2025/12/01 - Agents for Amazon Bedrock Runtime - 7 updated api methods
Changes Support audio and video content retrieval on Bedrock Knowledge Bases.
{'completion': {'chunk': {'attribution': {'citations': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}},
'trace': {'trace': {'orchestrationTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}},
'routingClassifierTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}}}}}}
Sends a prompt for the agent to process and respond to. Note the following fields for the request:
To continue the same conversation with an agent, use the same sessionId value in the request.
To activate trace enablement, turn enableTrace to true. Trace enablement helps you follow the agent's reasoning process that led it to the information it processed, the actions it took, and the final result it yielded. For more information, see Trace enablement.
End a conversation by setting endSession to true.
In the sessionState object, you can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group.
The response contains both chunk and trace attributes.
The final response is returned in the bytes field of the chunk object. The InvokeAgent returns one chunk for the entire interaction.
The attribution object contains citations for parts of the response.
If you set enableTrace to true in the request, you can trace the agent's steps and reasoning process that led it to the response.
If the action predicted was configured to return control, the response returns parameters for the action, elicited from the user, in the returnControl field.
Errors are also surfaced in the response.
See also: AWS API Documentation
Request Syntax
client.invoke_agent(
agentAliasId='string',
agentId='string',
bedrockModelConfigurations={
'performanceConfig': {
'latency': 'standard'|'optimized'
}
},
enableTrace=True|False,
endSession=True|False,
inputText='string',
memoryId='string',
promptCreationConfigurations={
'excludePreviousThinkingSteps': True|False,
'previousConversationTurnsToInclude': 123
},
sessionId='string',
sessionState={
'conversationHistory': {
'messages': [
{
'content': [
{
'text': 'string'
},
],
'role': 'user'|'assistant'
},
]
},
'files': [
{
'name': 'string',
'source': {
'byteContent': {
'data': b'bytes',
'mediaType': 'string'
},
's3Location': {
'uri': 'string'
},
'sourceType': 'S3'|'BYTE_CONTENT'
},
'useCase': 'CODE_INTERPRETER'|'CHAT'
},
],
'invocationId': 'string',
'knowledgeBaseConfigurations': [
{
'knowledgeBaseId': 'string',
'retrievalConfiguration': {
'vectorSearchConfiguration': {
'filter': {
'andAll': [
{'... recursive ...'},
],
'equals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'in': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'listContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notIn': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'orAll': [
{'... recursive ...'},
],
'startsWith': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'stringContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
}
},
'implicitFilterConfiguration': {
'metadataAttributes': [
{
'description': 'string',
'key': 'string',
'type': 'STRING'|'NUMBER'|'BOOLEAN'|'STRING_LIST'
},
],
'modelArn': 'string'
},
'numberOfResults': 123,
'overrideSearchType': 'HYBRID'|'SEMANTIC',
'rerankingConfiguration': {
'bedrockRerankingConfiguration': {
'metadataConfiguration': {
'selectionMode': 'SELECTIVE'|'ALL',
'selectiveModeConfiguration': {
'fieldsToExclude': [
{
'fieldName': 'string'
},
],
'fieldsToInclude': [
{
'fieldName': 'string'
},
]
}
},
'modelConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'modelArn': 'string'
},
'numberOfRerankedResults': 123
},
'type': 'BEDROCK_RERANKING_MODEL'
}
}
}
},
],
'promptSessionAttributes': {
'string': 'string'
},
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
],
'sessionAttributes': {
'string': 'string'
}
},
sourceArn='string',
streamingConfigurations={
'applyGuardrailInterval': 123,
'streamFinalResponse': True|False
}
)
string
[REQUIRED]
The alias of the agent to use.
string
[REQUIRED]
The unique identifier of the agent to use.
dict
Model performance settings for the request.
performanceConfig (dict) --
The performance configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
boolean
Specifies whether to turn on the trace or not to track the agent's reasoning process. For more information, see Trace enablement.
boolean
Specifies whether to end the session with the agent or not.
string
The prompt text to send the agent.
string
The unique identifier of the agent memory.
dict
Specifies parameters that control how the service populates the agent prompt for an InvokeAgent request. You can control which aspects of previous invocations in the same agent session the service uses to populate the agent prompt. This gives you more granular control over the contextual history that is used to process the current request.
excludePreviousThinkingSteps (boolean) --
If true, the service removes any content between <thinking> tags from previous conversations in an agent session. The service will only remove content from already processed turns. This helps you remove content which might not be useful for current and subsequent invocations. This can reduce the input token count and potentially save costs. The default value is false.
previousConversationTurnsToInclude (integer) --
The number of previous conversations from the ongoing agent session to include in the conversation history of the agent prompt, during the current invocation. This gives you more granular control over the context that the model is made aware of, and helps the model remove older context which is no longer useful during the ongoing agent session.
string
[REQUIRED]
The unique identifier of the session. Use the same value across requests to continue the same conversation.
dict
Contains parameters that specify various attributes of the session. For more information, see Control session context.
conversationHistory (dict) --
The state's conversation history.
messages (list) --
The conversation's messages.
(dict) --
Details about a message.
content (list) -- [REQUIRED]
The message's content.
(dict) --
A content block.
text (string) --
The block's text.
role (string) -- [REQUIRED]
The message's role.
files (list) --
Contains information about the files used by code interpreter.
(dict) --
Contains details of the source files.
name (string) -- [REQUIRED]
The name of the source file.
source (dict) -- [REQUIRED]
Specifies where the files are located.
byteContent (dict) --
The data and the text of the attached files.
data (bytes) -- [REQUIRED]
The raw bytes of the file to attach. The maximum size of all files that is attached is 10MB. You can attach a maximum of 5 files.
mediaType (string) -- [REQUIRED]
The MIME type of data contained in the file used for chat.
s3Location (dict) --
The s3 location of the files to attach.
uri (string) -- [REQUIRED]
The uri of the s3 object.
sourceType (string) -- [REQUIRED]
The source type of the files to attach.
useCase (string) -- [REQUIRED]
Specifies how the source files will be used by the code interpreter.
invocationId (string) --
The identifier of the invocation of an action. This value must match the invocationId returned in the InvokeAgent response for the action whose results are provided in the returnControlInvocationResults field. For more information, see Return control to the agent developer and Control session context.
knowledgeBaseConfigurations (list) --
An array of configurations, each of which applies to a knowledge base attached to the agent.
(dict) --
Configurations to apply to a knowledge base attached to the agent during query. For more information, see Knowledge base retrieval configurations.
knowledgeBaseId (string) -- [REQUIRED]
The unique identifier for a knowledge base attached to the agent.
retrievalConfiguration (dict) -- [REQUIRED]
The configurations to apply to the knowledge base during query. For more information, see Query configurations.
vectorSearchConfiguration (dict) -- [REQUIRED]
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
filter (dict) --
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
andAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
equals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is cat:
"equals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than 1989:
"greaterThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989:
"greaterThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
in (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either cat or dog:
"in": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to 1989.
"lessThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to 1989.
"lessThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
listContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"]).
"listContains": { "key": "animals", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notEquals (dict) --
Knowledge base data sources are returned when:
It contains a metadata attribute whose name matches the key and whose value doesn't match the value in this object.
The key is not present in the document.
The following example would return data sources that don't contain an animal attribute whose value is cat.
"notEquals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notIn (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither cat nor dog.
"notIn": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
orAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
startsWith (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).
"startsWith": { "key": "animal", "value": "ca" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
stringContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat). "stringContains": { "key": "animal", "value": "at" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"]). "stringContains": { "key": "animals", "value": "at" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
implicitFilterConfiguration (dict) --
Settings for implicit filtering.
metadataAttributes (list) -- [REQUIRED]
Metadata that can be used in a filter.
(dict) --
Details about a metadata attribute.
description (string) -- [REQUIRED]
The attribute's description.
key (string) -- [REQUIRED]
The attribute's key.
type (string) -- [REQUIRED]
The attribute's type.
modelArn (string) -- [REQUIRED]
The model that generates the filter.
numberOfResults (integer) --
The number of source chunks to retrieve.
overrideSearchType (string) --
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
rerankingConfiguration (dict) --
Contains configurations for reranking the retrieved results. For more information, see Improve the relevance of query responses with a reranker model.
bedrockRerankingConfiguration (dict) --
Contains configurations for an Amazon Bedrock reranker model.
metadataConfiguration (dict) --
Contains configurations for the metadata to use in reranking.
selectionMode (string) -- [REQUIRED]
Specifies whether to consider all metadata when reranking, or only the metadata that you select. If you specify SELECTIVE, include the selectiveModeConfiguration field.
selectiveModeConfiguration (dict) --
Contains configurations for the metadata fields to include or exclude when considering reranking.
fieldsToExclude (list) --
An array of objects, each of which specifies a metadata field to exclude from consideration when reranking.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
fieldsToInclude (list) --
An array of objects, each of which specifies a metadata field to include in consideration when reranking. The remaining metadata fields are ignored.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
modelConfiguration (dict) -- [REQUIRED]
Contains configurations for the reranker model.
additionalModelRequestFields (dict) --
A JSON object whose keys are request fields for the model and whose values are values for those fields.
(string) --
(:ref:`document<document>`) --
modelArn (string) -- [REQUIRED]
The ARN of the reranker model to use.
numberOfRerankedResults (integer) --
The number of results to return after reranking.
type (string) -- [REQUIRED]
The type of reranker model.
promptSessionAttributes (dict) --
Contains attributes that persist across a prompt and the values of those attributes.
In orchestration prompt template, these attributes replace the $prompt_session_attributes$ placeholder variable. For more information, see Prompt template placeholder variables.
In multi-agent collaboration, the promptSessionAttributes will only be used by supervisor agent when $prompt_session_attributes$ is present in prompt template.
(string) --
(string) --
returnControlInvocationResults (list) --
Contains information about the results from the action group invocation. For more information, see Return control to the agent developer and Control session context.
(dict) --
A result from the invocation of an action. For more information, see Return control to the agent developer and Control session context.
This data type is used in the following API operations:
apiResult (dict) --
The result from the API response from the action group invocation.
actionGroup (string) -- [REQUIRED]
The action group that the API operation belongs to.
agentId (string) --
The agent's ID.
apiPath (string) --
The path to the API operation.
confirmationState (string) --
Controls the API operations or functions to invoke based on the user confirmation.
httpMethod (string) --
The HTTP method for the API operation.
httpStatusCode (integer) --
http status code from API execution response (for example: 200, 400, 500).
responseBody (dict) --
The response body from the API operation. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.
(string) --
(dict) --
Contains the body of the API response.
This data type is used in the following API operations:
In the returnControlInvocationResults field of the InvokeAgent request
body (string) --
The body of the API response.
images (list) --
Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
(dict) --
Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
format (string) -- [REQUIRED]
The type of image in the result.
source (dict) -- [REQUIRED]
The source of the image in the result.
bytes (bytes) --
The raw image bytes for the image. If you use an Amazon Web Services SDK, you don't need to encode the image bytes in base64.
responseState (string) --
Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
functionResult (dict) --
The result from the function from the action group invocation.
actionGroup (string) -- [REQUIRED]
The action group that the function belongs to.
agentId (string) --
The agent's ID.
confirmationState (string) --
Contains the user confirmation information about the function that was called.
function (string) --
The name of the function that was called.
responseBody (dict) --
The response from the function call using the parameters. The response might be returned directly or from the Lambda function. Specify TEXT or IMAGES. The key of the object is the content type. You can only specify one type. If you specify IMAGES, you can specify only one image. You can specify images only when the function in the returnControlInvocationResults is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
(string) --
(dict) --
Contains the body of the API response.
This data type is used in the following API operations:
In the returnControlInvocationResults field of the InvokeAgent request
body (string) --
The body of the API response.
images (list) --
Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
(dict) --
Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
format (string) -- [REQUIRED]
The type of image in the result.
source (dict) -- [REQUIRED]
The source of the image in the result.
bytes (bytes) --
The raw image bytes for the image. If you use an Amazon Web Services SDK, you don't need to encode the image bytes in base64.
responseState (string) --
Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
sessionAttributes (dict) --
Contains attributes that persist across a session and the values of those attributes. If sessionAttributes are passed to a supervisor agent in multi-agent collaboration, it will be forwarded to all agent collaborators.
(string) --
(string) --
string
The ARN of the resource making the request.
dict
Specifies the configurations for streaming.
applyGuardrailInterval (integer) --
The guardrail interval to apply as response is generated. By default, the guardrail interval is set to 50 characters. If a larger interval is specified, the response will be generated in larger chunks with fewer ApplyGuardrail calls. The following examples show the response generated for Hello, I am an agent input string.
Example response in chunks: Interval set to 3 characters
'Hel', 'lo, ','I am', ' an', ' Age', 'nt'
Each chunk has at least 3 characters except for the last chunk
Example response in chunks: Interval set to 20 or more characters
Hello, I am an Agent
streamFinalResponse (boolean) --
Specifies whether to enable streaming for the final response. This is set to false by default.
