Anthropic Claude

Class: AnthropicClaudeBlockV1

Source: inference.core.workflows.core_steps.models.foundation.anthropic_claude.v1.AnthropicClaudeBlockV1

Ask a question to Anthropic Claude 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 Anthropic API key to use the Claude model.

Type identifier

Use the following identifier in step "type" field: roboflow_core/anthropic_claude@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 Claude 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 Anthropic 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_image_size	int	Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.	✅
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 Anthropic 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 Anthropic Claude in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Anthropic Claude in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the Claude model.
  • classes (list_of_values): List of classes to be used.
  • api_key (Union[secret, string]): Your Anthropic 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..
  • max_image_size (integer): Maximum size of the image - if input has larger side, it will be downscaled, keeping aspect ratio.

• 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 Anthropic Claude in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/anthropic_claude@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": "claude-3-5-sonnet",
    "max_tokens": "<block_does_not_provide_example>",
    "temperature": "<block_does_not_provide_example>",
    "max_image_size": "<block_does_not_provide_example>",
    "max_concurrent_requests": "<block_does_not_provide_example>"
}