@propulsionworks/cloudformation 0.0.2 → 0.1.0

package/out/exports/resources.generated/aws-bedrock-datasource.d.ts

@@ -0,0 +1,743 @@
+import type { ResourceDefinitionWithAttributes } from "../main.ts";
+export type BedrockDataSource = ResourceDefinitionWithAttributes<"AWS::Bedrock::DataSource", BedrockDataSourceProps, BedrockDataSourceAttribs>;
+/**
+ * > Properties with `__Update requires: Replacement__` can result in the creation of a new data source and deletion of the old one. This can happen if you also change the Name of the data source.
+ *
+ * Specifies a data source as a resource in a top-level template. Minimally, you must specify the following properties:
+ *
+ * - Name – Specify a name for the data source.
+ * - KnowledgeBaseId – Specify the ID of the knowledge base for the data source to belong to.
+ * - DataSourceConfiguration – Specify information about the Amazon S3 bucket containing the data source. The following sub-properties are required:
+ *
+ * - Type – Specify the value `S3` .
+ *
+ * For more information about setting up data sources in Amazon Bedrock , see [Set up a data source for your knowledge base](https://docs.aws.amazon.com/bedrock/latest/userguide/knowledge-base-ds.html) .
+ *
+ * See the *Properties* section below for descriptions of both the required and optional properties.
+ */
+export type BedrockDataSourceProps = {
+    /**
+     * The data deletion policy for the data source.
+     */
+    DataDeletionPolicy?: DataDeletionPolicy | undefined;
+    /**
+     * The connection configuration for the data source.
+     */
+    DataSourceConfiguration: DataSourceConfiguration;
+    /**
+     * The description of the data source.
+     * @minLength 1
+     * @maxLength 200
+     */
+    Description?: string | undefined;
+    /**
+     * The unique identifier of the knowledge base to which the data source belongs.
+     * @pattern ^[0-9a-zA-Z]{10}$
+     */
+    KnowledgeBaseId: string;
+    /**
+     * The name of the data source.
+     * @pattern ^([0-9a-zA-Z][_-]?){1,100}$
+     */
+    Name: string;
+    /**
+     * Contains details about the configuration of the server-side encryption.
+     */
+    ServerSideEncryptionConfiguration?: ServerSideEncryptionConfiguration | undefined;
+    /**
+     * Contains details about how to ingest the documents in the data source.
+     */
+    VectorIngestionConfiguration?: VectorIngestionConfiguration | undefined;
+};
+export type BedrockDataSourceAttribs = {
+    /**
+     * The time at which the data source was created.
+     */
+    CreatedAt: string;
+    /**
+     * 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.
+     * @minLength 61
+     * @maxLength 86
+     */
+    "DataSourceConfiguration.WebConfiguration.CrawlerConfiguration.UserAgentHeader": string;
+    /**
+     * The unique identifier of the data source.
+     * @pattern ^[0-9a-zA-Z]{10}$
+     */
+    DataSourceId: string;
+    /**
+     * The status of the data source. The following statuses are possible:
+     *
+     * - Available – The data source has been created and is ready for ingestion into the knowledge base.
+     * - Deleting – The data source is being deleted.
+     */
+    DataSourceStatus: DataSourceStatus;
+    /**
+     * The detailed reasons on the failure to delete a data source.
+     */
+    FailureReasons: string[];
+    /**
+     * The time at which the data source was last updated.
+     */
+    UpdatedAt: string;
+};
+/**
+ * Contains configurations for using Amazon Bedrock Data Automation as the parser for ingesting your data sources.
+ */
+export type BedrockDataAutomationConfiguration = {
+    /**
+     * Specifies whether to enable parsing of multimodal data, including both text and/or images.
+     */
+    ParsingModality?: ParsingModality | undefined;
+};
+/**
+ * Settings for a foundation model used to parse documents for a data source.
