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

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, 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
}