Skip to content

Submits content directly for ingestion to generate long-term memory records in a AgentCore Memory resource

Description

Submits content directly for ingestion to generate long-term memory records in a AgentCore Memory resource.

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

Usage

bedrockagentcore_ingest_data(memoryId, source, contentTimestamp,
  actorId, sessionId, extractionConfig, metadata, clientToken)

Arguments

  • memoryId

    [required] The identifier of the AgentCore Memory resource to ingest content into.

  • source

    [required] The content to ingest. Only inline content is supported.

  • contentTimestamp

    [required] The timestamp of when the content occurred.

  • actorId

    [required] The identifier of the actor associated with this content. An actor represents an entity that participates in sessions and generates content.

  • sessionId

    The identifier of the session that the content belongs to. If not provided, a session identifier is generated and returned in the response.

  • extractionConfig

    The extraction configuration for long-term memory records. Use this parameter to specify namespace variable keys and their values for namespace substitution during extraction.

  • metadata

    The key-value metadata to attach to the content.

  • clientToken

    A unique, case-sensitive identifier to ensure that the operation completes no more than one time. If this token matches a previous request, AgentCore ignores the request, but does not return an error.

Value

A list with the following syntax:

list(
  sessionId = "string"
)

Request syntax

svc$ingest_data(
  memoryId = "string",
  source = list(
    inline = list(
      payload = list(
        list(
          conversational = list(
            content = list(
              text = "string"
            ),
            role = "ASSISTANT"|"USER"|"TOOL"|"OTHER"
          ),
          json = list(
            content = list()
          )
        )
      )
    )
  ),
  contentTimestamp = as.POSIXct(
    "2015-01-01"
  ),
  actorId = "string",
  sessionId = "string",
  extractionConfig = list(
    namespaceVariables = list(
      "string"
    )
  ),
  metadata = list(
    list(
      stringValue = "string"
    )
  ),
  clientToken = "string"
)