+ */
+export type BedrockFoundationModelConfiguration = {
+    /**
+     * The ARN of the foundation model to use for parsing.
+     */
+    ModelArn: string;
+    /**
+     * Specifies whether to enable parsing of multimodal data, including both text and/or images.
+     */
+    ParsingModality?: ParsingModality | undefined;
+    /**
+     * Instructions for interpreting the contents of a document.
+     */
+    ParsingPrompt?: ParsingPrompt | undefined;
+};
+/**
+ * Context enrichment configuration is used to provide additional context to the RAG application using Amazon Bedrock foundation models.
+ */
+export type BedrockFoundationModelContextEnrichmentConfiguration = {
+    /**
+     * The enrichment stategy used to provide additional context. For example, Neptune GraphRAG uses Amazon Bedrock foundation models to perform chunk entity extraction.
+     */
+    EnrichmentStrategyConfiguration: EnrichmentStrategyConfiguration;
+    /**
+     * The Amazon Resource Name (ARN) of the model used to create vector embeddings for the knowledge base.
+     */
+    ModelArn: string;
+};
+/**
+ * Details about how to chunk the documents in the data source. A *chunk* refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
+ */
+export type ChunkingConfiguration = {
+    /**
+     * Knowledge base can split your source data into chunks. A *chunk* refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for `NONE` , then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
+     *
+     * - `FIXED_SIZE` – Amazon Bedrock splits your source data into chunks of the approximate size that you set in the `fixedSizeChunkingConfiguration` .
+     * - `HIERARCHICAL` – Split documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
+     * - `SEMANTIC` – Split documents into chunks based on groups of similar content derived with natural language processing.
+     * - `NONE` – Amazon Bedrock treats each file as one chunk. If you choose this option, you may want to pre-process your documents by splitting them into separate files.
+     */
+    ChunkingStrategy: ChunkingStrategy;
+    /**
+     * Configurations for when you choose fixed-size chunking. If you set the `chunkingStrategy` as `NONE` , exclude this field.
+     */
+    FixedSizeChunkingConfiguration?: FixedSizeChunkingConfiguration | undefined;
+    /**
+     * Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
+     */
+    HierarchicalChunkingConfiguration?: HierarchicalChunkingConfiguration | undefined;
+    /**
+     * Settings for semantic document chunking for a data source. Semantic chunking splits a document into into smaller documents based on groups of similar content derived from the text with natural language processing.
+     */
+    SemanticChunkingConfiguration?: SemanticChunkingConfiguration | undefined;
+};
+/**
+ * Knowledge base can split your source data into chunks. A chunk refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried. You have the following options for chunking your data. If you opt for NONE, then you may want to pre-process your files by splitting them up such that each file corresponds to a chunk.
+ */
+export type ChunkingStrategy = "FIXED_SIZE" | "NONE" | "HIERARCHICAL" | "SEMANTIC";
+/**
+ * The configuration of the Confluence content. For example, configuring specific types of Confluence content.
+ */
+export type ConfluenceCrawlerConfiguration = {
+    /**
+     * The configuration of filtering the Confluence content. For example, configuring regular expression patterns to include or exclude certain content.
+     */
+    FilterConfiguration?: CrawlFilterConfiguration | undefined;
+};
+/**
+ * The configuration information to connect to Confluence as your data source.
+ */
+export type ConfluenceDataSourceConfiguration = {
+    /**
+     * The configuration of the Confluence content. For example, configuring specific types of Confluence content.
+     */
+    CrawlerConfiguration?: ConfluenceCrawlerConfiguration | undefined;
+    /**
+     * The endpoint information to connect to your Confluence data source.
+     */
+    SourceConfiguration: ConfluenceSourceConfiguration;
+};
+/**
+ * The endpoint information to connect to your Confluence data source.
+ */
+export type ConfluenceSourceConfiguration = {
+    /**
+     * The supported authentication type to authenticate and connect to your Confluence instance.
