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, Dynamic Zone, VLM as Classifier, Detections Transformation, Model Monitoring Inference Aggregator, Identify Outliers, Detections Classes Replacement, Object Detection Model, Line Counter, Local File Sink, Keypoint Detection Model, Email Notification, Time in Zone, Anthropic Claude, Google Gemini, Florence-2 Model, Multi-Label Classification Model, Segment Anything 2 Model, OCR Model, Byte Tracker, Time in Zone, Roboflow Custom Metadata, Florence-2 Model, LMM For Classification, Identify Changes, Single-Label Classification Model, Overlap Filter, Detection Offset, Perspective Correction, Google Vision OCR, EasyOCR, Llama 3.2 Vision, Detections Stabilizer, SAM 3, Slack Notification, Velocity, Clip Comparison, Stitch OCR Detections, Byte Tracker, OpenAI, Roboflow Dataset Upload, Path Deviation, Template Matching, CogVLM, Email Notification, VLM as Detector, Instance Segmentation Model, Byte Tracker, OpenAI, Detections Stitch, Keypoint Detection Model, Object Detection Model, YOLO-World Model, Detections Merge, Gaze Detection, Moondream2, Multi-Label Classification Model, Seg Preview, Path Deviation, Roboflow Dataset Upload, JSON Parser, Instance Segmentation Model, Detections Filter, OpenAI, VLM as Classifier, Bounding Rectangle, CSV Formatter, Time in Zone, Detections Combine, Twilio SMS Notification, SIFT Comparison, VLM as Detector, Webhook Sink, Detections Consensus, Single-Label Classification Model, PTZ Tracking (ONVIF).md), Dynamic Crop, SIFT Comparison
• outputs: Background Color Visualization, Size Measurement, Corner Visualization, Mask Visualization, CLIP Embedding Model, Line Counter, Local File Sink, Model Comparison Visualization, Email Notification, Time in Zone, Florence-2 Model, Multi-Label Classification Model, Ellipse Visualization, Label Visualization, LMM For Classification, Blur Visualization, Dot Visualization, Google Vision OCR, Llama 3.2 Vision, Line Counter, Slack Notification, Image Blur, Stitch OCR Detections, Stability AI Outpainting, Halo Visualization, Stability AI Inpainting, CogVLM, Classification Label Visualization, Instance Segmentation Model, Polygon Zone Visualization, Perception Encoder Embedding Model, Detections Stitch, Crop Visualization, Cache Get, YOLO-World Model, Multi-Label Classification Model, Icon Visualization, Seg Preview, Color Visualization, Path Deviation, Circle Visualization, Time in Zone, Dynamic Crop, Single-Label Classification Model, Line Counter Visualization, PTZ Tracking (ONVIF).md), Image Preprocessing, Trace Visualization, SIFT Comparison, LMM, Dynamic Zone, Model Monitoring Inference Aggregator, Detections Classes Replacement, Object Detection Model, Keypoint Detection Model, Pixelate Visualization, Anthropic Claude, Google Gemini, Triangle Visualization, Segment Anything 2 Model, QR Code Generator, Time in Zone, Pixel Color Count, Roboflow Custom Metadata, Cache Set, Florence-2 Model, Single-Label Classification Model, Stability AI Image Generation, SAM 3, Morphological Transformation, Clip Comparison, Image Threshold, Polygon Visualization, OpenAI, Roboflow Dataset Upload, Path Deviation, Template Matching, Distance Measurement, Email Notification, Bounding Box Visualization, OpenAI, Keypoint Detection Model, Object Detection Model, Gaze Detection, Moondream2, Roboflow Dataset Upload, Keypoint Visualization, Contrast Equalization, Instance Segmentation Model, OpenAI, Reference Path Visualization, Twilio SMS Notification, Webhook Sink, Detections Consensus, Perspective Correction

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[classification_prediction, instance_segmentation_prediction, keypoint_detection_prediction, object_detection_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
}