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

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[secret, string]): 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-2.0-flash-exp",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}