+     */
+    AuthType: "BASIC" | "OAUTH2_CLIENT_CREDENTIALS";
+    /**
+     * The Amazon Resource Name of an AWS Secrets Manager secret that stores your authentication credentials for your Confluence instance URL. For more information on the key-value pairs that must be included in your secret, depending on your authentication type, see [Confluence connection configuration](https://docs.aws.amazon.com/bedrock/latest/userguide/confluence-data-source-connector.html#configuration-confluence-connector) .
+     * @pattern ^arn:aws(|-cn|-us-gov):secretsmanager:[a-z0-9-]{1,20}:([0-9]{12}|):secret:[a-zA-Z0-9!/_+=.@-]{1,512}$
+     */
+    CredentialsSecretArn: string;
+    /**
+     * The supported host type, whether online/cloud or server/on-premises.
+     */
+    HostType: "SAAS";
+    /**
+     * The Confluence host URL or instance URL.
+     * @minLength 1
+     * @maxLength 2048
+     * @pattern ^https://[A-Za-z0-9][^\s]*$
+     */
+    HostUrl: string;
+};
+/**
+ * Context enrichment configuration is used to provide additional context to the RAG application.
+ */
+export type ContextEnrichmentConfiguration = {
+    /**
+     * The configuration of the Amazon Bedrock foundation model used for context enrichment.
+     */
+    BedrockFoundationModelConfiguration?: BedrockFoundationModelContextEnrichmentConfiguration | undefined;
+    /**
+     * The method used for context enrichment. It must be Amazon Bedrock foundation models.
+     */
+    Type: ContextEnrichmentType;
+};
+/**
+ * Enrichment type to be used for the vector database.
+ */
+export type ContextEnrichmentType = "BEDROCK_FOUNDATION_MODEL";
+/**
+ * The configuration of filtering the data source content. For example, configuring regular expression patterns to include or exclude certain content.
+ */
+export type CrawlFilterConfiguration = {
+    /**
+     * The configuration of filtering certain objects or content types of the data source.
+     */
+    PatternObjectFilter?: PatternObjectFilterConfiguration | undefined;
+    /**
+     * The type of filtering that you want to apply to certain objects or content of the data source. For example, the `PATTERN` type is regular expression patterns you can apply to filter your content.
+     */
+    Type: "PATTERN";
+};
+/**
+ * Settings for customizing steps in the data source content ingestion pipeline.
+ *
+ * You can configure the data source to process documents with a Lambda function after they are parsed and converted into chunks. When you add a post-chunking transformation, the service stores chunked documents in an S3 bucket and invokes a Lambda function to process them.
+ *
+ * To process chunked documents with a Lambda function, define an S3 bucket path for input and output objects, and a transformation that specifies the Lambda function to invoke. You can use the Lambda function to customize how chunks are split, and the metadata for each chunk.
+ */
+export type CustomTransformationConfiguration = {
+    /**
+     * An S3 bucket path for input and output objects.
+     */
+    IntermediateStorage: IntermediateStorage;
+    /**
+     * A Lambda function that processes documents.
+     */
+    Transformations: Transformation[];
+};
+/**
+ * The deletion policy for the data source.
+ */
+export type DataDeletionPolicy = "RETAIN" | "DELETE";
+/**
+ * The connection configuration for the data source.
+ */
+export type DataSourceConfiguration = {
+    /**
+     * The configuration information to connect to Confluence as your data source.
+     *
+     * > Confluence data source connector is in preview release and is subject to change.
+     */
+    ConfluenceConfiguration?: ConfluenceDataSourceConfiguration | undefined;
+    /**
+     * The configuration information to connect to Amazon S3 as your data source.
+     */
+    S3Configuration?: S3DataSourceConfiguration | undefined;
+    /**
+     * The configuration information to connect to Salesforce as your data source.
+     *
+     * > Salesforce data source connector is in preview release and is subject to change.
