Google Gemini

Class: GoogleGeminiBlockV1

Source: inference.core.workflows.core_steps.models.foundation.google_gemini.v1.GoogleGeminiBlockV1

Ask a question to Google's Gemini model with vision capabilities.

You can specify arbitrary text prompts or predefined ones, the block supports the following types of prompt:

• Open Prompt (unconstrained) - Use any prompt to generate a raw response

• Text Recognition (OCR) (ocr) - Model recognizes text in the image

• Visual Question Answering (visual-question-answering) - Model answers the question you submit in the prompt

• Captioning (short) (caption) - Model provides a short description of the image

• Captioning (detailed-caption) - Model provides a long description of the image

• Single-Label Classification (classification) - Model classifies the image content as one of the provided classes

• Multi-Label Classification (multi-label-classification) - Model classifies the image content as one or more of the provided classes

• Unprompted Object Detection (object-detection) - Model detects and returns the bounding boxes for prominent objects in the image

• Structured Output Generation (structured-answering) - Model returns a JSON response with the specified fields

You need to provide your Google AI API key to use the Gemini model.

WARNING!

This block makes use of /v1beta API of Google Gemini model - the implementation may change in the future, without guarantee of backward compatibility.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
task_type	str	Task type to be performed by model. Value determines required parameters and output response..	❌
prompt	str	Text prompt to the Gemini model.	✅
output_structure	Dict[str, str]	Dictionary with structure of expected JSON response.	❌
classes	List[str]	List of classes to be used.	✅
api_key	str	Your Google AI API key.	✅
model_version	str	Model to be used.	✅
max_tokens	int	Maximum number of tokens the model can generate in it's response..	❌
temperature	float	Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..	✅
max_concurrent_requests	int	Number of concurrent requests that can be executed by block when batch of input images provided. If not given - block defaults to value configured globally in Workflows Execution Engine. Please restrict if you hit Google Gemini API limits..	❌

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 Gemini in version v1.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Gemini model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[string, secret]): Your Google AI API key.
  • model_version (string): Model to be used.
  • temperature (float): Temperature to sample from the model - value in range 0.0-2.0, the higher - the more random / "creative" the generations are..

• output

  • output (Union[string, language_model_output]): String value if string or LLM / VLM output if language_model_output.
  • classes (list_of_values): List of values of any type.

Example JSON definition of step Google Gemini in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/google_gemini@v1",
    "images": "$inputs.image",
    "task_type": "<block_does_not_provide_example>",
    "prompt": "my prompt",
    "output_structure": {
        "my_key": "description"
    },
    "classes": [
        "class-a",
        "class-b"
    ],
    "api_key": "xxx-xxx",
    "model_version": "gemini-2.5-pro",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}