IngestionJob
Contains details about a data ingestion job. Data sources are ingested into a knowledge base so that Large Language Models (LLMs) can use your data.
This data type is used in the following API operations:
Contents
- dataSourceId
-
The unique identifier of the data source for the data ingestion job.
Type: String
Pattern:
[0-9a-zA-Z]{10}Required: Yes
- ingestionJobId
-
The unique identifier of the data ingestion job.
Type: String
Pattern:
[0-9a-zA-Z]{10}Required: Yes
- knowledgeBaseId
-
The unique identifier of the knowledge for the data ingestion job.
Type: String
Pattern:
[0-9a-zA-Z]{10}Required: Yes
- startedAt
-
The time the data ingestion job started.
If you stop a data ingestion job, the
startedAttime is the time the job was started before the job was stopped.Type: Timestamp
Required: Yes
- status
-
The status of the data ingestion job.
Type: String
Valid Values:
STARTING | IN_PROGRESS | COMPLETE | FAILED | STOPPING | STOPPEDRequired: Yes
- updatedAt
-
The time the data ingestion job was last updated.
If you stop a data ingestion job, the
updatedAttime is the time the job was stopped.Type: Timestamp
Required: Yes
- description
-
The description of the data ingestion job.
Type: String
Length Constraints: Minimum length of 1. Maximum length of 200.
Required: No
- failureReasons
-
A list of reasons that the data ingestion job failed.
Type: Array of strings
Array Members: Minimum number of 0 items. Maximum number of 2048 items.
Length Constraints: Minimum length of 0. Maximum length of 2048.
Required: No
- statistics
-
Contains statistics about the data ingestion job.
Type: IngestionJobStatistics object
Required: No
- textReadyAt
-
The time at which all text content in the data ingestion job finished extraction and became available to query.
This time isn't returned until text extraction is complete for all the documents in the job.
Type: Timestamp
Required: No
See Also
For more information about using this API in one of the language-specific AWS SDKs, see the following: