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

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
}