feat(bedrock): expose bda parsing strategy for data sources

[krokoko]

Fixes #

• Fix a typo
• Expose BDA as a parsing strategy for data sources

Testing with the following code snippet:

const docBucket = new s3.Bucket(this, 'DocBucket', {
      enforceSSL: true,
      versioned: true,
      publicReadAccess: false,
      blockPublicAccess: s3.BlockPublicAccess.BLOCK_ALL,
      encryption: s3.BucketEncryption.S3_MANAGED,
      removalPolicy: cdk.RemovalPolicy.DESTROY,
      autoDeleteObjects: true,
      serverAccessLogsPrefix: 'inputsAssetsBucketLogs/',
    });

    const supplementalStorage = new s3.Bucket(this, 'SupplementalStorage', {
      enforceSSL: true,
      versioned: true,
      publicReadAccess: false,
      blockPublicAccess: s3.BlockPublicAccess.BLOCK_ALL,
      encryption: s3.BucketEncryption.S3_MANAGED,
      removalPolicy: cdk.RemovalPolicy.DESTROY,
      autoDeleteObjects: true,
      serverAccessLogsPrefix: 'inputsAssetsBucketLogs/',
    });

    const supplementalStorageS3 = bedrock.SupplementalDataStorageLocation.s3({
      uri: `s3://${supplementalStorage.bucketName}/`
    });

    const kb = new bedrock.VectorKnowledgeBase(this, 'KnowledgeBase', {
      embeddingsModel: bedrock.BedrockFoundationModel.TITAN_EMBED_TEXT_V2_1024,
      instruction: 'Use this knowledge base to answer questions about books. ' + 'It contains the full text of novels.',
      supplementalDataStorageLocations: [supplementalStorageS3],
    });

    // Grant the role access to the document bucket with the provided supplemental data storage bucket
    supplementalStorage.grantReadWrite(kb.role);

    const dataSource = new bedrock.S3DataSource(this, 'DataSource', {
      bucket: docBucket,
      knowledgeBase: kb,
      dataSourceName: 'books',
      chunkingStrategy: bedrock.ChunkingStrategy.fixedSize({
        maxTokens: 500,
        overlapPercentage: 20
      }),
      parsingStrategy: bedrock.ParsingStrategy.bedrockDataAutomation()
    });

Deploys correctly:

Sync of the data source works as expected:

Images from documents are extracted and placed in the supplemental data storage:

---

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of the project license.

[MichaelWalker-git]

LGTM