+     */
+    SalesforceConfiguration?: SalesforceDataSourceConfiguration | undefined;
+    /**
+     * The configuration information to connect to SharePoint as your data source.
+     *
+     * > SharePoint data source connector is in preview release and is subject to change.
+     */
+    SharePointConfiguration?: SharePointDataSourceConfiguration | undefined;
+    /**
+     * The type of data source.
+     */
+    Type: DataSourceType;
+    /**
+     * The configuration of web URLs to crawl for your data source. You should be authorized to crawl the URLs.
+     *
+     * > Crawling web URLs as your data source is in preview release and is subject to change.
+     */
+    WebConfiguration?: WebDataSourceConfiguration | undefined;
+};
+/**
+ * The status of a data source.
+ */
+export type DataSourceStatus = "AVAILABLE" | "DELETING" | "DELETE_UNSUCCESSFUL";
+/**
+ * The type of the data source location.
+ */
+export type DataSourceType = "S3" | "CONFLUENCE" | "SALESFORCE" | "SHAREPOINT" | "WEB" | "CUSTOM" | "REDSHIFT_METADATA";
+/**
+ * The strategy used for performing context enrichment.
+ */
+export type EnrichmentStrategyConfiguration = {
+    /**
+     * The method used for the context enrichment strategy.
+     */
+    Method: EnrichmentStrategyMethod;
+};
+/**
+ * Enrichment Strategy method.
+ */
+export type EnrichmentStrategyMethod = "CHUNK_ENTITY_EXTRACTION";
+/**
+ * Configurations for when you choose fixed-size chunking. If you set the `chunkingStrategy` as `NONE` , exclude this field.
+ */
+export type FixedSizeChunkingConfiguration = {
+    /**
+     * The maximum number of tokens to include in a chunk.
+     * @min 1
+     */
+    MaxTokens: number;
+    /**
+     * The percentage of overlap between adjacent chunks of a data source.
+     * @min 1
+     * @max 99
+     */
+    OverlapPercentage: number;
+};
+/**
+ * Settings for hierarchical document chunking for a data source. Hierarchical chunking splits documents into layers of chunks where the first layer contains large chunks, and the second layer contains smaller chunks derived from the first layer.
+ *
+ * You configure the number of tokens to overlap, or repeat across adjacent chunks. For example, if you set overlap tokens to 60, the last 60 tokens in the first chunk are also included at the beginning of the second chunk. For each layer, you must also configure the maximum number of tokens in a chunk.
+ */
+export type HierarchicalChunkingConfiguration = {
+    /**
+     * Token settings for each layer.
+     */
+    LevelConfigurations: HierarchicalChunkingLevelConfiguration[];
+    /**
+     * The number of tokens to repeat across chunks in the same layer.
+     * @min 1
+     */
+    OverlapTokens: number;
+};
+/**
+ * Token settings for a layer in a hierarchical chunking configuration.
+ */
+export type HierarchicalChunkingLevelConfiguration = {
+    /**
+     * The maximum number of tokens that a chunk can contain in this layer.
+     * @min 1
+     * @max 8192
+     */
+    MaxTokens: number;
+};
+/**
+ * A location for storing content from data sources temporarily as it is processed by custom components in the ingestion pipeline.
+ */
+export type IntermediateStorage = {
+    /**
+     * An S3 bucket path.
+     */
+    S3Location: S3Location;
+};
+/**
+ * Settings for parsing document contents. If you exclude this field, the default parser converts the contents of each document into text before splitting it into chunks. Specify the parsing strategy to use in the `parsingStrategy` field and include the relevant configuration, or omit it to use the Amazon Bedrock default parser. For more information, see [Parsing options for your data source](https://docs.aws.amazon.com/bedrock/latest/userguide/kb-advanced-parsing.html) .
+ *
+ * > If you specify `BEDROCK_DATA_AUTOMATION` or `BEDROCK_FOUNDATION_MODEL` and it fails to parse a file, the Amazon Bedrock default parser will be used instead.
