使用 Nova 生成结构化输出

结构化输出对计算机间通信用例至关重要，因为结构化输出可以使下游用例更有效地使用和处理所产生的输出。无论是从文档中提取信息、创建从 API 获取数据的助手，还是开发执行操作的代理，这些任务都需要基础模型以特定结构化格式生成输出。

Nova 模型利用“约束解码”来确保生成的输出具有很高的模型可靠性，并使模型能够轻松处理复杂的架构。约束解码依赖于语法来“约束”模型在每个步骤中可能输出的词元。这与历史上使用的提示技术有所不同，因为这改变了模型在生成输出时可选择的实际词元。例如，在关闭 JSON 对象时，模型会被限制为只有 {} 个词元可供选择。每次传递工具配置时，都会利用约束解码功能。由于工具使用功能已经为我们提供了特定的架构，因此我们可以借此根据开发人员所需的架构来动态生成语法。约束解码可防止模型生成无效键，并根据定义的架构强制执行正确的数据类型。

要利用工具使用功能进行结构化输出，首要步骤是定义输出所需的 JSON 架构。下面是在 tool_config 定义中定义 JSON 架构的一个示例：

  tool_config = {
  "tools": [
    {
      "toolSpec": {
        "name": "ProductAnalysis",
        "description": "Analyze product information from text.",
        "inputSchema": {
          "json": {
            "type": "object",
            "properties": {
              "name": {
                "type": "string",
                "description": "Product name"
              },
              "rating": {
                "maximum": 5,
                "description": "Customer rating 1-5",
                "type": [
                  "number",
                  "null"
                ],
                "minimum": 1
              },
              "features": {
                "description": "Key product features",
                "type": "array",
                "items": {
                  "type": "string"
                }
              },
              "category": {
                "type": "string",
                "description": "Product category"
              },
              "price": {
                "type": "number",
                "description": "Price in USD"
              }
            },
            "required": [
              "name",
              "category",
              "price",
              "features"
            ]
          }
        }
      }
    }
  ],
  "toolChoice": {
    "tool": {
      "name": "ProductAnalysis"
    }
  }
}
 

稍后使用模型调用该工具时，您将收到以该架构格式响应的输出。例如，下面是在 Python 中调用模型的一个示例：

  import boto3

client = boto3.client("bedrock-runtime")
model_id = "amazon.nova-lite-1-5-v1:0"

user_query = """The Amazon Kindle Scribe is a state-of-the-art e-reader designed for both reading and writing, featuring a 10.2-inch paper-like display and a premium stylus. This versatile device allows users to enjoy books, take notes, annotate PDFs, and even sketch, making it ideal for readers, students, and professionals. Priced at $339.99, it falls under the electronics category and boasts features like a front light, adjustable warm light settings, and up to 12 weeks of battery life on a single charge. Customer ratings for the Kindle Scribe average around 4.5 stars, reflecting its high user satisfaction."""

messages = [{
   "role": "user",
   "content": [{
        "text": user_query
   }]
}]

system = [{"text": "Leverage the ProductAnalysis tool to extract product information"}]
inference_params = {"temperature": 0}

response = client.converse(modelId=model_id, system=system, messages=messages, toolConfig=tool_config, inferenceConfig=inference_params)
print(next(
    block["toolUse"]
    for block in response["output"]["message"]["content"]
    if "toolUse" in block
))
 

输出内容如下所示：

 {
  "toolUseId": "tooluse_hke1FUeuRbKXK8DPqIptVg",
  "name": "ProductAnalysis",
  "input": {
    "name": "Amazon Kindle Scribe",
    "rating": 4.5,
    "features": [
      "10.2-inch paper-like display",
      "premium stylus",
      "front light",
      "adjustable warm light settings",
      "up to 12 weeks of battery life"
    ],
    "category": "electronics",
    "price": 339.99
  }
}