }],
    "messages": [{
        "role": "user",
        "content": [{
            "text": "Describe the best way to learn programming"
        },
        {
            "text": "Add additional context here for the prompt that meets the minimum token requirement for your chosen model.",
            "cachePoint": {
                "type": "default"
            }
        }]
    }],
    "inferenceConfig": {
        "maxTokens": 300,
        "topP": 0.1,
        "topK": 20,
        "temperature": 0.3
    }
}