Buffer

Class: BufferBlockV1

Source: inference.core.workflows.core_steps.fusion.buffer.v1.BufferBlockV1

Returns an array of the last length values passed to it. The newest elements are added to the beginning of the array.

Useful for keeping a sliding window of images or detections for later processing, visualization, or comparison.

Type identifier

Use the following identifier in step "type" field: roboflow_core/buffer@v1to add the block as as step in your workflow.

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
length	int	The number of elements to keep in the buffer. Older elements will be removed..	❌
pad	bool	If True, the end of the buffer will be padded with None values so its size is always exactly length..	❌

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 Buffer in version v1.

• inputs: PTZ Tracking (ONVIF).md), Perception Encoder Embedding Model, SIFT, Cache Set, Dimension Collapse, Detections Stitch, Color Visualization, Perspective Correction, Path Deviation, Model Monitoring Inference Aggregator, Image Slicer, Model Comparison Visualization, Clip Comparison, Stitch Images, Dynamic Crop, Moondream2, Webhook Sink, Pixelate Visualization, Llama 3.2 Vision, Camera Calibration, Line Counter, Reference Path Visualization, Image Blur, Time in Zone, Blur Visualization, Environment Secrets Store, Ellipse Visualization, Trace Visualization, Corner Visualization, Polygon Zone Visualization, Single-Label Classification Model, Delta Filter, Email Notification, Object Detection Model, Byte Tracker, Dot Visualization, Label Visualization, Cosine Similarity, Detections Filter, Stitch OCR Detections, Image Preprocessing, SIFT Comparison, JSON Parser, Mask Visualization, Data Aggregator, Dominant Color, Florence-2 Model, Roboflow Dataset Upload, Byte Tracker, First Non Empty Or Default, Rate Limiter, Instance Segmentation Model, Background Color Visualization, Line Counter, Keypoint Visualization, Property Definition, Multi-Label Classification Model, VLM as Detector, YOLO-World Model, OpenAI, VLM as Detector, Bounding Rectangle, Keypoint Detection Model, Circle Visualization, Roboflow Dataset Upload, Gaze Detection, Roboflow Custom Metadata, Depth Estimation, Florence-2 Model, Buffer, Single-Label Classification Model, Template Matching, Dynamic Zone, Grid Visualization, Instance Segmentation Model, CSV Formatter, Detections Consensus, Overlap Filter, Object Detection Model, Identify Outliers, OpenAI, Keypoint Detection Model, Image Contours, Continue If, Byte Tracker, SIFT Comparison, Local File Sink, Cache Get, Expression, CLIP Embedding Model, OCR Model, Velocity, SmolVLM2, Camera Focus, Detections Classes Replacement, Google Gemini, OpenAI, Triangle Visualization, Stability AI Inpainting, Detections Transformation, Classification Label Visualization, Barcode Detection, Bounding Box Visualization, Distance Measurement, Detections Merge, Detections Stabilizer, CogVLM, Image Convert Grayscale, Halo Visualization, LMM, Polygon Visualization, Absolute Static Crop, Slack Notification, Stability AI Outpainting, Crop Visualization, Google Vision OCR, Stability AI Image Generation, Detection Offset, Image Threshold, Pixel Color Count, VLM as Classifier, Identify Changes, Time in Zone, Twilio SMS Notification, Segment Anything 2 Model, Clip Comparison, QR Code Detection, Line Counter Visualization, Path Deviation, VLM as Classifier, Anthropic Claude, LMM For Classification, Multi-Label Classification Model, Image Slicer, Qwen2.5-VL, Size Measurement, Relative Static Crop
• outputs: YOLO-World Model, VLM as Detector, Polygon Zone Visualization, Google Gemini, Corner Visualization, Keypoint Detection Model, OpenAI, Trace Visualization, Roboflow Dataset Upload, Circle Visualization, Triangle Visualization, Classification Label Visualization, Bounding Box Visualization, Florence-2 Model, Cache Set, Buffer, Halo Visualization, Grid Visualization, Email Notification, Polygon Visualization, Object Detection Model, Instance Segmentation Model, Label Visualization, Color Visualization, Dot Visualization, Detections Consensus, Crop Visualization, Object Detection Model, Perspective Correction, Path Deviation, OpenAI, Keypoint Detection Model, Clip Comparison, VLM as Classifier, Mask Visualization, Time in Zone, Webhook Sink, Florence-2 Model, Clip Comparison, Roboflow Dataset Upload, Llama 3.2 Vision, Line Counter, Reference Path Visualization, Time in Zone, Line Counter Visualization, Path Deviation, VLM as Classifier, Instance Segmentation Model, Anthropic Claude, LMM For Classification, Line Counter, Keypoint Visualization, Ellipse Visualization, Size Measurement, VLM as Detector

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Buffer in version v1 has.

Bindings

• input

  • data (Union[list_of_values, *, image]): Reference to step outputs at depth level n to be concatenated and moved into level n-1..

• output

  • output (list_of_values): List of values of any type.

Example JSON definition of step Buffer in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/buffer@v1",
    "data": "$steps.visualization",
    "length": 5,
    "pad": true
}