Amazon Bedrock AgentCore

Starts a memory extraction job that processes events that failed extraction previously in an AgentCore Memory resource and produces structured memory records. When earlier extraction attempts have left events unprocessed, this job will pick up and extract those as well.

To use this operation, you must have the bedrock-agentcore:StartMemoryExtractionJob permission.

See also: AWS API Documentation

Request Syntax

client.start_memory_extraction_job(
    memoryId='string',
    extractionJob={
        'jobId': 'string'
    },
    clientToken='string'
)

type memoryId:

string

param memoryId:

[REQUIRED]

The unique identifier of the memory for which to start extraction jobs.

type extractionJob:

dict

param extractionJob:

[REQUIRED]

Extraction job to start in this operation.

• jobId (string) -- [REQUIRED]

  The unique identifier of the extraction job.

type clientToken:

string

param clientToken:

A unique, case-sensitive identifier to ensure idempotent processing of the request.

This field is autopopulated if not provided.

rtype:

dict

returns:

Response Syntax

{
    'jobId': 'string'
}

Response Structure

• (dict) --

  • jobId (string) --

    Extraction Job ID that was attempted to start.

Lists all long-term memory extraction jobs that are eligible to be started with optional filtering.

To use this operation, you must have the bedrock-agentcore:ListMemoryExtractionJobs permission.

See also: AWS API Documentation

Request Syntax

client.list_memory_extraction_jobs(
    memoryId='string',
    maxResults=123,
    filter={
        'strategyId': 'string',
        'sessionId': 'string',
        'actorId': 'string',
        'status': 'FAILED'
    },
    nextToken='string'
)

type memoryId:

string

param memoryId:

[REQUIRED]

The unique identifier of the memory to list extraction jobs for.

type maxResults:

integer

param maxResults:

The maximum number of results to return in a single call. The default value is 20.

type filter:

dict

param filter:

Filter criteria to apply when listing extraction jobs.

• strategyId (string) --

  The memory strategy identifier to filter extraction jobs by. If specified, only extraction jobs with this strategy ID are returned.

• sessionId (string) --

  The unique identifier of the session. If specified, only extraction jobs with this session ID are returned.

• actorId (string) --

  The identifier of the actor. If specified, only extraction jobs with this actor ID are returned.

• status (string) --

  The status of the extraction job. If specified, only extraction jobs with this status are returned.

type nextToken:

string

param nextToken:

The token for the next set of results. Use the value returned in the previous response in the next request to retrieve the next set of results.

rtype:

dict

returns:

Response Syntax

{
    'jobs': [
        {
            'jobID': 'string',
            'messages': {
                'messagesList': [
                    {
                        'eventId': 'string',
                        'messageIndex': 123
                    },
                ]
            },
            'status': 'FAILED',
            'failureReason': 'string',
            'strategyId': 'string',
            'sessionId': 'string',
            'actorId': 'string'
        },
    ],
    'nextToken': 'string'
}

Response Structure

• (dict) --

  • jobs (list) --

    List of extraction job metadata matching the specified criteria.

    • (dict) --

      Metadata information associated with this extraction job.

      • jobID (string) --

        The unique identifier for the extraction job.

      • messages (dict) --

        The messages associated with the extraction job.

        • messagesList (list) --

          The list of messages that compose this extraction job.

          • (dict) --

            Metadata information associated with this message.

            • eventId (string) --

              The identifier of the event associated with this message.

            • messageIndex (integer) --

              The position of this message within that event’s ordered list of messages.

      • status (string) --

        The current status of the extraction job.

      • failureReason (string) --

        The cause of failure, if the job did not complete successfully.

      • strategyId (string) --

        The identifier of the memory strategy for this extraction job.

      • sessionId (string) --

        The identifier of the session for this extraction job.

      • actorId (string) --

        The identifier of the actor for this extraction job.

  • nextToken (string) --

    Token to retrieve the next page of results, if available.