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.

You need to provide your Google Vision API key to use this block.

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.	❌
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..	❌
api_key	str	Your Google Vision API key.	✅

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.

• inputs: Grid Visualization, Halo Visualization, Absolute Static Crop, Line Counter Visualization, Classification Label Visualization, OpenAI, LMM, Single-Label Classification Model, Image Preprocessing, Clip Comparison, Mask Visualization, Email Notification, Keypoint Detection Model, Ellipse Visualization, Google Gemini, Roboflow Dataset Upload, Keypoint Visualization, Instance Segmentation Model, Trace Visualization, LMM For Classification, Camera Focus, Roboflow Dataset Upload, Multi-Label Classification Model, VLM as Detector, Pixelate Visualization, Bounding Box Visualization, Florence-2 Model, Webhook Sink, Polygon Visualization, Google Vision OCR, Depth Estimation, Polygon Zone Visualization, Stitch OCR Detections, Perspective Correction, Stitch Images, Anthropic Claude, Object Detection Model, OCR Model, CSV Formatter, Stability AI Image Generation, Image Convert Grayscale, Model Comparison Visualization, Image Slicer, Llama 3.2 Vision, CogVLM, Background Color Visualization, Dynamic Crop, Blur Visualization, SIFT, Triangle Visualization, Reference Path Visualization, Model Monitoring Inference Aggregator, Corner Visualization, Image Contours, Local File Sink, Florence-2 Model, Relative Static Crop, Label Visualization, OpenAI, VLM as Classifier, Image Slicer, Dot Visualization, Slack Notification, Roboflow Custom Metadata, Circle Visualization, Image Threshold, Twilio SMS Notification, Image Blur, SIFT Comparison, Stability AI Inpainting, Crop Visualization, Color Visualization, Camera Calibration
• outputs: Line Counter Visualization, Halo Visualization, OpenAI, Image Preprocessing, Size Measurement, Mask Visualization, Email Notification, Ellipse Visualization, Keypoint Visualization, Instance Segmentation Model, Trace Visualization, LMM For Classification, Detections Consensus, Time in Zone, Line Counter, Byte Tracker, Pixelate Visualization, Byte Tracker, Florence-2 Model, Webhook Sink, Velocity, Google Vision OCR, Detection Offset, Anthropic Claude, Segment Anything 2 Model, Line Counter, Stitch OCR Detections, Detections Classes Replacement, YOLO-World Model, Overlap Filter, CogVLM, Model Monitoring Inference Aggregator, Triangle Visualization, Reference Path Visualization, Local File Sink, Florence-2 Model, OpenAI, Cache Set, Byte Tracker, Twilio SMS Notification, Path Deviation, Detections Stabilizer, SIFT Comparison, Stability AI Inpainting, Cache Get, Color Visualization, Instance Segmentation Model, CLIP Embedding Model, Classification Label Visualization, LMM, Clip Comparison, Detections Stitch, Google Gemini, Roboflow Dataset Upload, Path Deviation, Roboflow Dataset Upload, Bounding Box Visualization, Detections Transformation, Polygon Visualization, Pixel Color Count, Polygon Zone Visualization, Detections Merge, Perspective Correction, Detections Filter, Stability AI Image Generation, Model Comparison Visualization, Llama 3.2 Vision, Background Color Visualization, Dynamic Crop, Blur Visualization, Corner Visualization, Label Visualization, Time in Zone, Dot Visualization, Slack Notification, Distance Measurement, Roboflow Custom Metadata, Circle Visualization, Image Threshold, Image Blur, Crop Visualization

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, 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>",
    "language_hints": [
        "en",
        "fr"
    ],
    "api_key": "xxx-xxx"
}