Model Monitoring Inference Aggregator

Class: ModelMonitoringInferenceAggregatorBlockV1

Source: inference.core.workflows.core_steps.sinks.roboflow.model_monitoring_inference_aggregator.v1.ModelMonitoringInferenceAggregatorBlockV1

This block 📊 transforms inference data reporting to a whole new level by periodically aggregating and sending a curated sample of predictions to Roboflow Model Monitoring.

✨ Key Features

• Effortless Aggregation: Collects and organizes predictions in-memory, ensuring only the most relevant and confident predictions are reported.

• Customizable Reporting Intervals: Choose how frequently (in seconds) data should be sent—ensuring optimal balance between granularity and resource efficiency.

• Debug-Friendly Mode: Fine-tune operations by enabling or disabling asynchronous background execution.

🔍 Why Use This Block?

This block is a game-changer for projects relying on video processing in Workflows. With its aggregation process, it identifies the most confident predictions across classes and sends them at regular intervals in small messages to Roboflow backend - ensuring that video processing performance is impacted to the least extent.

Perfect for:

• Monitoring production line performance in real-time 🏭.

• Debugging and validating your model’s performance over time ⏱️.

• Providing actionable insights from inference workflows with minimal overhead 🔧.

🚨 Limitations

• The block is should not be relied on when running Workflow in inference server or via HTTP request to Roboflow hosted platform, as the internal state is not persisted in a memory that would be accessible for all requests to the server, causing aggregation to only have a scope of single request. We will solve that problem in future releases if proven to be serious limitation for clients.

• This block do not have ability to separate aggregations for multiple videos processed by InferencePipeline - effectively aggregating data for all video feeds connected to single process running InferencePipeline.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
frequency	int	Frequency of reporting (in seconds). For example, if 5 is provided, the block will report an aggregated sample of predictions every 5 seconds..	✅
unique_aggregator_key	str	Unique key used internally to track the session of inference results reporting. Must be unique for each step in your Workflow..	❌
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 Model Monitoring Inference Aggregator in version v1.

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

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Model Monitoring Inference Aggregator in version v1 has.

Bindings

• input

  • predictions (Union[object_detection_prediction, instance_segmentation_prediction, keypoint_detection_prediction, classification_prediction]): Model predictions to report to Roboflow Model Monitoring..
  • model_id (roboflow_model_id): Model ID to report to Roboflow Model Monitoring..
  • frequency (string): Frequency of reporting (in seconds). For example, if 5 is provided, the block will report an aggregated sample of predictions every 5 seconds..
  • 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 Model Monitoring Inference Aggregator in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/model_monitoring_inference_aggregator@v1",
    "predictions": "$steps.my_step.predictions",
    "model_id": "my_project/3",
    "frequency": "3",
    "unique_aggregator_key": "session-1v73kdhfse",
    "fire_and_forget": true
}