[アップデート] Amazon Bedrock Knowledge bases の GraphRAG が一般提供を開始しました

Example Corp はウィジェットを販売している

イギリスは最大のウィジェット市場である

ウィジェットは中国からイギリスに出荷されている

イギリスの港で遅延が発生している

{
    "schemaType": "ModelInvocationLog",
    "schemaVersion": "1.0",
    "timestamp": "2025-03-09T08:14:09Z",
    "accountId": "123456789012",
    "identity": {
        "arn": "arn:aws:sts::123456789012:assumed-role/AmazonBedrockExecutionRoleForKnowledgeBase_1dz6y/BKB-CP-EF1XBIB9ZO-HJkYjEKUNjMEpnA="
    },
    "region": "ap-northeast-1",
    "requestId": "150a7e31-6736-47e3-a671-f520be4b599d",
    "operation": "InvokeModel",
    "modelId": "arn:aws:bedrock:ap-northeast-1::foundation-model/anthropic.claude-3-haiku-20240307-v1:0",
    "input": {
        "inputContentType": "application/json",
        "inputBodyJson": {
            "anthropic_version": "bedrock-2023-05-31",
            "messages": [
                {
                    "role": "user",
                    "content": [
                        {
                            "type": "text",
                            "text": "Bedrock Knowledge Base verifying access to requested model"
                        }
                    ]
                }
            ],
            "system": "",
            "max_tokens": 2048,
            "temperature": 0,
            "top_p": 1,
            "stop_sequences": [
                "\nObservation"
            ],
            "top_k": 50
        },
        "inputTokenCount": 18
    },
    "output": {
        "outputContentType": "application/json",
        "outputBodyJson": {
            "id": "msg_bdrk_01DpL8fUg4o4FWNsHYWGgU7t",
            "type": "message",
            "role": "assistant",
            "model": "claude-3-haiku-20240307",
            "content": [
                {
                    "type": "text",
                    "text": "I'm afraid I don't have access to any Bedrock Knowledge Base or models. I'm Claude, an AI assistant created by Anthropic to be helpful, harmless, and honest. I don't have the capability to verify access to any external knowledge bases or models. I can only respond based on the information and capabilities I was trained on by Anthropic. Please let me know if there is anything else I can assist with!"
                }
            ],
            "stop_reason": "end_turn",
            "stop_sequence": null,
            "usage": {
                "input_tokens": 18,
                "output_tokens": 93
            }
        },
        "outputTokenCount": 93
    }
}

{
    "schemaType": "ModelInvocationLog",
    "schemaVersion": "1.0",
    "timestamp": "2025-03-09T08:14:13Z",
    "accountId": "123456789012",
    "identity": {
        "arn": "arn:aws:sts::123456789012:assumed-role/AmazonBedrockExecutionRoleForKnowledgeBase_1dz6y/GraphEntityExtractionTask-VJSCBJTIFC"
    },
    "region": "ap-northeast-1",
    "requestId": "f6b90802-47b5-48e1-899a-9bdf921d1870",
    "operation": "Converse",
    "modelId": "arn:aws:bedrock:ap-northeast-1::foundation-model/anthropic.claude-3-haiku-20240307-v1:0",
    "input": {
        "inputContentType": "application/json",
        "inputBodyJson": {
            "messages": [
                {
                    "role": "user",
                    "content": [
                        {
                            "text": "Example Corp はウィジェットを販売している"
                        }
                    ]
                }
            ],
            "system": [
                {
                    "text": "Given the following text, extract all important entities such as names, locations, organizations, and other relevant named entities.\nInstructions:\n    1. Extract all important entities (names, locations, organizations, etc.) from the text.\n    2. If there are no specific entities in the given text, please respond an empty <entities> tag set.\nYour response should be structured as follows:\n    <entities>\n     entity1\n     entity2\n     entity3\n     ...\n    </entities>\n"
                }
            ]
        },
        "inputTokenCount": 125
    },
    "output": {
        "outputContentType": "application/json",
        "outputBodyJson": {
            "output": {
                "message": {
                    "role": "assistant",
                    "content": [
                        {
                            "text": "<entities>\nExample Corp\n</entities>"
                        }
                    ]
                }
            },
            "stopReason": "end_turn",
            "metrics": {
                "latencyMs": 295
            },
            "usage": {
                "inputTokens": 125,
                "outputTokens": 13,
                "totalTokens": 138
            }
        },
        "outputTokenCount": 13
    }
}