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

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, classification_prediction, keypoint_detection_prediction, instance_segmentation_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
}