+ */
+export type ParsingConfiguration = {
+    /**
+     * If you specify `BEDROCK_DATA_AUTOMATION` as the parsing strategy for ingesting your data source, use this object to modify configurations for using the Amazon Bedrock Data Automation parser.
+     */
+    BedrockDataAutomationConfiguration?: BedrockDataAutomationConfiguration | undefined;
+    /**
+     * If you specify `BEDROCK_FOUNDATION_MODEL` as the parsing strategy for ingesting your data source, use this object to modify configurations for using a foundation model to parse documents.
+     */
+    BedrockFoundationModelConfiguration?: BedrockFoundationModelConfiguration | undefined;
+    /**
+     * The parsing strategy for the data source.
+     */
+    ParsingStrategy: ParsingStrategy;
+};
+/**
+ * Determine how will parsed content be stored.
+ */
+export type ParsingModality = "MULTIMODAL";
+/**
+ * Instructions for interpreting the contents of a document.
+ */
+export type ParsingPrompt = {
+    /**
+     * Instructions for interpreting the contents of a document.
+     * @minLength 1
+     * @maxLength 10000
+     */
+    ParsingPromptText: string;
+};
+/**
+ * The parsing strategy for the data source.
+ */
+export type ParsingStrategy = "BEDROCK_FOUNDATION_MODEL" | "BEDROCK_DATA_AUTOMATION";
+/**
+ * The specific filters applied to your data source content. You can filter out or include certain content.
+ */
+export type PatternObjectFilter = {
+    /**
+     * A list of one or more exclusion regular expression patterns to exclude certain object types that adhere to the pattern. If you specify an inclusion and exclusion filter/pattern and both match a document, the exclusion filter takes precedence and the document isn’t crawled.
+     */
+    ExclusionFilters?: string[] | undefined;
+    /**
+     * A list of one or more inclusion regular expression patterns to include certain object types that adhere to the pattern. If you specify an inclusion and exclusion filter/pattern and both match a document, the exclusion filter takes precedence and the document isn’t crawled.
+     */
+    InclusionFilters?: string[] | undefined;
+    /**
+     * The supported object type or content type of the data source.
+     * @minLength 1
+     * @maxLength 50
+     */
+    ObjectType: string;
+};
+/**
+ * The configuration of filtering certain objects or content types of the data source.
+ */
+export type PatternObjectFilterConfiguration = {
+    /**
+     * The configuration of specific filters applied to your data source content. You can filter out or include certain content.
+     */
+    Filters: PatternObjectFilter[];
+};
+/**
+ * The configuration information to connect to Amazon S3 as your data source.
+ */
+export type S3DataSourceConfiguration = {
+    /**
+     * The Amazon Resource Name (ARN) of the S3 bucket that contains your data.
+     * @minLength 1
+     * @maxLength 2048
+     * @pattern ^arn:aws(|-cn|-us-gov):s3:::[a-z0-9][a-z0-9.-]{1,61}[a-z0-9]$
+     */
+    BucketArn: string;
+    /**
+     * The account ID for the owner of the S3 bucket.
+     * @minLength 12
+     * @maxLength 12
+     * @pattern ^[0-9]{12}$
+     */
+    BucketOwnerAccountId?: string | undefined;
+    /**
+     * A list of S3 prefixes to include certain files or content. For more information, see [Organizing objects using prefixes](https://docs.aws.amazon.com/AmazonS3/latest/userguide/using-prefixes.html) .
+     */
+    InclusionPrefixes?: string[] | undefined;
+};
+/**
+ * A storage location in an Amazon S3 bucket.
+ */
+export type S3Location = {
+    /**
+     * An object URI starting with `s3://` .
+     * @minLength 1
+     * @maxLength 2048
+     * @pattern ^s3://.{1,128}$
+     */
+    URI: string;
+};
+/**
+ * The configuration of the Salesforce content. For example, configuring specific types of Salesforce content.