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{
'completion': EventStream({
'accessDeniedException': {
'message': 'string'
},
'badGatewayException': {
'message': 'string',
'resourceName': 'string'
},
'chunk': {
'attribution': {
'citations': [
{
'generatedResponsePart': {
'textResponsePart': {
'span': {
'end': 123,
'start': 123
},
'text': 'string'
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
]
},
'bytes': b'bytes'
},
'conflictException': {
'message': 'string'
},
'dependencyFailedException': {
'message': 'string',
'resourceName': 'string'
},
'files': {
'files': [
{
'bytes': b'bytes',
'name': 'string',
'type': 'string'
},
]
},
'internalServerException': {
'message': 'string',
'reason': 'string'
},
'modelNotReadyException': {
'message': 'string'
},
'resourceNotFoundException': {
'message': 'string'
},
'returnControl': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'serviceQuotaExceededException': {
'message': 'string'
},
'throttlingException': {
'message': 'string'
},
'trace': {
'agentAliasId': 'string',
'agentId': 'string',
'agentVersion': 'string',
'callerChain': [
{
'agentAliasArn': 'string'
},
],
'collaboratorName': 'string',
'eventTime': datetime(2015, 1, 1),
'sessionId': 'string',
'trace': {
'customOrchestrationTrace': {
'event': {
'text': 'string'
},
'traceId': 'string'
},
'failureTrace': {
'failureCode': 123,
'failureReason': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'traceId': 'string'
},
'guardrailTrace': {
'action': 'INTERVENED'|'NONE',
'inputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'outputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'traceId': 'string'
},
'orchestrationTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
},
'rationale': {
'text': 'string',
'traceId': 'string'
}
},
'postProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'text': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'preProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'isValid': True|False,
'rationale': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'routingClassifierTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
}
}
}
},
'validationException': {
'message': 'string'
}
}),
'contentType': 'string',
'memoryId': 'string',
'sessionId': 'string'
}
**Response Structure**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/bedrock-agent-runtime-2023-07-26/InvokeAgent>`_
{'responseStream': {'flowTraceEvent': {'trace': {'nodeDependencyTrace': {'traceElements': {'agentTraces': {'trace': {'orchestrationTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}},
'routingClassifierTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}}}}}}}}}}
Invokes an alias of a flow to run the inputs that you specify and return the output of each node as a stream. If there's an error, the error is returned. For more information, see Test a flow in Amazon Bedrock in the Amazon Bedrock User Guide.
See also: AWS API Documentation
Request Syntax
client.invoke_flow(
enableTrace=True|False,
executionId='string',
flowAliasIdentifier='string',
flowIdentifier='string',
inputs=[
{
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'nodeInputName': 'string',
'nodeName': 'string',
'nodeOutputName': 'string'
},
],
modelPerformanceConfiguration={
'performanceConfig': {
'latency': 'standard'|'optimized'
}
}
)
boolean
Specifies whether to return the trace for the flow or not. Traces track inputs and outputs for nodes in the flow. For more information, see Track each step in your prompt flow by viewing its trace in Amazon Bedrock.
string
The unique identifier for the current flow execution. If you don't provide a value, Amazon Bedrock creates the identifier for you.
string
[REQUIRED]
The unique identifier of the flow alias.
string
[REQUIRED]
The unique identifier of the flow.
list
[REQUIRED]
A list of objects, each containing information about an input into the flow.
(dict) --
Contains information about an input into the prompt flow and where to send it.
content (dict) -- [REQUIRED]
Contains information about an input into the prompt flow.
document (:ref:`document<document>`) --
The input to send to the prompt flow input node.
nodeInputName (string) --
The name of the input from the flow input node.
nodeName (string) -- [REQUIRED]
The name of the flow input node that begins the prompt flow.
nodeOutputName (string) --
The name of the output from the flow input node that begins the prompt flow.
dict
Model performance settings for the request.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{
'executionId': 'string',
'responseStream': EventStream({
'accessDeniedException': {
'message': 'string'
},
'badGatewayException': {
'message': 'string',
'resourceName': 'string'
},
'conflictException': {
'message': 'string'
},
'dependencyFailedException': {
'message': 'string',
'resourceName': 'string'
},
'flowCompletionEvent': {
'completionReason': 'SUCCESS'|'INPUT_REQUIRED'
},
'flowMultiTurnInputRequestEvent': {
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'nodeName': 'string',
'nodeType': 'FlowInputNode'|'FlowOutputNode'|'LambdaFunctionNode'|'KnowledgeBaseNode'|'PromptNode'|'ConditionNode'|'LexNode'
},
'flowOutputEvent': {
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'nodeName': 'string',
'nodeType': 'FlowInputNode'|'FlowOutputNode'|'LambdaFunctionNode'|'KnowledgeBaseNode'|'PromptNode'|'ConditionNode'|'LexNode'
},
'flowTraceEvent': {
'trace': {
'conditionNodeResultTrace': {
'nodeName': 'string',
'satisfiedConditions': [
{
'conditionName': 'string'
},
],
'timestamp': datetime(2015, 1, 1)
},
'nodeActionTrace': {
'nodeName': 'string',
'operationName': 'string',
'operationRequest': {...}|[...]|123|123.4|'string'|True|None,
'operationResponse': {...}|[...]|123|123.4|'string'|True|None,
'requestId': 'string',
'serviceName': 'string',
'timestamp': datetime(2015, 1, 1)
},
'nodeDependencyTrace': {
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1),
'traceElements': {
'agentTraces': [
{
'agentAliasId': 'string',
'agentId': 'string',
'agentVersion': 'string',
'callerChain': [
{
'agentAliasArn': 'string'
},
],
'collaboratorName': 'string',
'eventTime': datetime(2015, 1, 1),
'sessionId': 'string',
'trace': {
'customOrchestrationTrace': {
'event': {
'text': 'string'
},
'traceId': 'string'
},
'failureTrace': {
'failureCode': 123,
'failureReason': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'traceId': 'string'
},
'guardrailTrace': {
'action': 'INTERVENED'|'NONE',
'inputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'outputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'traceId': 'string'
},
'orchestrationTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
},
'rationale': {
'text': 'string',
'traceId': 'string'
}
},
'postProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'text': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'preProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'isValid': True|False,
'rationale': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'routingClassifierTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
}
}
}
},
]
}
},
'nodeInputTrace': {
'fields': [
{
'category': 'LoopCondition'|'ReturnValueToLoopStart'|'ExitLoop',
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'executionChain': [
{
'index': 123,
'nodeName': 'string',
'type': 'Iterator'|'Loop'
},
],
'nodeInputName': 'string',
'source': {
'expression': 'string',
'nodeName': 'string',
'outputFieldName': 'string'
},
'type': 'String'|'Number'|'Boolean'|'Object'|'Array'
},
],
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1)
},
'nodeOutputTrace': {
'fields': [
{
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'next': [
{
'inputFieldName': 'string',
'nodeName': 'string'
},
],
'nodeOutputName': 'string',
'type': 'String'|'Number'|'Boolean'|'Object'|'Array'
},
],
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1)
}
}
},
'internalServerException': {
'message': 'string',
'reason': 'string'
},
'resourceNotFoundException': {
'message': 'string'
},
'serviceQuotaExceededException': {
'message': 'string'
},
'throttlingException': {
'message': 'string'
},
'validationException': {
'message': 'string'
}
})
}
**Response Structure**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/bedrock-agent-runtime-2023-07-26/InvokeFlow>`_
{'completion': {'chunk': {'attribution': {'citations': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}},
'trace': {'trace': {'orchestrationTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}},
'routingClassifierTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}}}}}}
Invokes an inline Amazon Bedrock agent using the configurations you provide with the request.
Specify the following fields for security purposes.
(Optional) customerEncryptionKeyArn – The Amazon Resource Name (ARN) of a KMS key to encrypt the creation of the agent.
(Optional) idleSessionTTLinSeconds – Specify the number of seconds for which the agent should maintain session information. After this time expires, the subsequent InvokeInlineAgent request begins a new session.
To override the default prompt behavior for agent orchestration and to use advanced prompts, include a promptOverrideConfiguration object. For more information, see Advanced prompts.
The agent instructions will not be honored if your agent has only one knowledge base, uses default prompts, has no action group, and user input is disabled.
See also: AWS API Documentation
Request Syntax
client.invoke_inline_agent(
actionGroups=[
{
'actionGroupExecutor': {
'customControl': 'RETURN_CONTROL',
'lambda': 'string'
},
'actionGroupName': 'string',
'apiSchema': {
'payload': 'string',
's3': {
's3BucketName': 'string',
's3ObjectKey': 'string'
}
},
'description': 'string',
'functionSchema': {
'functions': [
{
'description': 'string',
'name': 'string',
'parameters': {
'string': {
'description': 'string',
'required': True|False,
'type': 'string'|'number'|'integer'|'boolean'|'array'
}
},
'requireConfirmation': 'ENABLED'|'DISABLED'
},
]
},
'parentActionGroupSignature': 'AMAZON.UserInput'|'AMAZON.CodeInterpreter'|'ANTHROPIC.Computer'|'ANTHROPIC.Bash'|'ANTHROPIC.TextEditor',
'parentActionGroupSignatureParams': {
'string': 'string'
}
},
],
agentCollaboration='SUPERVISOR'|'SUPERVISOR_ROUTER'|'DISABLED',
agentName='string',
bedrockModelConfigurations={
'performanceConfig': {
'latency': 'standard'|'optimized'
}
},
collaboratorConfigurations=[
{
'agentAliasArn': 'string',
'collaboratorInstruction': 'string',
'collaboratorName': 'string',
'relayConversationHistory': 'TO_COLLABORATOR'|'DISABLED'
},
],
collaborators=[
{
'actionGroups': [
{
'actionGroupExecutor': {
'customControl': 'RETURN_CONTROL',
'lambda': 'string'
},
'actionGroupName': 'string',
'apiSchema': {
'payload': 'string',
's3': {
's3BucketName': 'string',
's3ObjectKey': 'string'
}
},
'description': 'string',
'functionSchema': {
'functions': [
{
'description': 'string',
'name': 'string',
'parameters': {
'string': {
'description': 'string',
'required': True|False,
'type': 'string'|'number'|'integer'|'boolean'|'array'
}
},
'requireConfirmation': 'ENABLED'|'DISABLED'
},
]
},
'parentActionGroupSignature': 'AMAZON.UserInput'|'AMAZON.CodeInterpreter'|'ANTHROPIC.Computer'|'ANTHROPIC.Bash'|'ANTHROPIC.TextEditor',
'parentActionGroupSignatureParams': {
'string': 'string'
}
},
],
'agentCollaboration': 'SUPERVISOR'|'SUPERVISOR_ROUTER'|'DISABLED',
'agentName': 'string',
'collaboratorConfigurations': [
{
'agentAliasArn': 'string',
'collaboratorInstruction': 'string',
'collaboratorName': 'string',
'relayConversationHistory': 'TO_COLLABORATOR'|'DISABLED'
},
],
'customerEncryptionKeyArn': 'string',
'foundationModel': 'string',
'guardrailConfiguration': {
'guardrailIdentifier': 'string',
'guardrailVersion': 'string'
},
'idleSessionTTLInSeconds': 123,
'instruction': 'string',
'knowledgeBases': [
{
'description': 'string',
'knowledgeBaseId': 'string',
'retrievalConfiguration': {
'vectorSearchConfiguration': {
'filter': {
'andAll': [
{'... recursive ...'},
],
'equals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'in': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'listContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notIn': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'orAll': [
{'... recursive ...'},
],
'startsWith': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'stringContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
}
},
'implicitFilterConfiguration': {
'metadataAttributes': [
{
'description': 'string',
'key': 'string',
'type': 'STRING'|'NUMBER'|'BOOLEAN'|'STRING_LIST'
},
],
'modelArn': 'string'
},
'numberOfResults': 123,
'overrideSearchType': 'HYBRID'|'SEMANTIC',
'rerankingConfiguration': {
'bedrockRerankingConfiguration': {
'metadataConfiguration': {
'selectionMode': 'SELECTIVE'|'ALL',
'selectiveModeConfiguration': {
'fieldsToExclude': [
{
'fieldName': 'string'
},
],
'fieldsToInclude': [
{
'fieldName': 'string'
},
]
}
},
'modelConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'modelArn': 'string'
},
'numberOfRerankedResults': 123
},
'type': 'BEDROCK_RERANKING_MODEL'
}
}
}
},
],
'promptOverrideConfiguration': {
'overrideLambda': 'string',
'promptConfigurations': [
{
'additionalModelRequestFields': {...}|[...]|123|123.4|'string'|True|None,
'basePromptTemplate': 'string',
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'promptState': 'ENABLED'|'DISABLED',
'promptType': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
]
}
},
],
customOrchestration={
'executor': {
'lambda': 'string'
}
},
customerEncryptionKeyArn='string',
enableTrace=True|False,
endSession=True|False,
foundationModel='string',
guardrailConfiguration={
'guardrailIdentifier': 'string',
'guardrailVersion': 'string'
},
idleSessionTTLInSeconds=123,
inlineSessionState={
'conversationHistory': {
'messages': [
{
'content': [
{
'text': 'string'
},
],
'role': 'user'|'assistant'
},
]
},
'files': [
{
'name': 'string',
'source': {
'byteContent': {
'data': b'bytes',
'mediaType': 'string'
},
's3Location': {
'uri': 'string'
},
'sourceType': 'S3'|'BYTE_CONTENT'
},
'useCase': 'CODE_INTERPRETER'|'CHAT'
},
],
'invocationId': 'string',
'promptSessionAttributes': {
'string': 'string'
},
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
],
'sessionAttributes': {
'string': 'string'
}
},
inputText='string',
instruction='string',
knowledgeBases=[
{
'description': 'string',
'knowledgeBaseId': 'string',
'retrievalConfiguration': {
'vectorSearchConfiguration': {
'filter': {
'andAll': [
{'... recursive ...'},
],
'equals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'in': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'listContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notIn': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'orAll': [
{'... recursive ...'},
],
'startsWith': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'stringContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
}
},
'implicitFilterConfiguration': {
'metadataAttributes': [
{
'description': 'string',
'key': 'string',
'type': 'STRING'|'NUMBER'|'BOOLEAN'|'STRING_LIST'
},
],
'modelArn': 'string'
},
'numberOfResults': 123,
'overrideSearchType': 'HYBRID'|'SEMANTIC',
'rerankingConfiguration': {
'bedrockRerankingConfiguration': {
'metadataConfiguration': {
'selectionMode': 'SELECTIVE'|'ALL',
'selectiveModeConfiguration': {
'fieldsToExclude': [
{
'fieldName': 'string'
},
],
'fieldsToInclude': [
{
'fieldName': 'string'
},
]
}
},
'modelConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'modelArn': 'string'
},
'numberOfRerankedResults': 123
},
'type': 'BEDROCK_RERANKING_MODEL'
}
}
}
},
],
orchestrationType='DEFAULT'|'CUSTOM_ORCHESTRATION',
promptCreationConfigurations={
'excludePreviousThinkingSteps': True|False,
'previousConversationTurnsToInclude': 123
},
promptOverrideConfiguration={
'overrideLambda': 'string',
'promptConfigurations': [
{
'additionalModelRequestFields': {...}|[...]|123|123.4|'string'|True|None,
'basePromptTemplate': 'string',
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'promptState': 'ENABLED'|'DISABLED',
'promptType': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
]
},
sessionId='string',
streamingConfigurations={
'applyGuardrailInterval': 123,
'streamFinalResponse': True|False
}
)
list
A list of action groups with each action group defining the action the inline agent needs to carry out.
