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