Cache Get

Class: CacheGetBlockV1

Source: inference.core.workflows.core_steps.cache.cache_get.v1.CacheGetBlockV1

Fetches a previously stored value from a cache entry.

Use the Cache Set block to store values in the cache.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
key	str	The key of the cache entry to fetch..	✅

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 Cache Get in version v1.

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

Input and Output Bindings

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

Bindings

• input

  • image (image): The image data to use as a reference for the cache namespace..
  • key (string): The key of the cache entry to fetch..

• output

  • output (*): Equivalent of any element.

Example JSON definition of step Cache Get in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/cache_get@v1",
    "image": "$inputs.image",
    "key": "my_cache_key"
}