(dict) --
Contains details of the inline agent's action group.
actionGroupExecutor (dict) --
The Amazon Resource Name (ARN) of 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.
customControl (string) --
To return the action group invocation results directly in the InvokeInlineAgent response, specify RETURN_CONTROL.
lambda (string) --
The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action.
actionGroupName (string) -- [REQUIRED]
The name of the action group.
apiSchema (dict) --
Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas.
payload (string) --
The JSON or YAML-formatted payload defining the OpenAPI schema for the action group.
s3 (dict) --
Contains details about the S3 object containing the OpenAPI schema for the action group.
s3BucketName (string) --
The name of the S3 bucket.
s3ObjectKey (string) --
The S3 object key for the S3 resource.
description (string) --
A description of the action group.
functionSchema (dict) --
Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
functions (list) --
A list of functions that each define an action in the action group.
(dict) --
Defines parameters that the agent needs to invoke from the user to complete the function. Corresponds to an action in an action group.
description (string) --
A description of the function and its purpose.
name (string) -- [REQUIRED]
A name for the function.
parameters (dict) --
The parameters that the agent elicits from the user to fulfill the function.
(string) --
(dict) --
Contains details about a parameter in a function for an action group.
description (string) --
A description of the parameter. Helps the foundation model determine how to elicit the parameters from the user.
required (boolean) --
Whether the parameter is required for the agent to complete the function for action group invocation.
type (string) -- [REQUIRED]
The data type of the parameter.
requireConfirmation (string) --
Contains information if user confirmation is required to invoke the function.
parentActionGroupSignature (string) --
Specify a built-in or computer use action for this action group. If you specify a value, you must leave the description, apiSchema, and actionGroupExecutor fields empty for this action group.
To allow your agent to request the user for additional information when trying to complete a task, set this field to AMAZON.UserInput.
To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to AMAZON.CodeInterpreter.
To allow your agent to use an Anthropic computer use tool, specify one of the following values.
parentActionGroupSignatureParams (dict) --
The configuration settings for a computer use action.
(string) --
(string) --
string
Defines how the inline collaborator agent handles information across multiple collaborator agents to coordinate a final response. The inline collaborator agent can also be the supervisor.
string
The name for the agent.
dict
Model settings for the request.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
list
Settings for an inline agent collaborator called with InvokeInlineAgent.
(dict) --
Settings of an inline collaborator agent.
agentAliasArn (string) --
The Amazon Resource Name (ARN) of the inline collaborator agent.
collaboratorInstruction (string) -- [REQUIRED]
Instructions that tell the inline collaborator agent what it should do and how it should interact with users.
collaboratorName (string) -- [REQUIRED]
Name of the inline collaborator agent which must be the same name as specified for agentName.
relayConversationHistory (string) --
A relay conversation history for the inline collaborator agent.
list
List of collaborator inline agents.
(dict) --
List of inline collaborators.
actionGroups (list) --
List of action groups with each action group defining tasks the inline collaborator agent needs to carry out.
(dict) --
Contains details of the inline agent's action group.
actionGroupExecutor (dict) --
The Amazon Resource Name (ARN) of 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.
customControl (string) --
To return the action group invocation results directly in the InvokeInlineAgent response, specify RETURN_CONTROL.
lambda (string) --
The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action.
actionGroupName (string) -- [REQUIRED]
The name of the action group.
apiSchema (dict) --
Contains either details about the S3 object containing the OpenAPI schema for the action group or the JSON or YAML-formatted payload defining the schema. For more information, see Action group OpenAPI schemas.
payload (string) --
The JSON or YAML-formatted payload defining the OpenAPI schema for the action group.
s3 (dict) --
Contains details about the S3 object containing the OpenAPI schema for the action group.
s3BucketName (string) --
The name of the S3 bucket.
s3ObjectKey (string) --
The S3 object key for the S3 resource.
description (string) --
A description of the action group.
functionSchema (dict) --
Contains details about the function schema for the action group or the JSON or YAML-formatted payload defining the schema.
functions (list) --
A list of functions that each define an action in the action group.
(dict) --
Defines parameters that the agent needs to invoke from the user to complete the function. Corresponds to an action in an action group.
description (string) --
A description of the function and its purpose.
name (string) -- [REQUIRED]
A name for the function.
parameters (dict) --
The parameters that the agent elicits from the user to fulfill the function.
(string) --
(dict) --
Contains details about a parameter in a function for an action group.
description (string) --
A description of the parameter. Helps the foundation model determine how to elicit the parameters from the user.
required (boolean) --
Whether the parameter is required for the agent to complete the function for action group invocation.
type (string) -- [REQUIRED]
The data type of the parameter.
requireConfirmation (string) --
Contains information if user confirmation is required to invoke the function.
parentActionGroupSignature (string) --
Specify a built-in or computer use action for this action group. If you specify a value, you must leave the description, apiSchema, and actionGroupExecutor fields empty for this action group.
To allow your agent to request the user for additional information when trying to complete a task, set this field to AMAZON.UserInput.
To allow your agent to generate, run, and troubleshoot code when trying to complete a task, set this field to AMAZON.CodeInterpreter.
To allow your agent to use an Anthropic computer use tool, specify one of the following values.
parentActionGroupSignatureParams (dict) --
The configuration settings for a computer use action.
(string) --
(string) --
agentCollaboration (string) --
Defines how the inline supervisor agent handles information across multiple collaborator agents to coordinate a final response.
agentName (string) --
Name of the inline collaborator agent which must be the same name as specified for collaboratorName.
collaboratorConfigurations (list) --
Settings of the collaborator agent.
(dict) --
Settings of an inline collaborator agent.
agentAliasArn (string) --
The Amazon Resource Name (ARN) of the inline collaborator agent.
collaboratorInstruction (string) -- [REQUIRED]
Instructions that tell the inline collaborator agent what it should do and how it should interact with users.
collaboratorName (string) -- [REQUIRED]
Name of the inline collaborator agent which must be the same name as specified for agentName.
relayConversationHistory (string) --
A relay conversation history for the inline collaborator agent.
customerEncryptionKeyArn (string) --
The Amazon Resource Name (ARN) of the AWS KMS key that encrypts the inline collaborator.
foundationModel (string) -- [REQUIRED]
The foundation model used by the inline collaborator agent.
guardrailConfiguration (dict) --
Details of the guardwrail associated with the inline collaborator.
guardrailIdentifier (string) -- [REQUIRED]
The unique identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
idleSessionTTLInSeconds (integer) --
The number of seconds for which the Amazon Bedrock keeps information about the user's conversation with the inline collaborator agent.
A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and Amazon Bedrock deletes any data provided before the timeout.
instruction (string) -- [REQUIRED]
Instruction that tell the inline collaborator agent what it should do and how it should interact with users.
knowledgeBases (list) --
Knowledge base associated with the inline collaborator agent.
(dict) --
Details of the knowledge base associated withe inline agent.
description (string) -- [REQUIRED]
The description of the knowledge base associated with the inline agent.
knowledgeBaseId (string) -- [REQUIRED]
The unique identifier for a knowledge base associated with the inline agent.
retrievalConfiguration (dict) --
The configurations to apply to the knowledge base during query. For more information, see Query configurations.
vectorSearchConfiguration (dict) -- [REQUIRED]
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
filter (dict) --
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
andAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
equals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is cat:
"equals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than 1989:
"greaterThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989:
"greaterThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
in (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either cat or dog:
"in": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to 1989.
"lessThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to 1989.
"lessThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
listContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"]).
"listContains": { "key": "animals", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notEquals (dict) --
Knowledge base data sources are returned when:
It contains a metadata attribute whose name matches the key and whose value doesn't match the value in this object.
The key is not present in the document.
The following example would return data sources that don't contain an animal attribute whose value is cat.
"notEquals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notIn (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither cat nor dog.
"notIn": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
orAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
startsWith (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).
"startsWith": { "key": "animal", "value": "ca" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
stringContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat). "stringContains": { "key": "animal", "value": "at" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"]). "stringContains": { "key": "animals", "value": "at" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
implicitFilterConfiguration (dict) --
Settings for implicit filtering.
metadataAttributes (list) -- [REQUIRED]
Metadata that can be used in a filter.
(dict) --
Details about a metadata attribute.
description (string) -- [REQUIRED]
The attribute's description.
key (string) -- [REQUIRED]
The attribute's key.
type (string) -- [REQUIRED]
The attribute's type.
modelArn (string) -- [REQUIRED]
The model that generates the filter.
numberOfResults (integer) --
The number of source chunks to retrieve.
overrideSearchType (string) --
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
rerankingConfiguration (dict) --
Contains configurations for reranking the retrieved results. For more information, see Improve the relevance of query responses with a reranker model.
bedrockRerankingConfiguration (dict) --
Contains configurations for an Amazon Bedrock reranker model.
metadataConfiguration (dict) --
Contains configurations for the metadata to use in reranking.
selectionMode (string) -- [REQUIRED]
Specifies whether to consider all metadata when reranking, or only the metadata that you select. If you specify SELECTIVE, include the selectiveModeConfiguration field.
selectiveModeConfiguration (dict) --
Contains configurations for the metadata fields to include or exclude when considering reranking.
fieldsToExclude (list) --
An array of objects, each of which specifies a metadata field to exclude from consideration when reranking.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
fieldsToInclude (list) --
An array of objects, each of which specifies a metadata field to include in consideration when reranking. The remaining metadata fields are ignored.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
modelConfiguration (dict) -- [REQUIRED]
Contains configurations for the reranker model.
additionalModelRequestFields (dict) --
A JSON object whose keys are request fields for the model and whose values are values for those fields.
(string) --
(:ref:`document<document>`) --
modelArn (string) -- [REQUIRED]
The ARN of the reranker model to use.
numberOfRerankedResults (integer) --
The number of results to return after reranking.
type (string) -- [REQUIRED]
The type of reranker model.
promptOverrideConfiguration (dict) --
Contains configurations to override prompt templates in different parts of an inline collaborator sequence. For more information, see Advanced prompts.
overrideLambda (string) --
The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the promptConfigurations must contain a parserMode value that is set to OVERRIDDEN. For more information, see Parser Lambda function in Amazon Bedrock Agents.
promptConfigurations (list) -- [REQUIRED]
Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.
(dict) --
Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.
additionalModelRequestFields (:ref:`document<document>`) --
If the Converse or ConverseStream operations support the model, additionalModelRequestFields contains additional inference parameters, beyond the base set of inference parameters in the inferenceConfiguration field.
For more information, see Inference request parameters and response fields for foundation models in the Amazon Bedrock user guide.
basePromptTemplate (string) --
Defines the prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables. For more information, see Configure the prompt templates.
foundationModel (string) --
The foundation model to use.
inferenceConfiguration (dict) --
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.
maximumLength (integer) --
The maximum number of tokens allowed in the generated response.
stopSequences (list) --
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
(string) --
temperature (float) --
The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
topK (integer) --
While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.
topP (float) --
While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.
parserMode (string) --
Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType. If you set the field as OVERRIDDEN, the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
promptCreationMode (string) --
Specifies whether to override the default prompt template for this promptType. Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate. If you leave it as DEFAULT, the agent uses a default prompt template.
promptState (string) --
Specifies whether to allow the inline agent to carry out the step specified in the promptType. If you set this value to DISABLED, the agent skips that step. The default state for each promptType is as follows.
PRE_PROCESSING – ENABLED
ORCHESTRATION – ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION – ENABLED
POST_PROCESSING – DISABLED
promptType (string) --
The step in the agent sequence that this prompt configuration applies to.
dict
Contains details of the custom orchestration configured for the agent.
executor (dict) --
The structure of the executor invoking the actions in custom orchestration.
lambda (string) --
The Amazon Resource Name (ARN) of the Lambda function containing the business logic that is carried out upon invoking the action.
string
The Amazon Resource Name (ARN) of the Amazon Web Services KMS key to use to encrypt your inline agent.
boolean
Specifies whether to turn on the trace or not to track the agent's reasoning process. For more information, see Using trace.
boolean
Specifies whether to end the session with the inline agent or not.
string
[REQUIRED]
The model identifier (ID) of the model to use for orchestration by the inline agent. For example, meta.llama3-1-70b-instruct-v1:0.
dict
The guardrails to assign to the inline agent.
guardrailIdentifier (string) -- [REQUIRED]
The unique identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
integer
The number of seconds for which the inline agent should maintain session information. After this time expires, the subsequent InvokeInlineAgent request begins a new session.
A user interaction remains active for the amount of time specified. If no conversation occurs during this time, the session expires and the data provided before the timeout is deleted.
dict
Parameters that specify the various attributes of a sessions. You can include attributes for the session or prompt or, if you configured an action group to return control, results from invocation of the action group. For more information, see Control session context.
conversationHistory (dict) --
Contains the conversation history that persist across sessions.
messages (list) --
The conversation's messages.
(dict) --
Details about a message.
content (list) -- [REQUIRED]
The message's content.
(dict) --
A content block.
text (string) --
The block's text.
role (string) -- [REQUIRED]
The message's role.
files (list) --
Contains information about the files used by code interpreter.
(dict) --
Contains details of the source files.
name (string) -- [REQUIRED]
The name of the source file.
source (dict) -- [REQUIRED]
Specifies where the files are located.
byteContent (dict) --
The data and the text of the attached files.
data (bytes) -- [REQUIRED]
The raw bytes of the file to attach. The maximum size of all files that is attached is 10MB. You can attach a maximum of 5 files.
mediaType (string) -- [REQUIRED]
The MIME type of data contained in the file used for chat.
s3Location (dict) --
The s3 location of the files to attach.
uri (string) -- [REQUIRED]
The uri of the s3 object.
sourceType (string) -- [REQUIRED]
The source type of the files to attach.
useCase (string) -- [REQUIRED]
Specifies how the source files will be used by the code interpreter.
invocationId (string) --
The identifier of the invocation of an action. This value must match the invocationId returned in the InvokeInlineAgent response for the action whose results are provided in the returnControlInvocationResults field. For more information, see Return control to the agent developer.
promptSessionAttributes (dict) --
Contains attributes that persist across a session and the values of those attributes.
(string) --
(string) --
returnControlInvocationResults (list) --
Contains information about the results from the action group invocation. For more information, see Return control to the agent developer.
(dict) --
A result from the invocation of an action. For more information, see Return control to the agent developer and Control session context.
This data type is used in the following API operations:
apiResult (dict) --
The result from the API response from the action group invocation.
actionGroup (string) -- [REQUIRED]
The action group that the API operation belongs to.
agentId (string) --
The agent's ID.
apiPath (string) --
The path to the API operation.
confirmationState (string) --
Controls the API operations or functions to invoke based on the user confirmation.
httpMethod (string) --
The HTTP method for the API operation.
httpStatusCode (integer) --
http status code from API execution response (for example: 200, 400, 500).
responseBody (dict) --
The response body from the API operation. The key of the object is the content type (currently, only TEXT is supported). The response may be returned directly or from the Lambda function.
(string) --
(dict) --
Contains the body of the API response.
This data type is used in the following API operations:
In the returnControlInvocationResults field of the InvokeAgent request
body (string) --
The body of the API response.
images (list) --
Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
(dict) --
Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
format (string) -- [REQUIRED]
The type of image in the result.
source (dict) -- [REQUIRED]
The source of the image in the result.
bytes (bytes) --
The raw image bytes for the image. If you use an Amazon Web Services SDK, you don't need to encode the image bytes in base64.
responseState (string) --
Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
functionResult (dict) --
The result from the function from the action group invocation.
actionGroup (string) -- [REQUIRED]
The action group that the function belongs to.
agentId (string) --
The agent's ID.
confirmationState (string) --
Contains the user confirmation information about the function that was called.
function (string) --
The name of the function that was called.
responseBody (dict) --
The response from the function call using the parameters. The response might be returned directly or from the Lambda function. Specify TEXT or IMAGES. The key of the object is the content type. You can only specify one type. If you specify IMAGES, you can specify only one image. You can specify images only when the function in the returnControlInvocationResults is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
(string) --
(dict) --
Contains the body of the API response.
This data type is used in the following API operations:
In the returnControlInvocationResults field of the InvokeAgent request
body (string) --
The body of the API response.
images (list) --
Lists details, including format and source, for the image in the response from the function call. You can specify only one image and the function in the returnControlInvocationResults must be a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
(dict) --
Details about an image in the result from a function in the action group invocation. You can specify images only when the function is a computer use action. For more information, see Configure an Amazon Bedrock Agent to complete tasks with computer use tools.
format (string) -- [REQUIRED]
The type of image in the result.
source (dict) -- [REQUIRED]
The source of the image in the result.
bytes (bytes) --
The raw image bytes for the image. If you use an Amazon Web Services SDK, you don't need to encode the image bytes in base64.
responseState (string) --
Controls the final response state returned to end user when API/Function execution failed. When this state is FAILURE, the request would fail with dependency failure exception. When this state is REPROMPT, the API/function response will be sent to model for re-prompt
sessionAttributes (dict) --
Contains attributes that persist across a session and the values of those attributes.
(string) --
(string) --
string
The prompt text to send to the agent.
string
[REQUIRED]
The instructions that tell the inline agent what it should do and how it should interact with users.
list
Contains information of the knowledge bases to associate with.
(dict) --
Details of the knowledge base associated withe inline agent.
description (string) -- [REQUIRED]
The description of the knowledge base associated with the inline agent.
knowledgeBaseId (string) -- [REQUIRED]
The unique identifier for a knowledge base associated with the inline agent.
retrievalConfiguration (dict) --
The configurations to apply to the knowledge base during query. For more information, see Query configurations.
vectorSearchConfiguration (dict) -- [REQUIRED]
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
filter (dict) --
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
andAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
equals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is cat:
"equals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than 1989:
"greaterThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989:
"greaterThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
in (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either cat or dog:
"in": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to 1989.
"lessThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to 1989.
"lessThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
listContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"]).
"listContains": { "key": "animals", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notEquals (dict) --
Knowledge base data sources are returned when:
It contains a metadata attribute whose name matches the key and whose value doesn't match the value in this object.
The key is not present in the document.
The following example would return data sources that don't contain an animal attribute whose value is cat.
"notEquals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notIn (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither cat nor dog.
"notIn": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
orAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
startsWith (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).
"startsWith": { "key": "animal", "value": "ca" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
stringContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat). "stringContains": { "key": "animal", "value": "at" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"]). "stringContains": { "key": "animals", "value": "at" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
implicitFilterConfiguration (dict) --
Settings for implicit filtering.
metadataAttributes (list) -- [REQUIRED]
Metadata that can be used in a filter.
(dict) --
Details about a metadata attribute.
description (string) -- [REQUIRED]
The attribute's description.
key (string) -- [REQUIRED]
The attribute's key.
type (string) -- [REQUIRED]
The attribute's type.
modelArn (string) -- [REQUIRED]
The model that generates the filter.
numberOfResults (integer) --
The number of source chunks to retrieve.
overrideSearchType (string) --
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
rerankingConfiguration (dict) --
Contains configurations for reranking the retrieved results. For more information, see Improve the relevance of query responses with a reranker model.
bedrockRerankingConfiguration (dict) --
Contains configurations for an Amazon Bedrock reranker model.
metadataConfiguration (dict) --
Contains configurations for the metadata to use in reranking.
selectionMode (string) -- [REQUIRED]
Specifies whether to consider all metadata when reranking, or only the metadata that you select. If you specify SELECTIVE, include the selectiveModeConfiguration field.
selectiveModeConfiguration (dict) --
Contains configurations for the metadata fields to include or exclude when considering reranking.
fieldsToExclude (list) --
An array of objects, each of which specifies a metadata field to exclude from consideration when reranking.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
fieldsToInclude (list) --
An array of objects, each of which specifies a metadata field to include in consideration when reranking. The remaining metadata fields are ignored.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
modelConfiguration (dict) -- [REQUIRED]
Contains configurations for the reranker model.
additionalModelRequestFields (dict) --
A JSON object whose keys are request fields for the model and whose values are values for those fields.
(string) --
(:ref:`document<document>`) --
modelArn (string) -- [REQUIRED]
The ARN of the reranker model to use.
numberOfRerankedResults (integer) --
The number of results to return after reranking.
type (string) -- [REQUIRED]
The type of reranker model.
string
Specifies the type of orchestration strategy for the agent. This is set to DEFAULT orchestration type, by default.
dict
Specifies parameters that control how the service populates the agent prompt for an InvokeInlineAgent request. You can control which aspects of previous invocations in the same agent session the service uses to populate the agent prompt. This gives you more granular control over the contextual history that is used to process the current request.
excludePreviousThinkingSteps (boolean) --
If true, the service removes any content between <thinking> tags from previous conversations in an agent session. The service will only remove content from already processed turns. This helps you remove content which might not be useful for current and subsequent invocations. This can reduce the input token count and potentially save costs. The default value is false.
previousConversationTurnsToInclude (integer) --
The number of previous conversations from the ongoing agent session to include in the conversation history of the agent prompt, during the current invocation. This gives you more granular control over the context that the model is made aware of, and helps the model remove older context which is no longer useful during the ongoing agent session.
dict
Configurations for advanced prompts used to override the default prompts to enhance the accuracy of the inline agent.
overrideLambda (string) --
The ARN of the Lambda function to use when parsing the raw foundation model output in parts of the agent sequence. If you specify this field, at least one of the promptConfigurations must contain a parserMode value that is set to OVERRIDDEN. For more information, see Parser Lambda function in Amazon Bedrock Agents.
promptConfigurations (list) -- [REQUIRED]
Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.
(dict) --
Contains configurations to override a prompt template in one part of an agent sequence. For more information, see Advanced prompts.
additionalModelRequestFields (:ref:`document<document>`) --
If the Converse or ConverseStream operations support the model, additionalModelRequestFields contains additional inference parameters, beyond the base set of inference parameters in the inferenceConfiguration field.
For more information, see Inference request parameters and response fields for foundation models in the Amazon Bedrock user guide.
basePromptTemplate (string) --
Defines the prompt template with which to replace the default prompt template. You can use placeholder variables in the base prompt template to customize the prompt. For more information, see Prompt template placeholder variables. For more information, see Configure the prompt templates.
foundationModel (string) --
The foundation model to use.
inferenceConfiguration (dict) --
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.
maximumLength (integer) --
The maximum number of tokens allowed in the generated response.
stopSequences (list) --
A list of stop sequences. A stop sequence is a sequence of characters that causes the model to stop generating the response.
(string) --
temperature (float) --
The likelihood of the model selecting higher-probability options while generating a response. A lower value makes the model more likely to choose higher-probability options, while a higher value makes the model more likely to choose lower-probability options.
topK (integer) --
While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for topK is the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topK to 50, the model selects the next token from among the top 50 most likely choices.
topP (float) --
While generating a response, the model determines the probability of the following token at each point of generation. The value that you set for Top P determines the number of most-likely candidates from which the model chooses the next token in the sequence. For example, if you set topP to 0.8, the model only selects the next token from the top 80% of the probability distribution of next tokens.
parserMode (string) --
Specifies whether to override the default parser Lambda function when parsing the raw foundation model output in the part of the agent sequence defined by the promptType. If you set the field as OVERRIDDEN, the overrideLambda field in the PromptOverrideConfiguration must be specified with the ARN of a Lambda function.
promptCreationMode (string) --
Specifies whether to override the default prompt template for this promptType. Set this value to OVERRIDDEN to use the prompt that you provide in the basePromptTemplate. If you leave it as DEFAULT, the agent uses a default prompt template.
promptState (string) --
Specifies whether to allow the inline agent to carry out the step specified in the promptType. If you set this value to DISABLED, the agent skips that step. The default state for each promptType is as follows.
PRE_PROCESSING – ENABLED
ORCHESTRATION – ENABLED
KNOWLEDGE_BASE_RESPONSE_GENERATION – ENABLED
POST_PROCESSING – DISABLED
promptType (string) --
The step in the agent sequence that this prompt configuration applies to.
string
[REQUIRED]
The unique identifier of the session. Use the same value across requests to continue the same conversation.
dict
Specifies the configurations for streaming.
applyGuardrailInterval (integer) --
The guardrail interval to apply as response is generated. By default, the guardrail interval is set to 50 characters. If a larger interval is specified, the response will be generated in larger chunks with fewer ApplyGuardrail calls. The following examples show the response generated for Hello, I am an agent input string.
Example response in chunks: Interval set to 3 characters
'Hel', 'lo, ','I am', ' an', ' Age', 'nt'
Each chunk has at least 3 characters except for the last chunk
Example response in chunks: Interval set to 20 or more characters
Hello, I am an Agent
streamFinalResponse (boolean) --
Specifies whether to enable streaming for the final response. This is set to false by default.
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{
'completion': EventStream({
'accessDeniedException': {
'message': 'string'
},
'badGatewayException': {
'message': 'string',
'resourceName': 'string'
},
'chunk': {
'attribution': {
'citations': [
{
'generatedResponsePart': {
'textResponsePart': {
'span': {
'end': 123,
'start': 123
},
'text': 'string'
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
]
},
'bytes': b'bytes'
},
'conflictException': {
'message': 'string'
},
'dependencyFailedException': {
'message': 'string',
'resourceName': 'string'
},
'files': {
'files': [
{
'bytes': b'bytes',
'name': 'string',
'type': 'string'
},
]
},
'internalServerException': {
'message': 'string',
'reason': 'string'
},
'resourceNotFoundException': {
'message': 'string'
},
'returnControl': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'serviceQuotaExceededException': {
'message': 'string'
},
'throttlingException': {
'message': 'string'
},
'trace': {
'callerChain': [
{
'agentAliasArn': 'string'
},
],
'collaboratorName': 'string',
'eventTime': datetime(2015, 1, 1),
'sessionId': 'string',
'trace': {
'customOrchestrationTrace': {
'event': {
'text': 'string'
},
'traceId': 'string'
},
'failureTrace': {
'failureCode': 123,
'failureReason': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'traceId': 'string'
},
'guardrailTrace': {
'action': 'INTERVENED'|'NONE',
'inputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'outputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'traceId': 'string'
},
'orchestrationTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
},
'rationale': {
'text': 'string',
'traceId': 'string'
}
},
'postProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'text': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'preProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'isValid': True|False,
'rationale': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'routingClassifierTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
}
}
}
},
'validationException': {
'message': 'string'
}
}),
'contentType': 'string',
'sessionId': 'string'
}
**Response Structure**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/bedrock-agent-runtime-2023-07-26/InvokeInlineAgent>`_
{'flowExecutionEvents': {'nodeDependencyEvent': {'traceElements': {'agentTraces': {'trace': {'orchestrationTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}},
'routingClassifierTrace': {'observation': {'knowledgeBaseLookupOutput': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}}}}}}}}
Lists events that occurred during a flow execution. Events provide detailed information about the execution progress, including node inputs and outputs, flow inputs and outputs, condition results, and failure events.
