Amazon Bedrock Knowledge Basesで同期したメタデータがAmazon OpenSearch Serviceにどう格納されるか確認してみた

{
  "metadataAttributes": {
    "document_type": {
      "value": { "type": "STRING", "stringValue": "report" }
    },
    "priority": {
      "value": { "type": "NUMBER", "numberValue": 95 }
    },
    "is_public": {
      "value": { "type": "BOOLEAN", "booleanValue": false }
    },
    "department": {
      "value": { "type": "STRING", "stringValue": "finance" }
    },
    "year": {
      "value": { "type": "NUMBER", "numberValue": 2024 }
    },
    "tags": {
      "value": {
        "type": "STRING_LIST",
        "stringListValue": ["aws", "bedrock", "generative-ai"]
      }
    }
  }
}

git clone https://github.com/yuu551/sample-knowledge.git
cd sample-knowledge
pnpm install

export const parameter = {
  /**
   * OpenSearch Serverlessダッシュボードにアクセスを許可するIAMプリンシパル
   */
  opensearchAccessPrincipals: [
    'arn:aws:iam::123456789012:user/your-username',
    // 'arn:aws:iam::123456789012:role/Admin',
  ] as string[],

  // ... その他の設定
};

# 初回のみ
cdk bootstrap

# デプロイ
cdk deploy

Outputs:
SampleKnowledgeStack.KnowledgeBaseId = XXXXXXXXXX
SampleKnowledgeStack.DataSourceId = XXXXXXXXXX
SampleKnowledgeStack.DocumentBucketName = sampleknowledgestack-docbucket...
SampleKnowledgeStack.OpenSearchCollectionArn = arn:aws:aoss:...

GET /bedrock-knowledge-base-default-index/_mapping

{
  "bedrock-knowledge-base-default-index": {
    "mappings": {
      "properties": {
        "AMAZON_BEDROCK_METADATA": {
          "type": "text",
          "index": false
        },
        "AMAZON_BEDROCK_TEXT_CHUNK": {
          "type": "text"
        },
        "bedrock-knowledge-base-default-vector": {
          "type": "knn_vector",
          "dimension": 1024,
          "method": {
            "engine": "faiss",
            "space_type": "l2",
            "name": "hnsw",
            "parameters": {}
          }
        },
        "document_type": {
          "type": "text",
          "fields": {
            "keyword": { "type": "keyword", "ignore_above": 256 }
          }
        },
        "department": {
          "type": "text",
          "fields": {
            "keyword": { "type": "keyword", "ignore_above": 256 }
          }
        },
        "priority": { "type": "float" },
        "is_public": { "type": "boolean" },
        "year": { "type": "float" },
        "tags": {
          "type": "text",
          "fields": {
            "keyword": { "type": "keyword", "ignore_above": 256 }
          }
        }
      }
    }
  }
}

GET /bedrock-knowledge-base-default-index/_search

{
  "_source": {
    "document_type": "report",
    "department": "finance",
    "priority": 95,
    "is_public": false,
    "year": 2024,
    "AMAZON_BEDROCK_TEXT_CHUNK": "ドキュメント本文...",
    "bedrock-knowledge-base-default-vector": [...],
    "tags": ["aws", "bedrock", "generative-ai", "rag"]
  }
}

GET /bedrock-knowledge-base-default-index/_search
{
  "query": {
    "bool": {
      "filter": [
        { "term": { "document_type.keyword": "report" } },
        { "term": { "is_public": false } }
      ]
    }
  }
}

{
  "hits": {
    "total": { "value": 1, "relation": "eq" },
    "hits": [
      {
        "_source": {
          "x-amz-bedrock-kb-source-uri": "s3://sampleknowledgestack-docbucket.../annual-report-2024.txt",
          "year": 2024,
          "is_public": false,
          "priority": 95,
          "department": "finance",
          "AMAZON_BEDROCK_TEXT_CHUNK": "2024年度 年次報告書  概要 本報告書は、2024年度における当社の事業活動、財務状況、および今後の展望についてまとめたものです。...",
          "document_type": "report"
        }
      }
    ]
  }
}

GET /bedrock-knowledge-base-default-index/_search
{
  "query": {
    "bool": {
      "filter": [
        { "term": { "year": 2024 } }
      ]
    }
  }
}

GET /bedrock-knowledge-base-default-index/_search
{
  "query": {
    "bool": {
      "filter": [
        { "term": { "department.keyword": "engineering" } },
        { "term": { "tags.keyword": "aws" } }
      ]
    }
  }
}

{
  "hits": {
    "total": { "value": 1, "relation": "eq" },
    "hits": [
      {
        "_source": {
          "x-amz-bedrock-kb-source-uri": "s3://sampleknowledgestack-docbucket.../tech-blog-aws-bedrock.txt",
          "is_public": true,
          "priority": 70,
          "department": "engineering",
          "AMAZON_BEDROCK_TEXT_CHUNK": "技術ブログ: Amazon Bedrockで始める生成AI  はじめに Amazon Bedrockは、AWSが提供するフルマネージドの生成AIサービスです。...",
          "document_type": "blog",
          "tags": ["aws", "bedrock", "generative-ai", "rag"]
        }
      }
    ]
  }
}

GET /bedrock-knowledge-base-default-index/_search
{
  "size": 0,
  "aggs": {
    "by_type": {
      "terms": { "field": "document_type.keyword" }
    },
    "by_department": {
      "terms": { "field": "department.keyword" }
    },
    "avg_priority": {
      "avg": { "field": "priority" }
    }
  }
}

{
  "took": 80,
  "timed_out": false,
  "_shards": {
    "total": 0,
    "successful": 0,
    "skipped": 0,
    "failed": 0
  },
  "hits": {
    "total": {
      "value": 3,
      "relation": "eq"
    },
    "max_score": null,
    "hits": []
  },
  "aggregations": {
    "avg_priority": {
      "value": 81.66666666666667
    },
    "by_department": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "engineering",
          "doc_count": 1
        },
        {
          "key": "finance",
          "doc_count": 1
        },
        {
          "key": "product",
          "doc_count": 1
        }
      ]
    },
    "by_type": {
      "doc_count_error_upper_bound": 0,
      "sum_other_doc_count": 0,
      "buckets": [
        {
          "key": "blog",
          "doc_count": 1
        },
        {
          "key": "manual",
          "doc_count": 1
        },
        {
          "key": "report",
          "doc_count": 1
        }
      ]
    }
  }
}