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

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, classification_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
}