Contains details about the Lambda function containing the business logic that is carried out upon invoking the action or the custom control method for handling the information elicited from the user.

Contains details about an action group.

Contains details about an agent.

Contains details about an action group.

Contains details about an alias of an agent.

Contains details about the history of the alias.

Contains details about the routing configuration of the alias.

Contains details about an alias of an agent.

Defines an agent node in your flow. You specify the agent to invoke at this point in the flow. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

Contains details about a knowledge base that is associated with an agent.

Contains details about a knowledge base associated with an agent.

Contains details about an agent.

Contains details about a version of an agent.

Contains details about a version of an agent.

Contains details about the OpenAPI schema for the action group. For more information, see Action group OpenAPI schemas. You can either include the schema directly in the payload field or you can upload it to an S3 bucket and specify the S3 bucket location in the s3 field.

The vector configuration details for the Bedrock embeddings model.

Settings for a foundation model used to parse documents for a data source.

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.

Defines a collector node in your flow. This node takes an iteration of inputs and consolidates them into an array in the output. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

Defines a condition node in your flow. You can specify conditions that determine which node comes next in the flow. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

The configuration of the Confluence content. For example, configuring specific types of Confluence content.

The configuration information to connect to Confluence as your data source.

The endpoint information to connect to your Confluence data source.

The configuration of filtering the data source content. For example, configuring regular expression patterns to include or exclude certain content.

Settings for customizing steps in the data source content ingestion pipeline.

Contains details about a data source.

The connection configuration for the data source.

Contains details about a data source.

The configuration details for the embeddings model.

Configurations for when you choose fixed-size chunking. If you set the chunkingStrategy as NONE, exclude this field.

Contains information about a version that the alias maps to.

Contains information about an alias of a flow.

Defines a condition in the condition node.

The configuration of a connection between a condition node and another node.

Contains information about a connection between two nodes in the flow.

The configuration of the connection.

The configuration of a connection originating from a node that isn't a Condition node.

The definition of the nodes and connections between nodes in the flow.

Contains configurations about a node in the flow.

Contains configurations for a node in your flow. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

Contains configurations for an input to a node.

Contains configurations for an output from a node.

Contains the definition of a flow.

Contains information about validation of the flow.

Contains information about a version of a flow.

Defines parameters that the agent needs to invoke from the user to complete the function. Corresponds to an action in an action group.

Defines functions that each define parameters that the agent needs to invoke from the user. Each function represents an action in an action group.

Details about the guardrail associated with an agent.

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.

Token settings for a layer in a hierarchical chunking configuration.

Contains inference parameters to use when the agent invokes a foundation model in the part of the agent sequence defined by the promptType. For more information, see Inference parameters for foundation models.

Contains details about an ingestion job, which converts a data source to embeddings for a vector store in knowledge base.

Defines a filter by which to filter the results.

Parameters by which to sort the results.

Contains the statistics for the ingestion job.

Contains details about an ingestion job.

Contains configurations for the input flow node for a flow. This node takes the input from flow invocation and passes it to the next node in the data type that you specify.

A location for storing content from data sources temporarily as it is processed by custom components in the ingestion pipeline.

Contains configurations for an iterator node in a flow. Takes an input that is an array and iteratively sends each item of the array as an output to the following node. The size of the array is also returned in the output.

Contains information about a knowledge base.

Contains details about the embeddings configuration of the knowledge base.

Contains configurations for a knowledge base node in a flow. This node takes a query as the input and returns, as the output, the retrieved responses directly (as an array) or a response generated based on the retrieved responses. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

Contains details about a knowledge base.

Contains configurations for a Lambda function node in the flow. You specify the Lambda function to invoke and the inputs into the function. The output is the response that is defined in the Lambda function. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

Contains configurations for a Lex node in the flow. You specify a Amazon Lex bot to invoke. This node takes an utterance as the input and returns as the output the intent identified by the Amazon Lex bot. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

Details of the memory configuration.

Contains details about the storage configuration of the knowledge base in MongoDB Atlas.

Contains the names of the fields to which to map information about the vector store.

Contains details about the storage configuration of the knowledge base in Amazon OpenSearch Service. For more information, see Create a vector index in Amazon OpenSearch Service.

Contains the names of the fields to which to map information about the vector store.

Contains configurations for an output flow node in the flow. You specify the data type expected for the input into the node in the type field and how to return the final output in the expression field.

Contains details about a parameter in a function for an action group.

Settings for parsing document contents. By default, the service converts the contents of each document into text before splitting it into chunks. To improve processing of PDF files with tables and images, you can configure the data source to convert the pages of text into images and use a model to describe the contents of each page.

Instructions for interpreting the contents of a document.

The specific filters applied to your data source content. You can filter out or include certain content.

The configuration of filtering certain objects or content types of the data source.

Contains details about the storage configuration of the knowledge base in Pinecone. For more information, see Create a vector index in Pinecone.

Contains the names of the fields to which to map information about the vector store.

Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.

Contains configurations for a prompt node in the flow. You can use a prompt from Prompt management or you can define one in this node. If the prompt contains variables, the inputs into this node will fill in the variables. The output from this node is the response generated by the model. For more information, see Node types in Amazon Bedrock works in the Amazon Bedrock User Guide.

Contains configurations for a prompt defined inline in the node.

Contains configurations for a prompt from Prompt management to use in a node.

Contains configurations for a prompt and whether it is from Prompt management or defined inline.

Contains inference configurations for the prompt.

Contains information about a variable in the prompt.

Contains a key-value pair that defines a metadata tag and value to attach to a prompt variant. For more information, see Create a prompt using Prompt management.

Contains inference configurations related to model inference for a prompt. For more information, see Inference parameters.

Contains configurations to override prompts in different parts of an agent sequence. For more information, see Advanced prompts.

Contains information about a prompt in your Prompt management tool.

Contains the message for a prompt. For more information, see Prompt management in Amazon Bedrock.

Contains details about a variant of the prompt.

Contains details about the storage configuration of the knowledge base in Amazon RDS. For more information, see Create a vector index in Amazon RDS.

Contains the names of the fields to which to map information about the vector store.

Contains details about the storage configuration of the knowledge base in Redis Enterprise Cloud. For more information, see Create a vector index in Redis Enterprise Cloud.

Contains the names of the fields to which to map information about the vector store.

Contains configurations for a Retrieval node in a flow. This node retrieves data from the Amazon S3 location that you specify and returns it as the output.

Contains configurations for the Amazon S3 location from which to retrieve data to return as the output from the node.

Contains configurations for the service to use for retrieving data to return as the output from the node.

The configuration information to connect to Amazon S3 as your data source.

The identifier information for an Amazon S3 bucket.

An Amazon S3 location.

The configuration of the Salesforce content. For example, configuring specific types of Salesforce content.

The configuration information to connect to Salesforce as your data source.

The endpoint information to connect to your Salesforce data source.

The seed or starting point URL. You should be authorized to crawl the URL.

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.

Contains the configuration for server-side encryption.

The configuration of the SharePoint content. For example, configuring specific types of SharePoint content.

The configuration information to connect to SharePoint as your data source.

The endpoint information to connect to your SharePoint data source.

Contains the storage configuration of the knowledge base.

Contains configurations for a Storage node in a flow. This node stores the input in an Amazon S3 location that you specify.

Contains configurations for the Amazon S3 location in which to store the input into the node.

Contains configurations for the service to use for storing the input into the node.

Contains configurations for a text prompt template. To include a variable, enclose a word in double curly braces as in {{variable}}.

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.

A Lambda function that processes documents.

A Lambda function that processes documents.

The configuration of web URLs that you want to crawl. You should be authorized to crawl the URLs.

Contains details about how to ingest the documents in a data source.

Contains details about the model used to create vector embeddings for the knowledge base.

The configuration of web URLs that you want to crawl. You should be authorized to crawl the URLs.

The rate limits for the URLs that you want to crawl. You should be authorized to crawl the URLs.

The configuration details for the web data source.

The configuration of the URL/URLs for the web content that you want to crawl. You should be authorized to crawl the URLs.

ENUM to check if action requires user confirmation