Google Cloud Ai Platform V1 Client - Class ImportRagFilesConfig (1.13.1)

Reference documentation and code samples for the Google Cloud Ai Platform V1 Client class ImportRagFilesConfig.

Config for importing RagFiles.

Generated from protobuf message google.cloud.aiplatform.v1.ImportRagFilesConfig

Namespace

Google \ Cloud \ AIPlatform \ V1

Methods

__construct

Constructor.

Parameters
Name Description
data array

Optional. Data for populating the Message object.
↳ gcs_source GcsSource

Google Cloud Storage location. Supports importing individual files as well as entire Google Cloud Storage directories. Sample formats: - gs://bucket_name/my_directory/object_name/my_file.txt - gs://bucket_name/my_directory
↳ google_drive_source GoogleDriveSource

Google Drive location. Supports importing individual files as well as Google Drive folders.
↳ slack_source SlackSource

Slack channels with their corresponding access tokens.
↳ jira_source JiraSource

Jira queries with their corresponding authentication.
↳ share_point_sources SharePointSources

SharePoint sources.
↳ partial_failure_gcs_sink GcsDestination

The Cloud Storage path to write partial failures to. Deprecated. Prefer to use import_result_gcs_sink.
↳ partial_failure_bigquery_sink BigQueryDestination

The BigQuery destination to write partial failures to. It should be a bigquery table resource name (e.g. "bq://projectId.bqDatasetId.bqTableId"). The dataset must exist. If the table does not exist, it will be created with the expected schema. If the table exists, the schema will be validated and data will be added to this existing table. Deprecated. Prefer to use import_result_bq_sink.
↳ rag_file_transformation_config RagFileTransformationConfig

Specifies the transformation config for RagFiles.
↳ max_embedding_requests_per_min int

Optional. The max number of queries per minute that this job is allowed to make to the embedding model specified on the corpus. This value is specific to this job and not shared across other import jobs. Consult the Quotas page on the project to set an appropriate value here. If unspecified, a default value of 1,000 QPM would be used.

getGcsSource

Google Cloud Storage location. Supports importing individual files as well as entire Google Cloud Storage directories. Sample formats:

  • gs://bucket_name/my_directory/object_name/my_file.txt
  • gs://bucket_name/my_directory
Returns
Type Description
GcsSource|null

hasGcsSource

setGcsSource

Google Cloud Storage location. Supports importing individual files as well as entire Google Cloud Storage directories. Sample formats:

  • gs://bucket_name/my_directory/object_name/my_file.txt
  • gs://bucket_name/my_directory
Parameter
Name Description
var GcsSource
Returns
Type Description
$this

getGoogleDriveSource

Google Drive location. Supports importing individual files as well as Google Drive folders.

Returns
Type Description
GoogleDriveSource|null

hasGoogleDriveSource

setGoogleDriveSource

Google Drive location. Supports importing individual files as well as Google Drive folders.

Parameter
Name Description
var GoogleDriveSource
Returns
Type Description
$this

getSlackSource

Slack channels with their corresponding access tokens.

Returns
Type Description
SlackSource|null

hasSlackSource

setSlackSource

Slack channels with their corresponding access tokens.

Parameter
Name Description
var SlackSource
Returns
Type Description
$this

getJiraSource

Jira queries with their corresponding authentication.

Returns
Type Description
JiraSource|null

hasJiraSource

setJiraSource

Jira queries with their corresponding authentication.

Parameter
Name Description
var JiraSource
Returns
Type Description
$this

getSharePointSources

SharePoint sources.

Returns
Type Description
SharePointSources|null

hasSharePointSources

setSharePointSources

SharePoint sources.

Parameter
Name Description
var SharePointSources
Returns
Type Description
$this

getPartialFailureGcsSink

The Cloud Storage path to write partial failures to.

Deprecated. Prefer to use import_result_gcs_sink.

Returns
Type Description
GcsDestination|null

hasPartialFailureGcsSink

setPartialFailureGcsSink

The Cloud Storage path to write partial failures to.

Deprecated. Prefer to use import_result_gcs_sink.

Parameter
Name Description
var GcsDestination
Returns
Type Description
$this

getPartialFailureBigquerySink

The BigQuery destination to write partial failures to. It should be a bigquery table resource name (e.g.

"bq://projectId.bqDatasetId.bqTableId"). The dataset must exist. If the table does not exist, it will be created with the expected schema. If the table exists, the schema will be validated and data will be added to this existing table. Deprecated. Prefer to use import_result_bq_sink.

Returns
Type Description
BigQueryDestination|null

hasPartialFailureBigquerySink

setPartialFailureBigquerySink

The BigQuery destination to write partial failures to. It should be a bigquery table resource name (e.g.

"bq://projectId.bqDatasetId.bqTableId"). The dataset must exist. If the table does not exist, it will be created with the expected schema. If the table exists, the schema will be validated and data will be added to this existing table. Deprecated. Prefer to use import_result_bq_sink.

Parameter
Name Description
var BigQueryDestination
Returns
Type Description
$this

getRagFileTransformationConfig

Specifies the transformation config for RagFiles.

Returns
Type Description
RagFileTransformationConfig|null

hasRagFileTransformationConfig

clearRagFileTransformationConfig

setRagFileTransformationConfig

Specifies the transformation config for RagFiles.

Parameter
Name Description
var RagFileTransformationConfig
Returns
Type Description
$this

getMaxEmbeddingRequestsPerMin

Optional. The max number of queries per minute that this job is allowed to make to the embedding model specified on the corpus. This value is specific to this job and not shared across other import jobs. Consult the Quotas page on the project to set an appropriate value here.

If unspecified, a default value of 1,000 QPM would be used.

Returns
Type Description
int

setMaxEmbeddingRequestsPerMin

Optional. The max number of queries per minute that this job is allowed to make to the embedding model specified on the corpus. This value is specific to this job and not shared across other import jobs. Consult the Quotas page on the project to set an appropriate value here.

If unspecified, a default value of 1,000 QPM would be used.

Parameter
Name Description
var int
Returns
Type Description
$this

getImportSource

Returns
Type Description
string

getPartialFailureSink

Returns
Type Description
string