See also: AWS API Documentation
Request Syntax
client.list_flow_execution_events(
eventType='Node'|'Flow',
executionIdentifier='string',
flowAliasIdentifier='string',
flowIdentifier='string',
maxResults=123,
nextToken='string'
)
string
[REQUIRED]
The type of events to retrieve. Specify Node for node-level events or Flow for flow-level events.
string
[REQUIRED]
The unique identifier of the flow execution.
string
[REQUIRED]
The unique identifier of the flow alias used for the execution.
string
[REQUIRED]
The unique identifier of the flow.
integer
The maximum number of events to return in a single response. If more events exist than the specified maxResults value, a token is included in the response so that the remaining results can be retrieved.
string
A token to retrieve the next set of results. This value is returned in the response if more results are available.
dict
Response Syntax
{
'flowExecutionEvents': [
{
'conditionResultEvent': {
'nodeName': 'string',
'satisfiedConditions': [
{
'conditionName': 'string'
},
],
'timestamp': datetime(2015, 1, 1)
},
'flowFailureEvent': {
'errorCode': 'VALIDATION'|'INTERNAL_SERVER'|'NODE_EXECUTION_FAILED',
'errorMessage': 'string',
'timestamp': datetime(2015, 1, 1)
},
'flowInputEvent': {
'fields': [
{
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'name': 'string'
},
],
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1)
},
'flowOutputEvent': {
'fields': [
{
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'name': 'string'
},
],
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1)
},
'nodeActionEvent': {
'nodeName': 'string',
'operationName': 'string',
'operationRequest': {...}|[...]|123|123.4|'string'|True|None,
'operationResponse': {...}|[...]|123|123.4|'string'|True|None,
'requestId': 'string',
'serviceName': 'string',
'timestamp': datetime(2015, 1, 1)
},
'nodeDependencyEvent': {
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1),
'traceElements': {
'agentTraces': [
{
'agentAliasId': 'string',
'agentId': 'string',
'agentVersion': 'string',
'callerChain': [
{
'agentAliasArn': 'string'
},
],
'collaboratorName': 'string',
'eventTime': datetime(2015, 1, 1),
'sessionId': 'string',
'trace': {
'customOrchestrationTrace': {
'event': {
'text': 'string'
},
'traceId': 'string'
},
'failureTrace': {
'failureCode': 123,
'failureReason': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'traceId': 'string'
},
'guardrailTrace': {
'action': 'INTERVENED'|'NONE',
'inputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'outputAssessments': [
{
'contentPolicy': {
'filters': [
{
'action': 'BLOCKED',
'confidence': 'NONE'|'LOW'|'MEDIUM'|'HIGH',
'type': 'INSULTS'|'HATE'|'SEXUAL'|'VIOLENCE'|'MISCONDUCT'|'PROMPT_ATTACK'
},
]
},
'sensitiveInformationPolicy': {
'piiEntities': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'type': 'ADDRESS'|'AGE'|'AWS_ACCESS_KEY'|'AWS_SECRET_KEY'|'CA_HEALTH_NUMBER'|'CA_SOCIAL_INSURANCE_NUMBER'|'CREDIT_DEBIT_CARD_CVV'|'CREDIT_DEBIT_CARD_EXPIRY'|'CREDIT_DEBIT_CARD_NUMBER'|'DRIVER_ID'|'EMAIL'|'INTERNATIONAL_BANK_ACCOUNT_NUMBER'|'IP_ADDRESS'|'LICENSE_PLATE'|'MAC_ADDRESS'|'NAME'|'PASSWORD'|'PHONE'|'PIN'|'SWIFT_CODE'|'UK_NATIONAL_HEALTH_SERVICE_NUMBER'|'UK_NATIONAL_INSURANCE_NUMBER'|'UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER'|'URL'|'USERNAME'|'US_BANK_ACCOUNT_NUMBER'|'US_BANK_ROUTING_NUMBER'|'US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER'|'US_PASSPORT_NUMBER'|'US_SOCIAL_SECURITY_NUMBER'|'VEHICLE_IDENTIFICATION_NUMBER'
},
],
'regexes': [
{
'action': 'BLOCKED'|'ANONYMIZED',
'match': 'string',
'name': 'string',
'regex': 'string'
},
]
},
'topicPolicy': {
'topics': [
{
'action': 'BLOCKED',
'name': 'string',
'type': 'DENY'
},
]
},
'wordPolicy': {
'customWords': [
{
'action': 'BLOCKED',
'match': 'string'
},
],
'managedWordLists': [
{
'action': 'BLOCKED',
'match': 'string',
'type': 'PROFANITY'
},
]
}
},
],
'traceId': 'string'
},
'orchestrationTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
},
'rationale': {
'text': 'string',
'traceId': 'string'
}
},
'postProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'text': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'preProcessingTrace': {
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'parsedResponse': {
'isValid': True|False,
'rationale': 'string'
},
'rawResponse': {
'content': 'string'
},
'reasoningContent': {
'reasoningText': {
'signature': 'string',
'text': 'string'
},
'redactedContent': b'bytes'
},
'traceId': 'string'
}
},
'routingClassifierTrace': {
'invocationInput': {
'actionGroupInvocationInput': {
'actionGroupName': 'string',
'apiPath': 'string',
'executionType': 'LAMBDA'|'RETURN_CONTROL',
'function': 'string',
'invocationId': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
'verb': 'string'
},
'agentCollaboratorInvocationInput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'input': {
'returnControlResults': {
'invocationId': 'string',
'returnControlInvocationResults': [
{
'apiResult': {
'actionGroup': 'string',
'agentId': 'string',
'apiPath': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'httpMethod': 'string',
'httpStatusCode': 123,
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
},
'functionResult': {
'actionGroup': 'string',
'agentId': 'string',
'confirmationState': 'CONFIRM'|'DENY',
'function': 'string',
'responseBody': {
'string': {
'body': 'string',
'images': [
{
'format': 'png'|'jpeg'|'gif'|'webp',
'source': {
'bytes': b'bytes'
}
},
]
}
},
'responseState': 'FAILURE'|'REPROMPT'
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationInput': {
'code': 'string',
'files': [
'string',
]
},
'invocationType': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'FINISH'|'ACTION_GROUP_CODE_INTERPRETER'|'AGENT_COLLABORATOR',
'knowledgeBaseLookupInput': {
'knowledgeBaseId': 'string',
'text': 'string'
},
'traceId': 'string'
},
'modelInvocationInput': {
'foundationModel': 'string',
'inferenceConfiguration': {
'maximumLength': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topK': 123,
'topP': ...
},
'overrideLambda': 'string',
'parserMode': 'DEFAULT'|'OVERRIDDEN',
'promptCreationMode': 'DEFAULT'|'OVERRIDDEN',
'text': 'string',
'traceId': 'string',
'type': 'PRE_PROCESSING'|'ORCHESTRATION'|'KNOWLEDGE_BASE_RESPONSE_GENERATION'|'POST_PROCESSING'|'ROUTING_CLASSIFIER'
},
'modelInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'rawResponse': {
'content': 'string'
},
'traceId': 'string'
},
'observation': {
'actionGroupInvocationOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'agentCollaboratorInvocationOutput': {
'agentCollaboratorAliasArn': 'string',
'agentCollaboratorName': 'string',
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'output': {
'returnControlPayload': {
'invocationId': 'string',
'invocationInputs': [
{
'apiInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'apiPath': 'string',
'collaboratorName': 'string',
'httpMethod': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
],
'requestBody': {
'content': {
'string': {
'properties': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
}
}
},
'functionInvocationInput': {
'actionGroup': 'string',
'actionInvocationType': 'RESULT'|'USER_CONFIRMATION'|'USER_CONFIRMATION_AND_RESULT',
'agentId': 'string',
'collaboratorName': 'string',
'function': 'string',
'parameters': [
{
'name': 'string',
'type': 'string',
'value': 'string'
},
]
}
},
]
},
'text': 'string',
'type': 'TEXT'|'RETURN_CONTROL'
}
},
'codeInterpreterInvocationOutput': {
'executionError': 'string',
'executionOutput': 'string',
'executionTimeout': True|False,
'files': [
'string',
],
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
}
},
'finalResponse': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'text': 'string'
},
'knowledgeBaseLookupOutput': {
'metadata': {
'clientRequestId': 'string',
'endTime': datetime(2015, 1, 1),
'operationTotalTimeMs': 123,
'startTime': datetime(2015, 1, 1),
'totalTimeMs': 123,
'usage': {
'inputTokens': 123,
'outputTokens': 123
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'repromptResponse': {
'source': 'ACTION_GROUP'|'KNOWLEDGE_BASE'|'PARSER',
'text': 'string'
},
'traceId': 'string',
'type': 'ACTION_GROUP'|'AGENT_COLLABORATOR'|'KNOWLEDGE_BASE'|'FINISH'|'ASK_USER'|'REPROMPT'
}
}
}
},
]
}
},
'nodeFailureEvent': {
'errorCode': 'VALIDATION'|'DEPENDENCY_FAILED'|'BAD_GATEWAY'|'INTERNAL_SERVER',
'errorMessage': 'string',
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1)
},
'nodeInputEvent': {
'fields': [
{
'category': 'LoopCondition'|'ReturnValueToLoopStart'|'ExitLoop',
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'executionChain': [
{
'index': 123,
'nodeName': 'string',
'type': 'Iterator'|'Loop'
},
],
'name': 'string',
'source': {
'expression': 'string',
'nodeName': 'string',
'outputFieldName': 'string'
},
'type': 'String'|'Number'|'Boolean'|'Object'|'Array'
},
],
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1)
},
'nodeOutputEvent': {
'fields': [
{
'content': {
'document': {...}|[...]|123|123.4|'string'|True|None
},
'name': 'string',
'next': [
{
'inputFieldName': 'string',
'nodeName': 'string'
},
],
'type': 'String'|'Number'|'Boolean'|'Object'|'Array'
},
],
'nodeName': 'string',
'timestamp': datetime(2015, 1, 1)
}
},
],
'nextToken': 'string'
}
**Response Structure**
::
# This section is too large to render.
# Please see the AWS API Documentation linked below.
`AWS API Documentation <https://docs.aws.amazon.com/goto/WebAPI/bedrock-agent-runtime-2023-07-26/ListFlowExecutionEvents>`_
{'retrievalQuery': {'image': {'format': 'png | jpeg | gif | webp',
'inlineContent': 'blob'},
'type': 'TEXT | IMAGE'}}
Response {'retrievalResults': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO', 'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}
Queries a knowledge base and retrieves information from it.
See also: AWS API Documentation
Request Syntax
client.retrieve(
guardrailConfiguration={
'guardrailId': 'string',
'guardrailVersion': 'string'
},
knowledgeBaseId='string',
nextToken='string',
retrievalConfiguration={
'vectorSearchConfiguration': {
'filter': {
'andAll': [
{'... recursive ...'},
],
'equals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'in': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'listContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notIn': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'orAll': [
{'... recursive ...'},
],
'startsWith': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'stringContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
}
},
'implicitFilterConfiguration': {
'metadataAttributes': [
{
'description': 'string',
'key': 'string',
'type': 'STRING'|'NUMBER'|'BOOLEAN'|'STRING_LIST'
},
],
'modelArn': 'string'
},
'numberOfResults': 123,
'overrideSearchType': 'HYBRID'|'SEMANTIC',
'rerankingConfiguration': {
'bedrockRerankingConfiguration': {
'metadataConfiguration': {
'selectionMode': 'SELECTIVE'|'ALL',
'selectiveModeConfiguration': {
'fieldsToExclude': [
{
'fieldName': 'string'
},
],
'fieldsToInclude': [
{
'fieldName': 'string'
},
]
}
},
'modelConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'modelArn': 'string'
},
'numberOfRerankedResults': 123
},
'type': 'BEDROCK_RERANKING_MODEL'
}
}
},
retrievalQuery={
'image': {
'format': 'png'|'jpeg'|'gif'|'webp',
'inlineContent': b'bytes'
},
'text': 'string',
'type': 'TEXT'|'IMAGE'
}
)
dict
Guardrail settings.
guardrailId (string) -- [REQUIRED]
The unique identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
string
[REQUIRED]
The unique identifier of the knowledge base to query.
string
If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.
dict
Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
vectorSearchConfiguration (dict) -- [REQUIRED]
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
filter (dict) --
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
andAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
equals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is cat:
"equals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than 1989:
"greaterThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989:
"greaterThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
in (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either cat or dog:
"in": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to 1989.
"lessThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to 1989.
"lessThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
listContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"]).
"listContains": { "key": "animals", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notEquals (dict) --
Knowledge base data sources are returned when:
It contains a metadata attribute whose name matches the key and whose value doesn't match the value in this object.
The key is not present in the document.
The following example would return data sources that don't contain an animal attribute whose value is cat.
"notEquals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notIn (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither cat nor dog.
"notIn": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
orAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
startsWith (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).
"startsWith": { "key": "animal", "value": "ca" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
stringContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat). "stringContains": { "key": "animal", "value": "at" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"]). "stringContains": { "key": "animals", "value": "at" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
implicitFilterConfiguration (dict) --
Settings for implicit filtering.
metadataAttributes (list) -- [REQUIRED]
Metadata that can be used in a filter.
(dict) --
Details about a metadata attribute.
description (string) -- [REQUIRED]
The attribute's description.
key (string) -- [REQUIRED]
The attribute's key.
type (string) -- [REQUIRED]
The attribute's type.
modelArn (string) -- [REQUIRED]
The model that generates the filter.
numberOfResults (integer) --
The number of source chunks to retrieve.
overrideSearchType (string) --
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
rerankingConfiguration (dict) --
Contains configurations for reranking the retrieved results. For more information, see Improve the relevance of query responses with a reranker model.
bedrockRerankingConfiguration (dict) --
Contains configurations for an Amazon Bedrock reranker model.
metadataConfiguration (dict) --
Contains configurations for the metadata to use in reranking.
selectionMode (string) -- [REQUIRED]
Specifies whether to consider all metadata when reranking, or only the metadata that you select. If you specify SELECTIVE, include the selectiveModeConfiguration field.
selectiveModeConfiguration (dict) --
Contains configurations for the metadata fields to include or exclude when considering reranking.
fieldsToExclude (list) --
An array of objects, each of which specifies a metadata field to exclude from consideration when reranking.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
fieldsToInclude (list) --
An array of objects, each of which specifies a metadata field to include in consideration when reranking. The remaining metadata fields are ignored.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
modelConfiguration (dict) -- [REQUIRED]
Contains configurations for the reranker model.
additionalModelRequestFields (dict) --
A JSON object whose keys are request fields for the model and whose values are values for those fields.
