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

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[instance_segmentation_prediction, object_detection_prediction, keypoint_detection_prediction, classification_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
}