Roboflow Custom Metadata

Class: RoboflowCustomMetadataBlockV1

Source: inference.core.workflows.core_steps.sinks.roboflow.custom_metadata.v1.RoboflowCustomMetadataBlockV1

Block allows users to add custom metadata to each inference result in Roboflow Model Monitoring dashboard.

This is useful for adding information specific to your use case. For example, if you want to be able to filter inferences by a specific label such as location, you can attach those labels to each inference with this block.

For more information on Model Monitoring at Roboflow, see https://docs.roboflow.com/deploy/model-monitoring.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
field_value	str	This is the name of the metadata field you are creating.	✅
field_name	str	Name of the field to be updated..	❌
fire_and_forget	bool	Boolean flag to run the block asynchronously (True) for faster workflows or synchronously (False) for debugging and error handling..	✅

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 Roboflow Custom Metadata in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Roboflow Custom Metadata in version v1 has.

Bindings

• input

  • predictions (Union[keypoint_detection_prediction, instance_segmentation_prediction, object_detection_prediction, classification_prediction]): Model predictions to attach custom metadata to..
  • field_value (string): This is the name of the metadata field you are creating.
  • fire_and_forget (boolean): Boolean flag to run the block asynchronously (True) for faster workflows or synchronously (False) for debugging and error handling..

• output

  • error_status (boolean): Boolean flag.
  • message (string): String value.

Example JSON definition of step Roboflow Custom Metadata in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/roboflow_custom_metadata@v1",
    "predictions": "$steps.my_step.predictions",
    "field_value": "toronto",
    "field_name": "The name of the value of the field",
    "fire_and_forget": true
}