Perception Encoder Embedding Model

Class: PerceptionEncoderModelBlockV1

Source: inference.core.workflows.core_steps.models.foundation.perception_encoder.v1.PerceptionEncoderModelBlockV1

Use the Meta Perception Encoder model to create semantic embeddings of text and images.

This block accepts an image or string and returns an embedding. The embedding can be used to compare similarity between different images or between images and text.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Unique name of step in workflows.	❌
data	str	The string or image to generate an embedding for..	✅
version	str	Variant of Perception Encoder model.	✅

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 Perception Encoder Embedding Model in version v1.

• inputs: Roboflow Custom Metadata, Stitch Images, Webhook Sink, Halo Visualization, VLM as Classifier, Llama 3.2 Vision, Crop Visualization, Label Visualization, Instance Segmentation Model, Google Gemini, Roboflow Dataset Upload, Stability AI Inpainting, OCR Model, VLM as Detector, Image Preprocessing, CogVLM, Classification Label Visualization, Relative Static Crop, Keypoint Detection Model, Anthropic Claude, Triangle Visualization, Dot Visualization, Circle Visualization, Image Contours, LMM For Classification, Corner Visualization, LMM, Clip Comparison, Roboflow Dataset Upload, Trace Visualization, Camera Calibration, Bounding Box Visualization, Polygon Visualization, SIFT Comparison, OpenAI, Camera Focus, Color Visualization, Image Threshold, Image Blur, Blur Visualization, Image Convert Grayscale, Object Detection Model, Slack Notification, Florence-2 Model, Polygon Zone Visualization, Stability AI Image Generation, Pixelate Visualization, Multi-Label Classification Model, Model Comparison Visualization, Stitch OCR Detections, Depth Estimation, Florence-2 Model, Model Monitoring Inference Aggregator, Dynamic Crop, Absolute Static Crop, Image Slicer, Stability AI Outpainting, Reference Path Visualization, OpenAI, Email Notification, Single-Label Classification Model, Mask Visualization, Local File Sink, CSV Formatter, Google Vision OCR, Image Slicer, SIFT, Line Counter Visualization, Grid Visualization, Background Color Visualization, OpenAI, Ellipse Visualization, Keypoint Visualization, Twilio SMS Notification, Perspective Correction
• outputs: Identify Changes, Identify Outliers, Cosine Similarity

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds Perception Encoder Embedding Model in version v1 has.

Bindings

• input

  • data (Union[string, image]): The string or image to generate an embedding for..
  • version (string): Variant of Perception Encoder model.

• output

  • embedding (embedding): A list of floating point numbers representing a vector embedding..

Example JSON definition of step Perception Encoder Embedding Model in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/perception_encoder@v1",
    "data": "$inputs.image",
    "version": "PE-Core-B16-224"
}