(string) --
(:ref:`document<document>`) --
modelArn (string) -- [REQUIRED]
The ARN of the reranker model to use.
numberOfRerankedResults (integer) --
The number of results to return after reranking.
type (string) -- [REQUIRED]
The type of reranker model.
dict
[REQUIRED]
Contains the query to send the knowledge base.
image (dict) --
An image to include in the knowledge base query for multimodal retrieval.
format (string) -- [REQUIRED]
The format of the input image. Supported formats include png, gif, jpeg, and webp.
inlineContent (bytes) -- [REQUIRED]
The base64-encoded image data for inline image content. Maximum size is 5MB.
text (string) --
The text of the query made to the knowledge base.
type (string) --
The type of query being performed.
dict
Response Syntax
{
'guardrailAction': 'INTERVENED'|'NONE',
'nextToken': 'string',
'retrievalResults': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'score': 123.0
},
]
}
Response Structure
(dict) --
guardrailAction (string) --
Specifies if there is a guardrail intervention in the response.
nextToken (string) --
If there are more results than can fit in the response, the response returns a nextToken. Use this token in the nextToken field of another request to retrieve the next batch of results.
retrievalResults (list) --
A list of results from querying the knowledge base.
(dict) --
Details about a result from querying the knowledge base.
This data type is used in the following API operations:
Retrieve response – in the retrievalResults field
content (dict) --
Contains information about the content of the chunk.
audio (dict) --
Audio segment information when the retrieval result contains audio content.
s3Uri (string) --
The S3 URI where this specific audio segment is stored in the multimodal storage destination.
transcription (string) --
The text transcription of the audio segment content.
byteContent (string) --
A data URI with base64-encoded content from the data source. The URI is in the following format: returned in the following format: data:image/jpeg;base64,${base64-encoded string}.
row (list) --
Specifies information about the rows with the cells to return in retrieval.
(dict) --
Contains information about a column with a cell to return in retrieval.
columnName (string) --
The name of the column.
columnValue (string) --
The value in the column.
type (string) --
The data type of the value.
text (string) --
The cited text from the data source.
type (string) --
The type of content in the retrieval result.
video (dict) --
Video segment information when the retrieval result contains video content.
s3Uri (string) --
The S3 URI where this specific video segment is stored in the multimodal storage destination.
summary (string) --
A text summary describing the content of the video segment.
location (dict) --
Contains information about the location of the data source.
confluenceLocation (dict) --
The Confluence data source location.
url (string) --
The Confluence host URL for the data source location.
customDocumentLocation (dict) --
Specifies the location of a document in a custom data source.
id (string) --
The ID of the document.
kendraDocumentLocation (dict) --
The location of a document in Amazon Kendra.
uri (string) --
The document's uri.
s3Location (dict) --
The S3 data source location.
uri (string) --
The S3 URI for the data source location.
salesforceLocation (dict) --
The Salesforce data source location.
url (string) --
The Salesforce host URL for the data source location.
sharePointLocation (dict) --
The SharePoint data source location.
url (string) --
The SharePoint site URL for the data source location.
sqlLocation (dict) --
Specifies information about the SQL query used to retrieve the result.
query (string) --
The SQL query used to retrieve the result.
type (string) --
The type of data source location.
webLocation (dict) --
The web URL/URLs data source location.
url (string) --
The web URL/URLs for the data source location.
metadata (dict) --
Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
(string) --
(:ref:`document<document>`) --
score (float) --
The level of relevance of the result to the query.
{'citations': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO', 'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}
Queries a knowledge base and generates responses based on the retrieved results and using the specified foundation model or inference profile. The response only cites sources that are relevant to the query.
See also: AWS API Documentation
Request Syntax
client.retrieve_and_generate(
input={
'text': 'string'
},
retrieveAndGenerateConfiguration={
'externalSourcesConfiguration': {
'generationConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'guardrailConfiguration': {
'guardrailId': 'string',
'guardrailVersion': 'string'
},
'inferenceConfig': {
'textInferenceConfig': {
'maxTokens': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topP': ...
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
},
'promptTemplate': {
'textPromptTemplate': 'string'
}
},
'modelArn': 'string',
'sources': [
{
'byteContent': {
'contentType': 'string',
'data': b'bytes',
'identifier': 'string'
},
's3Location': {
'uri': 'string'
},
'sourceType': 'S3'|'BYTE_CONTENT'
},
]
},
'knowledgeBaseConfiguration': {
'generationConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'guardrailConfiguration': {
'guardrailId': 'string',
'guardrailVersion': 'string'
},
'inferenceConfig': {
'textInferenceConfig': {
'maxTokens': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topP': ...
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
},
'promptTemplate': {
'textPromptTemplate': 'string'
}
},
'knowledgeBaseId': 'string',
'modelArn': 'string',
'orchestrationConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'inferenceConfig': {
'textInferenceConfig': {
'maxTokens': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topP': ...
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
},
'promptTemplate': {
'textPromptTemplate': 'string'
},
'queryTransformationConfiguration': {
'type': 'QUERY_DECOMPOSITION'
}
},
'retrievalConfiguration': {
'vectorSearchConfiguration': {
'filter': {
'andAll': [
{'... recursive ...'},
],
'equals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'in': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'listContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notIn': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'orAll': [
{'... recursive ...'},
],
'startsWith': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'stringContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
}
},
'implicitFilterConfiguration': {
'metadataAttributes': [
{
'description': 'string',
'key': 'string',
'type': 'STRING'|'NUMBER'|'BOOLEAN'|'STRING_LIST'
},
],
'modelArn': 'string'
},
'numberOfResults': 123,
'overrideSearchType': 'HYBRID'|'SEMANTIC',
'rerankingConfiguration': {
'bedrockRerankingConfiguration': {
'metadataConfiguration': {
'selectionMode': 'SELECTIVE'|'ALL',
'selectiveModeConfiguration': {
'fieldsToExclude': [
{
'fieldName': 'string'
},
],
'fieldsToInclude': [
{
'fieldName': 'string'
},
]
}
},
'modelConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'modelArn': 'string'
},
'numberOfRerankedResults': 123
},
'type': 'BEDROCK_RERANKING_MODEL'
}
}
}
},
'type': 'KNOWLEDGE_BASE'|'EXTERNAL_SOURCES'
},
sessionConfiguration={
'kmsKeyArn': 'string'
},
sessionId='string'
)
dict
[REQUIRED]
Contains the query to be made to the knowledge base.
text (string) -- [REQUIRED]
The query made to the knowledge base, in characters.
dict
Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
externalSourcesConfiguration (dict) --
The configuration for the external source wrapper object in the retrieveAndGenerate function.
generationConfiguration (dict) --
The prompt used with the external source wrapper object with the retrieveAndGenerate function.
additionalModelRequestFields (dict) --
Additional model parameters and their corresponding values not included in the textInferenceConfig structure for an external source. Takes in custom model parameters specific to the language model being used.
(string) --
(:ref:`document<document>`) --
guardrailConfiguration (dict) --
The configuration details for the guardrail.
guardrailId (string) -- [REQUIRED]
The unique identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
inferenceConfig (dict) --
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using an external source.
textInferenceConfig (dict) --
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
maxTokens (integer) --
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
stopSequences (list) --
A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
(string) --
temperature (float) --
Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
topP (float) --
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
promptTemplate (dict) --
Contain the textPromptTemplate string for the external source wrapper object.
textPromptTemplate (string) --
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
modelArn (string) -- [REQUIRED]
The model Amazon Resource Name (ARN) for the external source wrapper object in the retrieveAndGenerate function.
sources (list) -- [REQUIRED]
The document for the external source wrapper object in the retrieveAndGenerate function.
(dict) --
The unique external source of the content contained in the wrapper object.
byteContent (dict) --
The identifier, contentType, and data of the external source wrapper object.
contentType (string) -- [REQUIRED]
The MIME type of the document contained in the wrapper object.
data (bytes) -- [REQUIRED]
The byte value of the file to upload, encoded as a Base-64 string.
identifier (string) -- [REQUIRED]
The file name of the document contained in the wrapper object.
s3Location (dict) --
The S3 location of the external source wrapper object.
uri (string) -- [REQUIRED]
The file location of the S3 wrapper object.
sourceType (string) -- [REQUIRED]
The source type of the external source wrapper object.
knowledgeBaseConfiguration (dict) --
Contains details about the knowledge base for retrieving information and generating responses.
generationConfiguration (dict) --
Contains configurations for response generation based on the knowledge base query results.
additionalModelRequestFields (dict) --
Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.
(string) --
(:ref:`document<document>`) --
guardrailConfiguration (dict) --
The configuration details for the guardrail.
guardrailId (string) -- [REQUIRED]
The unique identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
inferenceConfig (dict) --
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
textInferenceConfig (dict) --
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
maxTokens (integer) --
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
stopSequences (list) --
A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
(string) --
temperature (float) --
Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
topP (float) --
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
promptTemplate (dict) --
Contains the template for the prompt that's sent to the model for response generation. Generation prompts must include the $search_results$ variable. For more information, see Use placeholder variables in the user guide.
textPromptTemplate (string) --
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
knowledgeBaseId (string) -- [REQUIRED]
The unique identifier of the knowledge base that is queried.
modelArn (string) -- [REQUIRED]
The ARN of the foundation model or inference profile used to generate a response.
orchestrationConfiguration (dict) --
Settings for how the model processes the prompt prior to retrieval and generation.
additionalModelRequestFields (dict) --
Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.
(string) --
(:ref:`document<document>`) --
inferenceConfig (dict) --
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
textInferenceConfig (dict) --
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
maxTokens (integer) --
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
stopSequences (list) --
A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
(string) --
temperature (float) --
Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
topP (float) --
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
promptTemplate (dict) --
Contains the template for the prompt that's sent to the model. Orchestration prompts must include the $conversation_history$ and $output_format_instructions$ variables. For more information, see Use placeholder variables in the user guide.
textPromptTemplate (string) --
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
queryTransformationConfiguration (dict) --
To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.
type (string) -- [REQUIRED]
The type of transformation to apply to the prompt.
retrievalConfiguration (dict) --
Contains configurations for how to retrieve and return the knowledge base query.
vectorSearchConfiguration (dict) -- [REQUIRED]
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
filter (dict) --
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
andAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
equals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is cat:
"equals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than 1989:
"greaterThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989:
"greaterThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
in (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either cat or dog:
"in": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to 1989.
"lessThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to 1989.
"lessThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
listContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"]).
"listContains": { "key": "animals", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notEquals (dict) --
Knowledge base data sources are returned when:
It contains a metadata attribute whose name matches the key and whose value doesn't match the value in this object.
The key is not present in the document.
The following example would return data sources that don't contain an animal attribute whose value is cat.
"notEquals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notIn (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither cat nor dog.
"notIn": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
orAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
startsWith (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).
"startsWith": { "key": "animal", "value": "ca" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
stringContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat). "stringContains": { "key": "animal", "value": "at" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"]). "stringContains": { "key": "animals", "value": "at" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
implicitFilterConfiguration (dict) --
Settings for implicit filtering.
metadataAttributes (list) -- [REQUIRED]
Metadata that can be used in a filter.
(dict) --
Details about a metadata attribute.
description (string) -- [REQUIRED]
The attribute's description.
key (string) -- [REQUIRED]
The attribute's key.
type (string) -- [REQUIRED]
The attribute's type.
modelArn (string) -- [REQUIRED]
The model that generates the filter.
numberOfResults (integer) --
The number of source chunks to retrieve.
overrideSearchType (string) --
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
rerankingConfiguration (dict) --
Contains configurations for reranking the retrieved results. For more information, see Improve the relevance of query responses with a reranker model.
bedrockRerankingConfiguration (dict) --
Contains configurations for an Amazon Bedrock reranker model.
metadataConfiguration (dict) --
Contains configurations for the metadata to use in reranking.
selectionMode (string) -- [REQUIRED]
Specifies whether to consider all metadata when reranking, or only the metadata that you select. If you specify SELECTIVE, include the selectiveModeConfiguration field.
selectiveModeConfiguration (dict) --
Contains configurations for the metadata fields to include or exclude when considering reranking.
fieldsToExclude (list) --
An array of objects, each of which specifies a metadata field to exclude from consideration when reranking.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
fieldsToInclude (list) --
An array of objects, each of which specifies a metadata field to include in consideration when reranking. The remaining metadata fields are ignored.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
modelConfiguration (dict) -- [REQUIRED]
Contains configurations for the reranker model.
additionalModelRequestFields (dict) --
A JSON object whose keys are request fields for the model and whose values are values for those fields.
(string) --
(:ref:`document<document>`) --
modelArn (string) -- [REQUIRED]
The ARN of the reranker model to use.
numberOfRerankedResults (integer) --
The number of results to return after reranking.
type (string) -- [REQUIRED]
The type of reranker model.
type (string) -- [REQUIRED]
The type of resource that contains your data for retrieving information and generating responses.
dict
Contains details about the session with the knowledge base.
kmsKeyArn (string) -- [REQUIRED]
The ARN of the KMS key encrypting the session.
string
The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can't explicitly set the sessionId yourself.
dict
Response Syntax
{
'citations': [
{
'generatedResponsePart': {
'textResponsePart': {
'span': {
'end': 123,
'start': 123
},
'text': 'string'
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
],
'guardrailAction': 'INTERVENED'|'NONE',
'output': {
'text': 'string'
},
'sessionId': 'string'
}
Response Structure
(dict) --
citations (list) --
A list of segments of the generated response that are based on sources in the knowledge base, alongside information about the sources.
