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

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[classification_prediction, object_detection_prediction, instance_segmentation_prediction, keypoint_detection_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
}