gcloud alpha ml vision detect-text-pdf

NAME
gcloud alpha ml vision detect-text-pdf - detect and transcribe text from PDF files stored in Google Cloud Storage
SYNOPSIS
gcloud alpha ml vision detect-text-pdfINPUT_FILEOUTPUT_PATH[--batch-size=BATCH_SIZE][--model-version=MODEL_VERSION; default="builtin/stable"][GCLOUD_WIDE_FLAG …]
DESCRIPTION
(ALPHA) Detect and transcribe text from PDF files stored in GoogleCloud Storage.

The Vision API accepts PDF files up to 2000 pages. Larger files will return anerror.

EXAMPLES
To detect text for input PDF file 'gs://my_bucket/input_file' and store outputin 'gs://my_bucket/out_put_prefix':
gcloudalphamlvisiondetect-text-pdfgs://my_bucket/input_filegs://my_bucket/out_put_prefix
POSITIONAL ARGUMENTS
INPUT_FILE
Google Cloud Storage location to read the input from. It must be in Google CloudStorage format (gs://bucket/object)
OUTPUT_PATH
Google Cloud Storage location to store the output file. It must be in GoogleCloud Storage format (gs://bucket/object)
FLAGS
--batch-size=BATCH_SIZE
Maximum number of response protos to put into each output JSON file on GoogleCloud Storage. The valid range is [1, 100]. If not specified, the default valueis 20.
--model-version=MODEL_VERSION; default="builtin/stable"
Model version to use for the feature.MODEL_VERSION mustbe one of:builtin/latest,builtin/stable.
GCLOUD WIDE FLAGS
These flags are available to all commands:--access-token-file,--account,--billing-project,--configuration,--flags-file,--flatten,--format,--help,--impersonate-service-account,--log-http,--project,--quiet,--trace-token,--user-output-enabled,--verbosity.

Run$gcloud help for details.

API REFERENCE
This command uses thevision/v1 API. The full documentation forthis API can be found at:https://cloud.google.com/vision/
NOTES
This command is currently in alpha and might change without notice. If thiscommand fails with API permission errors despite specifying the correct project,you might be trying to access an API with an invitation-only early accessallowlist. These variants are also available:
gcloudmlvisiondetect-text-pdf
gcloudbetamlvisiondetect-text-pdf

Except as otherwise noted, the content of this page is licensed under theCreative Commons Attribution 4.0 License, and code samples are licensed under theApache 2.0 License. For details, see theGoogle Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-05-07 UTC.