Agent Retrieve and Generate

Overview

You can use this Snap to query a specific Knowledge base for relevant context and use a designated model to generate responses based on the retrieved information.

Note: The Bedrock Agent RetrieveAndGenerate API can retrieve information from a Knowledge base or external sources (S3 or byte content). Currently, this Snap supports retrieval of information from an existing Knowledge base.

Agent Retrieve and Generate Overview

Prerequisites

Limitations and known issues

None.

Snap views

View Description Examples of upstream and downstream Snaps
Input This Snap supports a maximum of one binary or document input view. The binary input is inserted into the Prompt field.
Note: If you select the Binary input view, the Prompt field is hidden.
Output This Snap has at the most one document output view. The output document contains citations, guardrailAction, original output, and sessionID. Mapper
Error

Error handling is a generic way to handle errors without losing data or failing the Snap execution. You can handle the errors that the Snap might encounter when running the pipeline by choosing one of the following options from the When errors occur list under the Views tab. The available options are:

  • Stop Pipeline Execution Stops the current pipeline execution when the Snap encounters an error.
  • Discard Error Data and Continue Ignores the error, discards that record, and continues with the remaining records.
  • Route Error Data to Error View Routes the error data to an error view without stopping the Snap execution.

Learn more about Error handling in Pipelines.

Snap settings

Note:
  • Suggestion icon (): Indicates a list that is dynamically populated based on the configuration.
  • Expression icon (): Indicates whether the value is an expression (if enabled) or a static value (if disabled). Learn more about Using Expressions in SnapLogic.
  • Add icon (): Indicates that you can add fields in the field set.
  • Remove icon (): Indicates that you can remove fields from the field set.
Field / Field set Type Description
Label String

Required. Specify a unique name for the Snap. Modify this to be more appropriate, especially if more than one of the same Snaps is in the pipeline.

Default value: Agent Retrieve and Generate

Example: Customer support responses
Knowledge base ID String/Expression/Suggestion

Required. Specify the unique identifier of the Knowledge base that is queried. The suggested option for the Knowledge base is in the following format:

KNOWLEDGE_BASE_ID:KNOWLEDGE_BASE_NAME

Default value: N/A

Example: YJ4ASDF84:samplekb
Prompt String/Expression

Appears when you select Document as the Input type.

Required. Specify the prompt to the Bedrock Agent RetrieveandGenerate API endpoint as the user message.

Default value: N/A

Example: $msg
Model ARN String/Expression/Suggestion

Required. Specify the ARN of the foundation model used to generate a response. If the suggestible list is not populated, check your access to models.

Default value: N/A

Example: anthropic-claude-3-sonnet-20240118-v1.0
Session ID String/Expression

Session ID is automatically generated by Amazon Bedrock during the first conversation.

Note: Use the same value across requests to continue the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions.

Default value: N/A

Example: f02fab57-a483-40c3-877f-619b643d2775
Retrieve options Use this field set to configure the retrieve options to use for the request.
Search type Dropdown list/Expression
Choose the type of resource to query. The available options are:
  • DEFAULT: Allows Amazon Bedrock to determine the Search type to use.
  • SEMANTIC: Uses only vector embeddings.
  • HYBRID: Uses both vector embeddings and raw text. HYBRID is only valid if you are using an Amazon OpenSearch Serverless vector store that contains a filterable text field.
Number of results to retrieve Integer/Expression
Specify the number of source chunks to retrieve.
Note: The number of retrieved references in the response might be smaller, as the response only cites sources that are relevant to the query.

Minimum value: 1

Maximum value: 100

Default value: N/A

Example: 50
Model parameters Configure the parameters to tune the model runtime.
Maximum tokens Integer/Expression

Specify the maximum number of tokens to generate in the chat completion. If left blank, the default value of the endpoint is used.

Default value: N/A

Example: 50
Temperature Decimal/Expression

Specify the sampling temperature to use a decimal value between 0 and 1. If left blank, the default value of the endpoint is used.

Default value: N/A

Example: 0.2
Top P Decimal/Expression

Specify the nucleus sampling value, a decimal value between 0 and 1. If left blank, the default value of the endpoint is used.

Default value: N/A

Example: 0.2
Snap execution Dropdown list
Select one of the three modes in which the Snap executes. Available options are:
  • Validate & Execute. Performs limited execution of the Snap and generates a data preview during pipeline validation. Subsequently, performs full execution of the Snap (unlimited records) during pipeline runtime.
  • Execute only. Performs full execution of the Snap during pipeline execution without generating preview data.
  • Disabled. Disables the Snap and all Snaps that are downstream from it.

Default value: Validate & Execute

Example: Execute only

Troubleshooting

Error validating the parameters of the retrieve request.

The Model ARN provided is not supported.

Verify your configuration and retry the request. Refer to Amazon's documentation to view the models that support your Knowledge base queries.

Examples