generative-ai-cdk-constructs

@cdklabs/generative-ai-cdk-constructs


@cdklabs/generative-ai-cdk-constructs / bedrock / WebCrawlerDataSourceAssociationProps

Interface: WebCrawlerDataSourceAssociationProps

Interface to add a new data source to an existing KB.

Extends

Extended by

Properties

chunkingStrategy?

readonly optional chunkingStrategy: ChunkingStrategy

The chunking stategy to use for splitting your documents or content. The chunks are then converted to embeddings and written to the vector index allowing for similarity search and retrieval of the content.

Default

ChunkingStrategy.DEFAULT

Inherited from

DataSourceAssociationProps.chunkingStrategy


contextEnrichment?

readonly optional contextEnrichment: ContextEnrichment

The context enrichment configuration to use.

Default

- No context enrichment is used.

Inherited from

DataSourceAssociationProps.contextEnrichment


crawlingRate?

readonly optional crawlingRate: number

The max rate at which pages are crawled, up to 300 per minute per host. Higher values will decrease sync time but increase the load on the host.

Default

300

crawlingScope?

readonly optional crawlingScope: CrawlingScope

The scope of the crawling.

Default

- CrawlingScope.DEFAULT

customTransformation?

readonly optional customTransformation: CustomTransformation

The custom transformation strategy to use.

Default

- No custom transformation is used.

Inherited from

DataSourceAssociationProps.customTransformation


dataDeletionPolicy?

readonly optional dataDeletionPolicy: DataDeletionPolicy

The data deletion policy to apply to the data source.

Default

- Sets the data deletion policy to the default of the data source type.

Inherited from

DataSourceAssociationProps.dataDeletionPolicy


dataSourceName?

readonly optional dataSourceName: string

The name of the data source.

Default

- A new name will be generated.

Inherited from

DataSourceAssociationProps.dataSourceName


description?

readonly optional description: string

A description of the data source.

Default

- No description is provided.

Inherited from

DataSourceAssociationProps.description


filters?

readonly optional filters: CrawlingFilters

The filters (regular expression patterns) for the crawling. If there’s a conflict, the exclude pattern takes precedence.

Default

None

kmsKey?

readonly optional kmsKey: IKey

The KMS key to use to encrypt the data source.

Default

- Service owned and managed key.

Inherited from

DataSourceAssociationProps.kmsKey


maxPages?

readonly optional maxPages: number

The maximum number of pages to crawl. The max number of web pages crawled from your source URLs, up to 25,000 pages. If the web pages exceed this limit, the data source sync will fail and no web pages will be ingested.

Default

- No limit

parsingStrategy?

readonly optional parsingStrategy: ParsingStategy

The parsing strategy to use.

Default

- No Parsing Stategy is used.

Inherited from

DataSourceAssociationProps.parsingStrategy


sourceUrls

readonly sourceUrls: string[]

The source urls in the format https://www.sitename.com. Maximum of 100 URLs.


userAgent?

readonly optional userAgent: string

The user agent string to use when crawling.

Default

- Default user agent string

userAgentHeader?

readonly optional userAgentHeader: string

The user agent header to use when crawling. A string used for identifying the crawler or bot when it accesses a web server. The user agent header value consists of the bedrockbot, UUID, and a user agent suffix for your crawler (if one is provided). By default, it is set to bedrockbot_UUID. You can optionally append a custom suffix to bedrockbot_UUID to allowlist a specific user agent permitted to access your source URLs.

Default

- Default user agent header (bedrockbot_UUID)