Google Vision OCR¶

Class: GoogleVisionOCRBlockV1

Source: inference.core.workflows.core_steps.models.foundation.google_vision_ocr.v1.GoogleVisionOCRBlockV1

Detect text in images using Google Vision OCR.

Supported types of text detection:

text_detection: optimized for areas of text within a larger image.
ocr_text_detection: optimized for dense text documents.

Provide your Google Vision API key or set the value to rf_key:account (or rf_key:user:<id>) to proxy requests through Roboflow's API.

Type identifier¶

Use the following identifier in step "type" field: roboflow_core/google_vision_ocr@v1to add the block as as step in your workflow.

Properties¶

Name	Type	Description	Refs
`name`	`str`	Enter a unique identifier for this step..	❌
`ocr_type`	`str`	Type of OCR to use.	❌
`api_key`	`str`	Your Google Vision API key.	✅
`language_hints`	`List[str]`	Optional list of language codes to pass to the OCR API. If not provided, the API will attempt to detect the language automatically.If provided, language codes must be supported by the OCR API, visit https://cloud.google.com/vision/docs/languages for list of supported language codes..	❌

The Refs column marks possibility to parametrise the property with dynamic values available in workflow runtime. See Bindings for more info.

Available Connections¶

Compatible Blocks

Check what blocks you can connect to Google Vision OCR in version v1.

Input and Output Bindings¶

The available connections depend on its binding kinds. Check what binding kinds Google Vision OCR in version v1 has.

Bindings

input
- image (image): Image to run OCR.
- api_key (Union[string, ROBOFLOW_MANAGED_KEY, secret]): Your Google Vision API key.
output
- text (string): String value.
- language (string): String value.
- predictions (object_detection_prediction): Prediction with detected bounding boxes in form of sv.Detections(...) object.

Example JSON definition of step Google Vision OCR in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/google_vision_ocr@v1",
    "image": "$inputs.image",
    "ocr_type": "<block_does_not_provide_example>",
    "api_key": "xxx-xxx",
    "language_hints": [
        "en",
        "fr"
    ]
}