Roboflow Visual Search Classifier¶
Class: RoboflowVisualSearchClassifierBlockV1
Search a Roboflow classification project for the visually closest image and return
the matched image's classification annotation as a standard classification
prediction. Single-label annotations are returned in single-label classification
shape, and multi-label annotations are returned in multi-label classification
shape. Classification confidence is derived from the best candidate's public
Roboflow project search score field when present.
This block performs an external visual search API call and is not intended for
real-time or high-throughput workloads. To bound latency, query images are
downscaled with aspect ratio preserved to a maximum side length of 224 pixels by
default. Increase max_image_size when finer visual matching is more important
than lower latency.
How This Block Works¶
This block uses Roboflow project image search:
- Receives an input image from the workflow
- Downscales the query image if its larger side exceeds
max_image_size - Sends the query image to Roboflow project search as
image_base64 - Requests candidate image fields and classification labels or annotations
- Uses the best candidate's annotation as the predicted class
- Maps the API
scorefield to classification confidence when present - Returns the result through the standard
predictionsclassification output
The target project must expose classification annotation data in visual search results. This block does not train a model, create annotations, consume raw search backend relevance scores, or manage the visual search index.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/visual_search_classifier@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
target_project |
str |
Roboflow classification project URL slug to search.. | ✅ |
workspace |
str |
Optional Roboflow workspace URL slug that owns the target project. If not provided, the workspace is resolved from the request API key.. | ✅ |
top_k |
int |
Number of visually similar image candidates to request. The nearest candidate is used for classification.. | ✅ |
max_image_size |
int |
Maximum side length, in pixels, for the visual search query image. Images larger than this are downscaled with aspect ratio preserved before search. Increase this value for finer matching at higher latency.. | ✅ |
The Refs column marks possibility to parametrise the property with dynamic values available
in workflow runtime. See Bindings for more info.
Runtime compatibility¶
-
requires_internet— air-gapped / offline deployments - This block depends on a service that is not reachable from fully offline / air-gapped deployments.
Available Connections¶
Compatible Blocks
Check what blocks you can connect to Roboflow Visual Search Classifier in version v1.
- inputs:
Google Gemini,OpenAI,Trace Visualization,Twilio SMS Notification,Pixel Color Count,Image Preprocessing,Anthropic Claude,Image Slicer,VLM As Classifier,Dynamic Crop,LMM For Classification,Object Detection Model,Bounding Box Visualization,Webhook Sink,Halo Visualization,Mask Visualization,Template Matching,Absolute Static Crop,Pixelate Visualization,Twilio SMS/MMS Notification,MoonshotAI Kimi,SIFT Comparison,Dot Visualization,Multi-Label Classification Model,Image Stack,Stitch Images,Stitch OCR Detections,OpenAI,OPC UA Writer Sink,Google Gemini,Stability AI Inpainting,Email Notification,Distance Measurement,Frame Delay,EasyOCR,Keypoint Visualization,Llama 3.2 Vision,Florence-2 Model,LMM,Roboflow Custom Metadata,Auto Rotate on Edges,Image Slicer,Keypoint Detection Model,OCR Model,Circle Visualization,Model Comparison Visualization,Stability AI Outpainting,Slack Notification,Line Counter Visualization,Camera Calibration,Contrast Enhancement,Relative Static Crop,Single-Label Classification Model,Clip Comparison,Morphological Transformation,Email Notification,Halo Visualization,VLM As Detector,Cosmos 3,CogVLM,Polygon Visualization,Camera Focus,Corner Visualization,Ellipse Visualization,Qwen-VL,Crop Visualization,PP-OCR,Google Gemma,Qwen 3.5 API,PLC Writer,Model Monitoring Inference Aggregator,Morphological Transformation,Anthropic Claude,Roboflow Visual Search,Icon Visualization,Heatmap Visualization,Color Visualization,Instance Segmentation Model,Google Gemma API,OpenAI,CSV Formatter,Image Blur,Triangle Visualization,Background Color Visualization,Grid Visualization,Detection Event Log,Image Contours,Image Threshold,Blur Visualization,GLM-OCR,Current Time,Roboflow Visual Search Classifier,QR Code Generator,Anthropic Claude,OpenAI-Compatible LLM,Florence-2 Model,Reference Path Visualization,Polygon Zone Visualization,Stitch OCR Detections,Roboflow Asset Library Attributes,Classification Label Visualization,Microsoft SQL Server Sink,Perspective Correction,Background Subtraction,Camera Focus,Image Convert Grayscale,Label Visualization,Contrast Equalization,Polygon Visualization,Google Vision OCR,SIFT,Stability AI Image Generation,Text Display,Llama 3.2 Vision,Qwen 3.6 API,Line Counter,MQTT Writer,MoonshotAI Kimi,Roboflow Dataset Upload,Local File Sink,OpenRouter,Qwen3.5-VL,Roboflow Vision Events,OpenAI,SIFT Comparison,Google Gemini,S3 Sink,Event Writer,Depth Estimation,Line Counter,Roboflow Dataset Upload - outputs:
