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: Image Contours, Florence-2 Model, CogVLM, Image Threshold, Trace Visualization, Slack Notification, Clip Comparison, Label Visualization, SIFT, Roboflow Custom Metadata, Image Blur, Single-Label Classification Model, Camera Calibration, Stability AI Image Generation, Corner Visualization, Keypoint Visualization, Line Counter Visualization, OCR Model, Model Comparison Visualization, Stitch Images, Instance Segmentation Model, Pixelate Visualization, CSV Formatter, Florence-2 Model, OpenAI, Google Vision OCR, Twilio SMS Notification, Classification Label Visualization, SIFT Comparison, Model Monitoring Inference Aggregator, Halo Visualization, Background Color Visualization, Stability AI Inpainting, Multi-Label Classification Model, Anthropic Claude, QR Code Generator, VLM as Classifier, Dynamic Crop, Polygon Visualization, Object Detection Model, Crop Visualization, Webhook Sink, Ellipse Visualization, Perspective Correction, Email Notification, Triangle Visualization, VLM as Detector, Image Convert Grayscale, Image Slicer, Grid Visualization, Reference Path Visualization, Circle Visualization, Blur Visualization, Local File Sink, Camera Focus, Depth Estimation, OpenAI, Color Visualization, Dot Visualization, Roboflow Dataset Upload, Relative Static Crop, Icon Visualization, LMM, Image Preprocessing, Roboflow Dataset Upload, OpenAI, Stitch OCR Detections, Keypoint Detection Model, LMM For Classification, Bounding Box Visualization, Mask Visualization, Llama 3.2 Vision, Image Slicer, Google Gemini, Stability AI Outpainting, Polygon Zone Visualization, Absolute Static Crop
• outputs: Florence-2 Model, CogVLM, Time in Zone, Trace Visualization, Slack Notification, Image Threshold, Clip Comparison, Label Visualization, Roboflow Custom Metadata, Image Blur, Stability AI Image Generation, Keypoint Visualization, Corner Visualization, Overlap Filter, Line Counter Visualization, Size Measurement, Detection Offset, Velocity, Byte Tracker, Model Comparison Visualization, Instance Segmentation Model, Pixelate Visualization, Cache Set, Time in Zone, PTZ Tracking (ONVIF).md), Florence-2 Model, OpenAI, CLIP Embedding Model, Google Vision OCR, Twilio SMS Notification, Classification Label Visualization, Perception Encoder Embedding Model, Model Monitoring Inference Aggregator, SIFT Comparison, Halo Visualization, Background Color Visualization, Stability AI Inpainting, Anthropic Claude, Time in Zone, QR Code Generator, Dynamic Crop, Detections Stitch, Path Deviation, Polygon Visualization, Byte Tracker, Crop Visualization, Webhook Sink, Ellipse Visualization, Perspective Correction, Detections Classes Replacement, Email Notification, Triangle Visualization, Distance Measurement, Cache Get, Instance Segmentation Model, Moondream2, Detections Filter, Reference Path Visualization, Circle Visualization, Blur Visualization, Path Deviation, Line Counter, Local File Sink, Detections Transformation, Segment Anything 2 Model, Line Counter, OpenAI, YOLO-World Model, Color Visualization, Dot Visualization, Roboflow Dataset Upload, Detections Merge, Icon Visualization, LMM, Image Preprocessing, Roboflow Dataset Upload, Detections Consensus, OpenAI, Detections Stabilizer, Stitch OCR Detections, LMM For Classification, Bounding Box Visualization, Mask Visualization, Pixel Color Count, Llama 3.2 Vision, Google Gemini, Stability AI Outpainting, Polygon Zone Visualization, Byte Tracker

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"
}