(dict) --
An object containing a segment of the generated response that is based on a source in the knowledge base, alongside information about the source.
This data type is used in the following API operations:
InvokeAgent response – in the citations field
RetrieveAndGenerate response – in the citations field
generatedResponsePart (dict) --
Contains the generated response and metadata
textResponsePart (dict) --
Contains metadata about a textual part of the generated response that is accompanied by a citation.
span (dict) --
Contains information about where the text with a citation begins and ends in the generated output.
end (integer) --
Where the text with a citation ends in the generated output.
start (integer) --
Where the text with a citation starts in the generated output.
text (string) --
The part of the generated text that contains a citation.
retrievedReferences (list) --
Contains metadata about the sources cited for the generated response.
(dict) --
Contains metadata about a source cited for the generated response.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the retrievedReferences field
InvokeAgent response – in the retrievedReferences field
content (dict) --
Contains the cited text from the data source.
audio (dict) --
Audio segment information when the retrieval result contains audio content.
s3Uri (string) --
The S3 URI where this specific audio segment is stored in the multimodal storage destination.
transcription (string) --
The text transcription of the audio segment content.
byteContent (string) --
A data URI with base64-encoded content from the data source. The URI is in the following format: returned in the following format: data:image/jpeg;base64,${base64-encoded string}.
row (list) --
Specifies information about the rows with the cells to return in retrieval.
(dict) --
Contains information about a column with a cell to return in retrieval.
columnName (string) --
The name of the column.
columnValue (string) --
The value in the column.
type (string) --
The data type of the value.
text (string) --
The cited text from the data source.
type (string) --
The type of content in the retrieval result.
video (dict) --
Video segment information when the retrieval result contains video content.
s3Uri (string) --
The S3 URI where this specific video segment is stored in the multimodal storage destination.
summary (string) --
A text summary describing the content of the video segment.
location (dict) --
Contains information about the location of the data source.
confluenceLocation (dict) --
The Confluence data source location.
url (string) --
The Confluence host URL for the data source location.
customDocumentLocation (dict) --
Specifies the location of a document in a custom data source.
id (string) --
The ID of the document.
kendraDocumentLocation (dict) --
The location of a document in Amazon Kendra.
uri (string) --
The document's uri.
s3Location (dict) --
The S3 data source location.
uri (string) --
The S3 URI for the data source location.
salesforceLocation (dict) --
The Salesforce data source location.
url (string) --
The Salesforce host URL for the data source location.
sharePointLocation (dict) --
The SharePoint data source location.
url (string) --
The SharePoint site URL for the data source location.
sqlLocation (dict) --
Specifies information about the SQL query used to retrieve the result.
query (string) --
The SQL query used to retrieve the result.
type (string) --
The type of data source location.
webLocation (dict) --
The web URL/URLs data source location.
url (string) --
The web URL/URLs for the data source location.
metadata (dict) --
Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
(string) --
(:ref:`document<document>`) --
guardrailAction (string) --
Specifies if there is a guardrail intervention in the response.
output (dict) --
Contains the response generated from querying the knowledge base.
text (string) --
The response generated from querying the knowledge base.
sessionId (string) --
The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can't explicitly set the sessionId yourself.
{'stream': {'citation': {'citation': {'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}},
'retrievedReferences': {'content': {'audio': {'s3Uri': 'string',
'transcription': 'string'},
'type': {'AUDIO',
'VIDEO'},
'video': {'s3Uri': 'string',
'summary': 'string'}}}}}}
Queries a knowledge base and generates responses based on the retrieved results, with output in streaming format.
This operation requires permission for the bedrock:RetrieveAndGenerate action.
See also: AWS API Documentation
Request Syntax
client.retrieve_and_generate_stream(
input={
'text': 'string'
},
retrieveAndGenerateConfiguration={
'externalSourcesConfiguration': {
'generationConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'guardrailConfiguration': {
'guardrailId': 'string',
'guardrailVersion': 'string'
},
'inferenceConfig': {
'textInferenceConfig': {
'maxTokens': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topP': ...
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
},
'promptTemplate': {
'textPromptTemplate': 'string'
}
},
'modelArn': 'string',
'sources': [
{
'byteContent': {
'contentType': 'string',
'data': b'bytes',
'identifier': 'string'
},
's3Location': {
'uri': 'string'
},
'sourceType': 'S3'|'BYTE_CONTENT'
},
]
},
'knowledgeBaseConfiguration': {
'generationConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'guardrailConfiguration': {
'guardrailId': 'string',
'guardrailVersion': 'string'
},
'inferenceConfig': {
'textInferenceConfig': {
'maxTokens': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topP': ...
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
},
'promptTemplate': {
'textPromptTemplate': 'string'
}
},
'knowledgeBaseId': 'string',
'modelArn': 'string',
'orchestrationConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'inferenceConfig': {
'textInferenceConfig': {
'maxTokens': 123,
'stopSequences': [
'string',
],
'temperature': ...,
'topP': ...
}
},
'performanceConfig': {
'latency': 'standard'|'optimized'
},
'promptTemplate': {
'textPromptTemplate': 'string'
},
'queryTransformationConfiguration': {
'type': 'QUERY_DECOMPOSITION'
}
},
'retrievalConfiguration': {
'vectorSearchConfiguration': {
'filter': {
'andAll': [
{'... recursive ...'},
],
'equals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'greaterThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'in': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThan': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'lessThanOrEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'listContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notEquals': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'notIn': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'orAll': [
{'... recursive ...'},
],
'startsWith': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
},
'stringContains': {
'key': 'string',
'value': {...}|[...]|123|123.4|'string'|True|None
}
},
'implicitFilterConfiguration': {
'metadataAttributes': [
{
'description': 'string',
'key': 'string',
'type': 'STRING'|'NUMBER'|'BOOLEAN'|'STRING_LIST'
},
],
'modelArn': 'string'
},
'numberOfResults': 123,
'overrideSearchType': 'HYBRID'|'SEMANTIC',
'rerankingConfiguration': {
'bedrockRerankingConfiguration': {
'metadataConfiguration': {
'selectionMode': 'SELECTIVE'|'ALL',
'selectiveModeConfiguration': {
'fieldsToExclude': [
{
'fieldName': 'string'
},
],
'fieldsToInclude': [
{
'fieldName': 'string'
},
]
}
},
'modelConfiguration': {
'additionalModelRequestFields': {
'string': {...}|[...]|123|123.4|'string'|True|None
},
'modelArn': 'string'
},
'numberOfRerankedResults': 123
},
'type': 'BEDROCK_RERANKING_MODEL'
}
}
}
},
'type': 'KNOWLEDGE_BASE'|'EXTERNAL_SOURCES'
},
sessionConfiguration={
'kmsKeyArn': 'string'
},
sessionId='string'
)
dict
[REQUIRED]
Contains the query to be made to the knowledge base.
text (string) -- [REQUIRED]
The query made to the knowledge base, in characters.
dict
Contains configurations for the knowledge base query and retrieval process. For more information, see Query configurations.
externalSourcesConfiguration (dict) --
The configuration for the external source wrapper object in the retrieveAndGenerate function.
generationConfiguration (dict) --
The prompt used with the external source wrapper object with the retrieveAndGenerate function.
additionalModelRequestFields (dict) --
Additional model parameters and their corresponding values not included in the textInferenceConfig structure for an external source. Takes in custom model parameters specific to the language model being used.
(string) --
(:ref:`document<document>`) --
guardrailConfiguration (dict) --
The configuration details for the guardrail.
guardrailId (string) -- [REQUIRED]
The unique identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
inferenceConfig (dict) --
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using an external source.
textInferenceConfig (dict) --
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
maxTokens (integer) --
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
stopSequences (list) --
A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
(string) --
temperature (float) --
Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
topP (float) --
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
promptTemplate (dict) --
Contain the textPromptTemplate string for the external source wrapper object.
textPromptTemplate (string) --
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
modelArn (string) -- [REQUIRED]
The model Amazon Resource Name (ARN) for the external source wrapper object in the retrieveAndGenerate function.
sources (list) -- [REQUIRED]
The document for the external source wrapper object in the retrieveAndGenerate function.
(dict) --
The unique external source of the content contained in the wrapper object.
byteContent (dict) --
The identifier, contentType, and data of the external source wrapper object.
contentType (string) -- [REQUIRED]
The MIME type of the document contained in the wrapper object.
data (bytes) -- [REQUIRED]
The byte value of the file to upload, encoded as a Base-64 string.
identifier (string) -- [REQUIRED]
The file name of the document contained in the wrapper object.
s3Location (dict) --
The S3 location of the external source wrapper object.
uri (string) -- [REQUIRED]
The file location of the S3 wrapper object.
sourceType (string) -- [REQUIRED]
The source type of the external source wrapper object.
knowledgeBaseConfiguration (dict) --
Contains details about the knowledge base for retrieving information and generating responses.
generationConfiguration (dict) --
Contains configurations for response generation based on the knowledge base query results.
additionalModelRequestFields (dict) --
Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.
(string) --
(:ref:`document<document>`) --
guardrailConfiguration (dict) --
The configuration details for the guardrail.
guardrailId (string) -- [REQUIRED]
The unique identifier for the guardrail.
guardrailVersion (string) -- [REQUIRED]
The version of the guardrail.
inferenceConfig (dict) --
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
textInferenceConfig (dict) --
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
maxTokens (integer) --
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
stopSequences (list) --
A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
(string) --
temperature (float) --
Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
topP (float) --
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
promptTemplate (dict) --
Contains the template for the prompt that's sent to the model for response generation. Generation prompts must include the $search_results$ variable. For more information, see Use placeholder variables in the user guide.
textPromptTemplate (string) --
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
knowledgeBaseId (string) -- [REQUIRED]
The unique identifier of the knowledge base that is queried.
modelArn (string) -- [REQUIRED]
The ARN of the foundation model or inference profile used to generate a response.
orchestrationConfiguration (dict) --
Settings for how the model processes the prompt prior to retrieval and generation.
additionalModelRequestFields (dict) --
Additional model parameters and corresponding values not included in the textInferenceConfig structure for a knowledge base. This allows users to provide custom model parameters specific to the language model being used.
(string) --
(:ref:`document<document>`) --
inferenceConfig (dict) --
Configuration settings for inference when using RetrieveAndGenerate to generate responses while using a knowledge base as a source.
textInferenceConfig (dict) --
Configuration settings specific to text generation while generating responses using RetrieveAndGenerate.
maxTokens (integer) --
The maximum number of tokens to generate in the output text. Do not use the minimum of 0 or the maximum of 65536. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
stopSequences (list) --
A list of sequences of characters that, if generated, will cause the model to stop generating further tokens. Do not use a minimum length of 1 or a maximum length of 1000. The limit values described here are arbitary values, for actual values consult the limits defined by your specific model.
(string) --
temperature (float) --
Controls the random-ness of text generated by the language model, influencing how much the model sticks to the most predictable next words versus exploring more surprising options. A lower temperature value (e.g. 0.2 or 0.3) makes model outputs more deterministic or predictable, while a higher temperature (e.g. 0.8 or 0.9) makes the outputs more creative or unpredictable.
topP (float) --
A probability distribution threshold which controls what the model considers for the set of possible next tokens. The model will only consider the top p% of the probability distribution when generating the next token.
performanceConfig (dict) --
The latency configuration for the model.
latency (string) --
To use a latency-optimized version of the model, set to optimized.
promptTemplate (dict) --
Contains the template for the prompt that's sent to the model. Orchestration prompts must include the $conversation_history$ and $output_format_instructions$ variables. For more information, see Use placeholder variables in the user guide.
textPromptTemplate (string) --
The template for the prompt that's sent to the model for response generation. You can include prompt placeholders, which become replaced before the prompt is sent to the model to provide instructions and context to the model. In addition, you can include XML tags to delineate meaningful sections of the prompt template.
For more information, see the following resources:
queryTransformationConfiguration (dict) --
To split up the prompt and retrieve multiple sources, set the transformation type to QUERY_DECOMPOSITION.
type (string) -- [REQUIRED]
The type of transformation to apply to the prompt.
retrievalConfiguration (dict) --
Contains configurations for how to retrieve and return the knowledge base query.
vectorSearchConfiguration (dict) -- [REQUIRED]
Contains details about how the results from the vector search should be returned. For more information, see Query configurations.
filter (dict) --
Specifies the filters to use on the metadata in the knowledge base data sources before returning results. For more information, see Query configurations.
andAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill all the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
equals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value matches the value in this object.
The following example would return data sources with an animal attribute whose value is cat:
"equals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than the value in this object.
The following example would return data sources with an year attribute whose value is greater than 1989:
"greaterThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
greaterThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is greater than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is greater than or equal to 1989:
"greaterThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
in (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is in the list specified in the value in this object.
The following example would return data sources with an animal attribute that is either cat or dog:
"in": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThan (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than the value in this object.
The following example would return data sources with an year attribute whose value is less than to 1989.
"lessThan": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
lessThanOrEquals (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is less than or equal to the value in this object.
The following example would return data sources with an year attribute whose value is less than or equal to 1989.
"lessThanOrEquals": { "key": "year", "value": 1989 }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
listContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is a list that contains the value as one of its members.
The following example would return data sources with an animals attribute that is a list containing a cat member (for example ["dog", "cat"]).
"listContains": { "key": "animals", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notEquals (dict) --
Knowledge base data sources are returned when:
It contains a metadata attribute whose name matches the key and whose value doesn't match the value in this object.
The key is not present in the document.
The following example would return data sources that don't contain an animal attribute whose value is cat.
"notEquals": { "key": "animal", "value": "cat" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
notIn (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value isn't in the list specified in the value in this object.
The following example would return data sources whose animal attribute is neither cat nor dog.