+ */
+export type SalesforceCrawlerConfiguration = {
+    /**
+     * The configuration of filtering the Salesforce content. For example, configuring regular expression patterns to include or exclude certain content.
+     */
+    FilterConfiguration?: CrawlFilterConfiguration | undefined;
+};
+/**
+ * The configuration information to connect to Salesforce as your data source.
+ */
+export type SalesforceDataSourceConfiguration = {
+    /**
+     * The configuration of the Salesforce content. For example, configuring specific types of Salesforce content.
+     */
+    CrawlerConfiguration?: SalesforceCrawlerConfiguration | undefined;
+    /**
+     * The endpoint information to connect to your Salesforce data source.
+     */
+    SourceConfiguration: SalesforceSourceConfiguration;
+};
+/**
+ * The endpoint information to connect to your Salesforce data source.
+ */
+export type SalesforceSourceConfiguration = {
+    /**
+     * The supported authentication type to authenticate and connect to your Salesforce instance.
+     */
+    AuthType: "OAUTH2_CLIENT_CREDENTIALS";
+    /**
+     * The Amazon Resource Name of an AWS Secrets Manager secret that stores your authentication credentials for your Salesforce instance URL. For more information on the key-value pairs that must be included in your secret, depending on your authentication type, see [Salesforce connection configuration](https://docs.aws.amazon.com/bedrock/latest/userguide/salesforce-data-source-connector.html#configuration-salesforce-connector) .
+     * @pattern ^arn:aws(|-cn|-us-gov):secretsmanager:[a-z0-9-]{1,20}:([0-9]{12}|):secret:[a-zA-Z0-9!/_+=.@-]{1,512}$
+     */
+    CredentialsSecretArn: string;
+    /**
+     * The Salesforce host URL or instance URL.
+     * @minLength 1
+     * @maxLength 2048
+     * @pattern ^https://[A-Za-z0-9][^\s]*$
+     */
+    HostUrl: string;
+};
+/**
+ * The seed or starting point URL. You should be authorized to crawl the URL.
+ */
+export type SeedUrl = {
+    /**
+     * A seed or starting point URL.
+     * @pattern ^https?://[A-Za-z0-9][^\s]*$
+     */
+    Url: string;
+};
+/**
+ * Settings for semantic document chunking for a data source. Semantic chunking splits a document into into smaller documents based on groups of similar content derived from the text with natural language processing.
+ *
+ * With semantic chunking, each sentence is compared to the next to determine how similar they are. You specify a threshold in the form of a percentile, where adjacent sentences that are less similar than that percentage of sentence pairs are divided into separate chunks. For example, if you set the threshold to 90, then the 10 percent of sentence pairs that are least similar are split. So if you have 101 sentences, 100 sentence pairs are compared, and the 10 with the least similarity are split, creating 11 chunks. These chunks are further split if they exceed the max token size.
+ *
+ * You must also specify a buffer size, which determines whether sentences are compared in isolation, or within a moving context window that includes the previous and following sentence. For example, if you set the buffer size to `1` , the embedding for sentence 10 is derived from sentences 9, 10, and 11 combined.
+ */
+export type SemanticChunkingConfiguration = {
+    /**
+     * The dissimilarity threshold for splitting chunks.
+     * @min 50
+     * @max 99
+     */
+    BreakpointPercentileThreshold: number;
+    /**
+     * The buffer size.
+     * @min 0
+     * @max 1
+     */
+    BufferSize: number;
+    /**
+     * The maximum number of tokens that a chunk can contain.
+     * @min 1
+     */
+    MaxTokens: number;
+};
+/**
+ * Contains the configuration for server-side encryption.
+ */
+export type ServerSideEncryptionConfiguration = {
+    /**
+     * The Amazon Resource Name (ARN) of the AWS KMS key used to encrypt the resource.
