Ottimizzazione dei Amazon Nova modelli con messa a punto supervisionata

Questo esempio mostra un formato base di solo testo compatibile con Amazon Nova 1.0.

{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a digital assistant with a friendly personality"
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What country is right next to Australia?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "text": "The closest country is New Zealand"
        }
      ]
    }
  ]
}

Questo esempio mostra il testo con contenuti di ragionamento facoltativi per la versione 2.0. Amazon Nova

{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a digital assistant with a friendly personality"
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "text": "What country is right next to Australia?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "reasoningContent": {
            "reasoningText": {
              "text": "I need to use my world knowledge of geography to answer this question"
            }
          }
        },
        {
          "text": "The closest country to Australia is New Zealand, located to the southeast across the Tasman Sea."
        }
      ]
    }
  ]
}

Questo esempio mostra come includere l'input di immagini nel testo.

{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a helpful assistant."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "image": {
            "format": "jpeg",
            "source": {
              "s3Location": {
                "uri": "s3://your-bucket/your-path/your-image.jpg",
                "bucketOwner": "your-aws-account-id"
              }
            }
          }
        },
        {
          "text": "Which country is highlighted in the image?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "reasoningContent": {
            "reasoningText": {
              "text": "I will determine the highlighted country by examining its location on the map and using my geographical knowledge"
            }
          }
        },
        {
          "text": "The highlighted country is New Zealand"
        }
      ]
    }
  ]
}

Questo esempio mostra come includere l'input video nel testo.

{
  "schemaVersion": "bedrock-conversation-2024",
  "system": [
    {
      "text": "You are a helpful assistant."
    }
  ],
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "video": {
            "format": "mp4",
            "source": {
              "s3Location": {
                "uri": "s3://your-bucket/your-path/your-video.mp4",
                "bucketOwner": "your-aws-account-id"
              }
            }
          }
        },
        {
          "text": "What is shown in this video?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "reasoningContent": {
            "reasoningText": {
              "text": "I will analyze the video content to identify key elements"
            }
          }
        },
        {
          "text": "The video shows a map with New Zealand highlighted"
        }
      ]
    }
  ]
}