Anthropic Claude,Image Slicer,Dynamic Crop,Mask Area Measurement,BoT-SORT Tracker,Cache Get,SIFT Comparison,Stitch Images,Stitch OCR Detections,Instance Segmentation Model,Stability AI Inpainting,Distance Measurement,EasyOCR,Llama 3.2 Vision,Track Class Lock,Florence-2 Model,Gaze Detection,YOLO-World Model,Dominant Color,Model Comparison Visualization,Detections Classes Replacement,Line Counter Visualization,PLC Reader,Clip Comparison,CogVLM,PP-OCR,Detections List Roll-Up,Morphological Transformation,Instance Segmentation Model,OpenAI,Time in Zone,Detections Stabilizer,Image Contours,SAM 3,Roboflow Visual Search Classifier,QR Code Generator,OpenAI-Compatible LLM,Polygon Zone Visualization,Roboflow Asset Library Attributes,Path Deviation,GeoTag Detection,Camera Focus,Llama 3.2 Vision,VLM As Detector,Instance Segmentation Model,MQTT Writer,Roboflow Dataset Upload,Local File Sink,Event Writer,Google Gemini,Semantic Segmentation Model,Depth Estimation,Seg Preview,Byte Tracker,Google Gemini,OpenAI,Twilio SMS Notification,Pixel Color Count,Object Detection Model,Webhook Sink,Halo Visualization,Buffer,Dot Visualization,Image Stack,OPC UA Writer Sink,Image Slicer,Time in Zone,Contrast Enhancement,Morphological Transformation,Per-Class Confidence Filter,Halo Visualization,Clip Comparison,Google Gemma,Qwen 3.5 API,Qwen3.5,Single-Label Classification Model,Motion Detection,Multi-Label Classification Model,Detections Consensus,Segment Anything 2 Model,Image Blur,Grid Visualization,Blur Visualization,GLM-OCR,Anthropic Claude,Google Vision OCR,Polygon Visualization,SIFT,Qwen 3.6 API,Text Display,Qwen3.5-VL,Roboflow Vision Events,Keypoint Detection Model,S3 Sink,Line Counter,Roboflow Dataset Upload,SAM 3,Image Preprocessing,Single-Label Classification Model,Time in Zone,CLIP Embedding Model,Bounding Box Visualization,Object Detection Model,Mask Edge Snap,Path Deviation,QR Code Detection,Absolute Static Crop,OpenAI,Email Notification,Frame Delay,Roboflow Custom Metadata,Dynamic Zone,Auto Rotate on Edges,Keypoint Detection Model,Continue If,Stability AI Outpainting,Slack Notification,Camera Calibration,Single-Label Classification Model,VLM As Detector,SORT Tracker,Ellipse Visualization,Corner Visualization,Camera Focus,Anthropic Claude,Roboflow Visual Search,Color Visualization,Triangle Visualization,Detection Event Log,Object Detection Model,SAM 3,Image Threshold,Barcode Detection,Current Time,Qwen2.5-VL,Florence-2 Model,Semantic Segmentation Model,SmolVLM2,Stitch OCR Detections,Microsoft SQL Server Sink,Moondream2,VLM As Classifier,Image Convert Grayscale,Label Visualization,Stability AI Image Generation,Perception Encoder Embedding Model,Line Counter,Cache Set,VLM As Classifier,Trace Visualization,SAM 3 Interactive,PLC EthernetIP,LMM For Classification,Velocity,Mask Visualization,Template Matching,Twilio SMS/MMS Notification,Pixelate Visualization,MoonshotAI Kimi,Multi-Label Classification Model,Google Gemini,OC-SORT Tracker,Keypoint Visualization,LMM,PTZ Tracking (ONVIF),OCR Model,Circle Visualization,Relative Static Crop,SAM2 Video Tracker,ByteTrack Tracker,Email Notification,Cosmos 3,Polygon Visualization,Qwen-VL,PLC Writer,Crop Visualization,Model Monitoring Inference Aggregator,Qwen3-VL,Keypoint Detection Model,Size Measurement,Icon Visualization,Heatmap Visualization,Google Gemma API,Instance Segmentation Model,SAM3 Video Tracker,Background Color Visualization,Detections Stitch,Reference Path Visualization,Classification Label Visualization,Perspective Correction,Background Subtraction,Contrast Equalization,MoonshotAI Kimi,OpenRouter,OpenAI,Multi-Label Classification Model
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
Roboflow Visual Search Classifier in version v1 has.
Bindings
-
input
image(image): Image to classify using visual search..target_project(roboflow_project): Roboflow classification project URL slug to search..workspace(string): Optional Roboflow workspace URL slug that owns the target project. If not provided, the workspace is resolved from the request API key..top_k(integer): Number of visually similar image candidates to request. The nearest candidate is used for classification..max_image_size(integer): Maximum side length, in pixels, for the visual search query image. Images larger than this are downscaled with aspect ratio preserved before search. Increase this value for finer matching at higher latency..
-
output
predictions(classification_prediction): Predictions from classifier.inference_id(inference_id): Inference identifier.candidate_found(boolean): Boolean flag.class_found(boolean): Boolean flag.best_candidate(dictionary): Dictionary.candidates(list_of_values): List of values of any type.best_candidate_image(image): Image in workflows.visual_search_score(float): Float value.error_status(boolean): Boolean flag.message(string): String value.
Example JSON definition of step Roboflow Visual Search Classifier in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/visual_search_classifier@v1",
"image": "$inputs.image",
"target_project": "reference-images",
"workspace": "my-workspace",
"top_k": 1,
"max_image_size": 224
}