"notIn": { "key": "animal", "value": ["cat", "dog"] }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
orAll (list) --
Knowledge base data sources are returned if their metadata attributes fulfill at least one of the filter conditions inside this list.
(dict) --
Specifies the filters to use on the metadata attributes in the knowledge base data sources before returning results. For more information, see Query configurations. See the examples below to see how to use these filters.
This data type is used in the following API operations:
Retrieve request – in the filter field
RetrieveAndGenerate request – in the filter field
startsWith (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value starts with the value in this object. This filter is currently only supported for Amazon OpenSearch Serverless vector stores.
The following example would return data sources with an animal attribute starts with ca (for example, cat or camel).
"startsWith": { "key": "animal", "value": "ca" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
stringContains (dict) --
Knowledge base data sources are returned if they contain a metadata attribute whose name matches the key and whose value is one of the following:
A string that contains the value as a substring. The following example would return data sources with an animal attribute that contains the substring at (for example cat). "stringContains": { "key": "animal", "value": "at" }
A list with a member that contains the value as a substring. The following example would return data sources with an animals attribute that is a list containing a member that contains the substring at (for example ["dog", "cat"]). "stringContains": { "key": "animals", "value": "at" }
key (string) -- [REQUIRED]
The name that the metadata attribute must match.
value (:ref:`document<document>`) -- [REQUIRED]
The value to whcih to compare the value of the metadata attribute.
implicitFilterConfiguration (dict) --
Settings for implicit filtering.
metadataAttributes (list) -- [REQUIRED]
Metadata that can be used in a filter.
(dict) --
Details about a metadata attribute.
description (string) -- [REQUIRED]
The attribute's description.
key (string) -- [REQUIRED]
The attribute's key.
type (string) -- [REQUIRED]
The attribute's type.
modelArn (string) -- [REQUIRED]
The model that generates the filter.
numberOfResults (integer) --
The number of source chunks to retrieve.
overrideSearchType (string) --
By default, Amazon Bedrock decides a search strategy for you. If you're using an Amazon OpenSearch Serverless vector store that contains a filterable text field, you can specify whether to query the knowledge base with a HYBRID search using both vector embeddings and raw text, or SEMANTIC search using only vector embeddings. For other vector store configurations, only SEMANTIC search is available. For more information, see Test a knowledge base.
rerankingConfiguration (dict) --
Contains configurations for reranking the retrieved results. For more information, see Improve the relevance of query responses with a reranker model.
bedrockRerankingConfiguration (dict) --
Contains configurations for an Amazon Bedrock reranker model.
metadataConfiguration (dict) --
Contains configurations for the metadata to use in reranking.
selectionMode (string) -- [REQUIRED]
Specifies whether to consider all metadata when reranking, or only the metadata that you select. If you specify SELECTIVE, include the selectiveModeConfiguration field.
selectiveModeConfiguration (dict) --
Contains configurations for the metadata fields to include or exclude when considering reranking.
fieldsToExclude (list) --
An array of objects, each of which specifies a metadata field to exclude from consideration when reranking.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
fieldsToInclude (list) --
An array of objects, each of which specifies a metadata field to include in consideration when reranking. The remaining metadata fields are ignored.
(dict) --
Contains information for a metadata field to include in or exclude from consideration when reranking.
fieldName (string) -- [REQUIRED]
The name of a metadata field to include in or exclude from consideration when reranking.
modelConfiguration (dict) -- [REQUIRED]
Contains configurations for the reranker model.
additionalModelRequestFields (dict) --
A JSON object whose keys are request fields for the model and whose values are values for those fields.
(string) --
(:ref:`document<document>`) --
modelArn (string) -- [REQUIRED]
The ARN of the reranker model to use.
numberOfRerankedResults (integer) --
The number of results to return after reranking.
type (string) -- [REQUIRED]
The type of reranker model.
type (string) -- [REQUIRED]
The type of resource that contains your data for retrieving information and generating responses.
dict
Contains details about the session with the knowledge base.
kmsKeyArn (string) -- [REQUIRED]
The ARN of the KMS key encrypting the session.
string
The unique identifier of the session. When you first make a RetrieveAndGenerate request, Amazon Bedrock automatically generates this value. You must reuse this value for all subsequent requests in the same conversational session. This value allows Amazon Bedrock to maintain context and knowledge from previous interactions. You can't explicitly set the sessionId yourself.
dict
The response of this operation contains an :class:`.EventStream` member. When iterated the :class:`.EventStream` will yield events based on the structure below, where only one of the top level keys will be present for any given event.
Response Syntax
{
'sessionId': 'string',
'stream': EventStream({
'accessDeniedException': {
'message': 'string'
},
'badGatewayException': {
'message': 'string',
'resourceName': 'string'
},
'citation': {
'citation': {
'generatedResponsePart': {
'textResponsePart': {
'span': {
'end': 123,
'start': 123
},
'text': 'string'
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'generatedResponsePart': {
'textResponsePart': {
'span': {
'end': 123,
'start': 123
},
'text': 'string'
}
},
'retrievedReferences': [
{
'content': {
'audio': {
's3Uri': 'string',
'transcription': 'string'
},
'byteContent': 'string',
'row': [
{
'columnName': 'string',
'columnValue': 'string',
'type': 'BLOB'|'BOOLEAN'|'DOUBLE'|'NULL'|'LONG'|'STRING'
},
],
'text': 'string',
'type': 'TEXT'|'IMAGE'|'ROW'|'AUDIO'|'VIDEO',
'video': {
's3Uri': 'string',
'summary': 'string'
}
},
'location': {
'confluenceLocation': {
'url': 'string'
},
'customDocumentLocation': {
'id': 'string'
},
'kendraDocumentLocation': {
'uri': 'string'
},
's3Location': {
'uri': 'string'
},
'salesforceLocation': {
'url': 'string'
},
'sharePointLocation': {
'url': 'string'
},
'sqlLocation': {
'query': 'string'
},
'type': 'S3'|'WEB'|'CONFLUENCE'|'SALESFORCE'|'SHAREPOINT'|'CUSTOM'|'KENDRA'|'SQL',
'webLocation': {
'url': 'string'
}
},
'metadata': {
'string': {...}|[...]|123|123.4|'string'|True|None
}
},
]
},
'conflictException': {
'message': 'string'
},
'dependencyFailedException': {
'message': 'string',
'resourceName': 'string'
},
'guardrail': {
'action': 'INTERVENED'|'NONE'
},
'internalServerException': {
'message': 'string',
'reason': 'string'
},
'output': {
'text': 'string'
},
'resourceNotFoundException': {
'message': 'string'
},
'serviceQuotaExceededException': {
'message': 'string'
},
'throttlingException': {
'message': 'string'
},
'validationException': {
'message': 'string'
}
})
}
Response Structure
(dict) --
sessionId (string) --
The session ID.
stream (:class:`.EventStream`) --
A stream of events from the model.
accessDeniedException (dict) --
The request is denied because you do not have sufficient permissions to perform the requested action. For troubleshooting this error, see AccessDeniedException in the Amazon Bedrock User Guide.
message (string) --
badGatewayException (dict) --
The request failed due to a bad gateway error.
message (string) --
resourceName (string) --
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
citation (dict) --
A citation event.
citation (dict) --
The citation.
generatedResponsePart (dict) --
Contains the generated response and metadata
textResponsePart (dict) --
Contains metadata about a textual part of the generated response that is accompanied by a citation.
span (dict) --
Contains information about where the text with a citation begins and ends in the generated output.
end (integer) --
Where the text with a citation ends in the generated output.
start (integer) --
Where the text with a citation starts in the generated output.
text (string) --
The part of the generated text that contains a citation.
retrievedReferences (list) --
Contains metadata about the sources cited for the generated response.
(dict) --
Contains metadata about a source cited for the generated response.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the retrievedReferences field
InvokeAgent response – in the retrievedReferences field
content (dict) --
Contains the cited text from the data source.
audio (dict) --
Audio segment information when the retrieval result contains audio content.
s3Uri (string) --
The S3 URI where this specific audio segment is stored in the multimodal storage destination.
transcription (string) --
The text transcription of the audio segment content.
byteContent (string) --
A data URI with base64-encoded content from the data source. The URI is in the following format: returned in the following format: data:image/jpeg;base64,${base64-encoded string}.
row (list) --
Specifies information about the rows with the cells to return in retrieval.
(dict) --
Contains information about a column with a cell to return in retrieval.
columnName (string) --
The name of the column.
columnValue (string) --
The value in the column.
type (string) --
The data type of the value.
text (string) --
The cited text from the data source.
type (string) --
The type of content in the retrieval result.
video (dict) --
Video segment information when the retrieval result contains video content.
s3Uri (string) --
The S3 URI where this specific video segment is stored in the multimodal storage destination.
summary (string) --
A text summary describing the content of the video segment.
location (dict) --
Contains information about the location of the data source.
confluenceLocation (dict) --
The Confluence data source location.
url (string) --
The Confluence host URL for the data source location.
customDocumentLocation (dict) --
Specifies the location of a document in a custom data source.
id (string) --
The ID of the document.
kendraDocumentLocation (dict) --
The location of a document in Amazon Kendra.
uri (string) --
The document's uri.
s3Location (dict) --
The S3 data source location.
uri (string) --
The S3 URI for the data source location.
salesforceLocation (dict) --
The Salesforce data source location.
url (string) --
The Salesforce host URL for the data source location.
sharePointLocation (dict) --
The SharePoint data source location.
url (string) --
The SharePoint site URL for the data source location.
sqlLocation (dict) --
Specifies information about the SQL query used to retrieve the result.
query (string) --
The SQL query used to retrieve the result.
type (string) --
The type of data source location.
webLocation (dict) --
The web URL/URLs data source location.
url (string) --
The web URL/URLs for the data source location.
metadata (dict) --
Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
(string) --
(:ref:`document<document>`) --
generatedResponsePart (dict) --
The generated response to the citation event.
textResponsePart (dict) --
Contains metadata about a textual part of the generated response that is accompanied by a citation.
span (dict) --
Contains information about where the text with a citation begins and ends in the generated output.
end (integer) --
Where the text with a citation ends in the generated output.
start (integer) --
Where the text with a citation starts in the generated output.
text (string) --
The part of the generated text that contains a citation.
retrievedReferences (list) --
The retrieved references of the citation event.
(dict) --
Contains metadata about a source cited for the generated response.
This data type is used in the following API operations:
RetrieveAndGenerate response – in the retrievedReferences field
InvokeAgent response – in the retrievedReferences field
content (dict) --
Contains the cited text from the data source.
audio (dict) --
Audio segment information when the retrieval result contains audio content.
s3Uri (string) --
The S3 URI where this specific audio segment is stored in the multimodal storage destination.
transcription (string) --
The text transcription of the audio segment content.
byteContent (string) --
A data URI with base64-encoded content from the data source. The URI is in the following format: returned in the following format: data:image/jpeg;base64,${base64-encoded string}.
row (list) --
Specifies information about the rows with the cells to return in retrieval.
(dict) --
Contains information about a column with a cell to return in retrieval.
columnName (string) --
The name of the column.
columnValue (string) --
The value in the column.
type (string) --
The data type of the value.
text (string) --
The cited text from the data source.
type (string) --
The type of content in the retrieval result.
video (dict) --
Video segment information when the retrieval result contains video content.
s3Uri (string) --
The S3 URI where this specific video segment is stored in the multimodal storage destination.
summary (string) --
A text summary describing the content of the video segment.
location (dict) --
Contains information about the location of the data source.
confluenceLocation (dict) --
The Confluence data source location.
url (string) --
The Confluence host URL for the data source location.
customDocumentLocation (dict) --
Specifies the location of a document in a custom data source.
id (string) --
The ID of the document.
kendraDocumentLocation (dict) --
The location of a document in Amazon Kendra.
uri (string) --
The document's uri.
s3Location (dict) --
The S3 data source location.
uri (string) --
The S3 URI for the data source location.
salesforceLocation (dict) --
The Salesforce data source location.
url (string) --
The Salesforce host URL for the data source location.
sharePointLocation (dict) --
The SharePoint data source location.
url (string) --
The SharePoint site URL for the data source location.
sqlLocation (dict) --
Specifies information about the SQL query used to retrieve the result.
query (string) --
The SQL query used to retrieve the result.
type (string) --
The type of data source location.
webLocation (dict) --
The web URL/URLs data source location.
url (string) --
The web URL/URLs for the data source location.
metadata (dict) --
Contains metadata attributes and their values for the file in the data source. For more information, see Metadata and filtering.
(string) --
(:ref:`document<document>`) --
conflictException (dict) --
Error occurred because of a conflict while performing an operation.
message (string) --
dependencyFailedException (dict) --
The request failed due to a dependency error.
message (string) --
resourceName (string) --
The name of the dependency that caused the issue, such as Amazon Bedrock, Lambda, or STS.
guardrail (dict) --
A guardrail event.
action (string) --
The guardrail action.
internalServerException (dict) --
An internal server error occurred. Retry your request.
message (string) --
reason (string) --
The reason for the exception. If the reason is BEDROCK_MODEL_INVOCATION_SERVICE_UNAVAILABLE, the model invocation service is unavailable. Retry your request.
output (dict) --
An output event.
text (string) --
A text response.
resourceNotFoundException (dict) --
The specified resource ARN was not found. For troubleshooting this error, see ResourceNotFound in the Amazon Bedrock User Guide.
message (string) --
serviceQuotaExceededException (dict) --
Your request exceeds the service quota for your account. You can view your quotas at Viewing service quotas. You can resubmit your request later.
message (string) --
throttlingException (dict) --
Your request was denied due to exceeding the account quotas for Amazon Bedrock. For troubleshooting this error, see ThrottlingException in the Amazon Bedrock User Guide.
message (string) --
validationException (dict) --
The input fails to satisfy the constraints specified by Amazon Bedrock. For troubleshooting this error, see ValidationError in the Amazon Bedrock User Guide.
message (string) --