+     * @minLength 1
+     * @maxLength 2048
+     * @pattern ^arn:aws(|-cn|-us-gov):kms:[a-zA-Z0-9-]*:[0-9]{12}:key/[a-zA-Z0-9-]{36}$
+     */
+    KmsKeyArn?: string | undefined;
+};
+/**
+ * The configuration of the SharePoint content. For example, configuring specific types of SharePoint content.
+ */
+export type SharePointCrawlerConfiguration = {
+    /**
+     * The configuration of filtering the SharePoint content. For example, configuring regular expression patterns to include or exclude certain content.
+     */
+    FilterConfiguration?: CrawlFilterConfiguration | undefined;
+};
+/**
+ * The configuration information to connect to SharePoint as your data source.
+ */
+export type SharePointDataSourceConfiguration = {
+    /**
+     * The configuration of the SharePoint content. For example, configuring specific types of SharePoint content.
+     */
+    CrawlerConfiguration?: SharePointCrawlerConfiguration | undefined;
+    /**
+     * The endpoint information to connect to your SharePoint data source.
+     */
+    SourceConfiguration: SharePointSourceConfiguration;
+};
+/**
+ * The endpoint information to connect to your SharePoint data source.
+ */
+export type SharePointSourceConfiguration = {
+    /**
+     * The supported authentication type to authenticate and connect to your SharePoint site/sites.
+     */
+    AuthType: "OAUTH2_CLIENT_CREDENTIALS" | "OAUTH2_SHAREPOINT_APP_ONLY_CLIENT_CREDENTIALS";
+    /**
+     * The Amazon Resource Name of an AWS Secrets Manager secret that stores your authentication credentials for your SharePoint site/sites. For more information on the key-value pairs that must be included in your secret, depending on your authentication type, see [SharePoint connection configuration](https://docs.aws.amazon.com/bedrock/latest/userguide/sharepoint-data-source-connector.html#configuration-sharepoint-connector) .
+     * @pattern ^arn:aws(|-cn|-us-gov):secretsmanager:[a-z0-9-]{1,20}:([0-9]{12}|):secret:[a-zA-Z0-9!/_+=.@-]{1,512}$
+     */
+    CredentialsSecretArn: string;
+    /**
+     * The domain of your SharePoint instance or site URL/URLs.
+     * @minLength 1
+     * @maxLength 50
+     */
+    Domain: string;
+    /**
+     * The supported host type, whether online/cloud or server/on-premises.
+     */
+    HostType: "ONLINE";
+    /**
+     * A list of one or more SharePoint site URLs.
+     */
+    SiteUrls: string[];
+    /**
+     * The identifier of your Microsoft 365 tenant.
+     * @pattern ^[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{12}$
+     */
+    TenantId?: string | undefined;
+};
+/**
+ * A custom processing step for documents moving through a data source ingestion pipeline. To process documents after they have been converted into chunks, set the step to apply to `POST_CHUNKING` .
+ */
+export type Transformation = {
+    /**
+     * When the service applies the transformation.
+     */
+    StepToApply: "POST_CHUNKING";
+    /**
+     * A Lambda function that processes documents.
+     */
+    TransformationFunction: TransformationFunction;
+};
+/**
+ * A Lambda function that processes documents.
+ */
+export type TransformationFunction = {
+    /**
+     * The Lambda function.
+     */
+    TransformationLambdaConfiguration: TransformationLambdaConfiguration;
+};
+/**
+ * A Lambda function that processes documents.
+ */
+export type TransformationLambdaConfiguration = {
+    /**
+     * The function's ARN identifier.
+     * @minLength 0
+     * @maxLength 2048
+     * @pattern ^arn:(aws[a-zA-Z-]*)?:lambda:[a-z]{2}(-gov)?-[a-z]+-\d{1}:\d{12}:function:[a-zA-Z0-9-_\.]+(:(\$LATEST|[a-zA-Z0-9-_]+))?$
+     */
+    LambdaArn: string;
+};
+/**
+ * The configuration of web URLs that you want to crawl. You should be authorized to crawl the URLs.
