Start Ingestion Job

bedrockagent_start_ingestion_job

R Documentation

Begins a data ingestion job

Description

Begins a data ingestion job. Data sources are ingested into your knowledge base so that Large Language Models (LLMs) can use your data.

Usage

bedrockagent_start_ingestion_job(clientToken, dataSourceId, description,
  knowledgeBaseId)

Arguments

clientToken

A unique, case-sensitive identifier to ensure that the API request completes no more than one time. If this token matches a previous request, Amazon Bedrock ignores the request, but does not return an error. For more information, see Ensuring idempotency.

dataSourceId

[required] The unique identifier of the data source you want to ingest into your knowledge base.

description

A description of the data ingestion job.

knowledgeBaseId

[required] The unique identifier of the knowledge base for the data ingestion job.

Value

A list with the following syntax:

list(
  ingestionJob = list(
    dataSourceId = "string",
    description = "string",
    failureReasons = list(
      "string"
    ),
    ingestionJobId = "string",
    knowledgeBaseId = "string",
    startedAt = as.POSIXct(
      "2015-01-01"
    ),
    statistics = list(
      numberOfDocumentsDeleted = 123,
      numberOfDocumentsFailed = 123,
      numberOfDocumentsScanned = 123,
      numberOfMetadataDocumentsModified = 123,
      numberOfMetadataDocumentsScanned = 123,
      numberOfModifiedDocumentsIndexed = 123,
      numberOfNewDocumentsIndexed = 123
    ),
    status = "STARTING"|"IN_PROGRESS"|"COMPLETE"|"FAILED"|"STOPPING"|"STOPPED",
    updatedAt = as.POSIXct(
      "2015-01-01"
    )
  )
)

Request syntax

svc$start_ingestion_job(
  clientToken = "string",
  dataSourceId = "string",
  description = "string",
  knowledgeBaseId = "string"
)