chore(knowledgebase): add support for vector type

[krokoko]

Fixes #948

• Expose a new parameter for vector knowledge bases, allowing the configuration of the vector type for embeddings
• Update the Vector Index construct to expose necessary fields
• Add validation methods to prevent runtime issues
• Add tests
• Base CDK version upgrade to v2.178.0

---

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

[krokoko]

Testing by building 2 vector indexes in a collection:

    // role creation here

    const vectorStore = new opensearchserverless.VectorCollection(this, 'KBVectors');

    vectorStore.grantDataAccess(role);

    const vectorIndex = new opensearch_vectorindex.VectorIndex(this, 'KBIndex', {
      collection: vectorStore,
      indexName: 'mysuperindex',
      vectorField: 'default-vector',
      vectorDimensions: 1024,
      precision: 'Binary',
      distanceType: 'hamming',
      mappings: [
        {
          mappingField: 'AMAZON_BEDROCK_TEXT_CHUNK',
          dataType: 'text',
          filterable: true,
        },
        {
          mappingField: 'AMAZON_BEDROCK_METADATA',
          dataType: 'text',
          filterable: false,
        },
      ],
    });

    vectorIndex.node.addDependency(vectorStore);

    // flaoting point embeddings
    const vectorIndex2 = new opensearch_vectorindex.VectorIndex(this, 'KBIndex2', {
      collection: vectorStore,
      indexName: 'mysuperindex2',
      vectorField: 'default-vector2',
      vectorDimensions: 1024,
      precision: 'float',
      distanceType: 'l2',
      mappings: [
        {
          mappingField: 'AMAZON_BEDROCK_TEXT_CHUNK',
          dataType: 'text',
          filterable: true,
        },
        {
          mappingField: 'AMAZON_BEDROCK_METADATA',
          dataType: 'text',
          filterable: false,
        },
      ],
    });

    vectorIndex2.node.addDependency(vectorStore);

Works as expected

[krokoko]

Deployed the bedrock sample agent and tested as is to ensure no regression. Sample working as expected

[krokoko]

Updating and deploying the bedrock agent sample by changing the vector type to binary:

...
const kb = new bedrock.VectorKnowledgeBase(this, 'KB', {
      embeddingsModel: bedrock.BedrockFoundationModel.TITAN_EMBED_TEXT_V2_1024,
      vectorType: bedrock.VectorType.BINARY,
      instruction: 'Use this knowledge base to answer questions about books. ' +
        'It contains the full text of novels. Please quote the books to explain your answers.',
    });
...

Correctly deployed

:

[dineshSajwan]

LGTM

[mergify]

This pull request has been removed from the queue for the following reason: pull request dequeued.

Pull request #949 has been dequeued. The pull request could not be merged. This could be related to an activated branch protection or ruleset rule that prevents us from merging. (details: You're not authorized to push to this branch. Visit https://docs.github.com/repositories/configuring-branches-and-merges-in-your-repository/managing-protected-branches/about-protected-branches for more information.)

You should look at the reason for the failure and decide if the pull request needs to be fixed or if you want to requeue it.

If you want to requeue this pull request, you need to post a comment with the text: @mergifyio requeue