+ */
+export type UrlConfiguration = {
+    /**
+     * One or more seed or starting point URLs.
+     */
+    SeedUrls: SeedUrl[];
+};
+/**
+ * Contains details about how to ingest the documents in a data source.
+ */
+export type VectorIngestionConfiguration = {
+    /**
+     * Details about how to chunk the documents in the data source. A *chunk* refers to an excerpt from a data source that is returned when the knowledge base that it belongs to is queried.
+     */
+    ChunkingConfiguration?: ChunkingConfiguration | undefined;
+    /**
+     * The context enrichment configuration used for ingestion of the data into the vector store.
+     */
+    ContextEnrichmentConfiguration?: ContextEnrichmentConfiguration | undefined;
+    /**
+     * A custom document transformer for parsed data source documents.
+     */
+    CustomTransformationConfiguration?: CustomTransformationConfiguration | undefined;
+    /**
+     * Configurations for a parser to use for parsing documents in your data source. If you exclude this field, the default parser will be used.
+     */
+    ParsingConfiguration?: ParsingConfiguration | undefined;
+};
+/**
+ * The configuration of web URLs that you want to crawl. You should be authorized to crawl the URLs.
+ */
+export type WebCrawlerConfiguration = {
+    /**
+     * The configuration of crawl limits for the web URLs.
+     */
+    CrawlerLimits?: WebCrawlerLimits | undefined;
+    /**
+     * A list of one or more exclusion regular expression patterns to exclude certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
+     */
+    ExclusionFilters?: string[] | undefined;
+    /**
+     * A list of one or more inclusion regular expression patterns to include certain URLs. If you specify an inclusion and exclusion filter/pattern and both match a URL, the exclusion filter takes precedence and the web content of the URL isn’t crawled.
+     */
+    InclusionFilters?: string[] | undefined;
+    /**
+     * The scope of what is crawled for your URLs.
+     *
+     * You can choose to crawl only web pages that belong to the same host or primary domain. For example, only web pages that contain the seed URL "https://docs.aws.amazon.com/bedrock/latest/userguide/" and no other domains. You can choose to include sub domains in addition to the host or primary domain. For example, web pages that contain "aws.amazon.com" can also include sub domain "docs.aws.amazon.com".
+     */
+    Scope?: WebScopeType | undefined;
+    /**
+     * Returns the user agent suffix for your web crawler.
+     * @minLength 15
+     * @maxLength 40
+     */
+    UserAgent?: string | undefined;
+};
+/**
+ * The rate limits for the URLs that you want to crawl. You should be authorized to crawl the URLs.
+ */
+export type WebCrawlerLimits = {
+    /**
+     * 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.
+     * @min 1
+     */
+    MaxPages?: number | undefined;
+    /**
+     * The max rate at which pages are crawled, up to 300 per minute per host.
+     * @min 1
+     * @max 300
+     */
+    RateLimit?: number | undefined;
+};
+/**
+ * The configuration details for the web data source.
+ */
+export type WebDataSourceConfiguration = {
+    /**
+     * The Web Crawler configuration details for the web data source.
+     */
+    CrawlerConfiguration?: WebCrawlerConfiguration | undefined;
+    /**
+     * The source configuration details for the web data source.
+     */
+    SourceConfiguration: WebSourceConfiguration;
+};
+/**
+ * The scope that a web crawl job will be restricted to.
+ */
+export type WebScopeType = "HOST_ONLY" | "SUBDOMAINS";
+/**
+ * The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.
+ */
+export type WebSourceConfiguration = {
+    /**
+     * The configuration of the URL/URLs.
+     */
+    UrlConfiguration: UrlConfiguration;
+};
+//# sourceMappingURL=aws-bedrock-datasource.d.ts.map