LMM For Classification

Class: LMMForClassificationBlockV1

Source: inference.core.workflows.core_steps.models.foundation.lmm_classifier.v1.LMMForClassificationBlockV1

Classify an image into one or more categories using a Large Multimodal Model (LMM).

You can specify arbitrary classes to an LMMBlock.

The LLMBlock supports two LMMs:

• OpenAI's GPT-4 with Vision.

You need to provide your OpenAI API key to use the GPT-4 with Vision model.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
lmm_type	str	Type of LMM to be used.	✅
classes	List[str]	List of classes that LMM shall classify against.	✅
lmm_config	LMMConfig	Configuration of LMM.	❌
remote_api_key	str	Holds API key required to call LMM model - in current state of development, we require OpenAI key when lmm_type=gpt_4v..	✅

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 LMM For Classification in version v1.

• inputs: Anthropic Claude, Mask Visualization, Classification Label Visualization, Instance Segmentation Model, Webhook Sink, Multi-Label Classification Model, Email Notification, Dynamic Zone, QR Code Generator, Dynamic Crop, VLM As Detector, Google Gemini, LMM, Image Blur, Corner Visualization, Image Convert Grayscale, Stability AI Outpainting, Halo Visualization, Stability AI Inpainting, Object Detection Model, Image Contours, Trace Visualization, Google Vision OCR, Morphological Transformation, Triangle Visualization, Clip Comparison, Relative Static Crop, CSV Formatter, Text Display, Stitch Images, Google Gemini, Camera Calibration, Grid Visualization, Local File Sink, Slack Notification, VLM As Classifier, Roboflow Dataset Upload, Camera Focus, Color Visualization, Dot Visualization, Image Slicer, Polygon Visualization, Anthropic Claude, LMM For Classification, Line Counter Visualization, Llama 3.2 Vision, Keypoint Detection Model, Buffer, Contrast Equalization, SIFT Comparison, Dimension Collapse, Camera Focus, Background Subtraction, Image Slicer, Circle Visualization, Halo Visualization, Florence-2 Model, Blur Visualization, Label Visualization, Twilio SMS/MMS Notification, Clip Comparison, Email Notification, Ellipse Visualization, OpenAI, SIFT, Image Preprocessing, Model Monitoring Inference Aggregator, Single-Label Classification Model, Detections List Roll-Up, OpenAI, Image Threshold, Background Color Visualization, Model Comparison Visualization, Depth Estimation, OpenAI, Motion Detection, Size Measurement, CogVLM, Absolute Static Crop, Roboflow Custom Metadata, EasyOCR, Stitch OCR Detections, Perspective Correction, Anthropic Claude, Pixelate Visualization, Stability AI Image Generation, Reference Path Visualization, Keypoint Visualization, Polygon Visualization, Twilio SMS Notification, Bounding Box Visualization, Polygon Zone Visualization, OCR Model, Icon Visualization, Crop Visualization, Stitch OCR Detections, Google Gemini, OpenAI, Florence-2 Model, Roboflow Dataset Upload
• outputs: Anthropic Claude, Mask Visualization, Classification Label Visualization, Instance Segmentation Model, Webhook Sink, Email Notification, QR Code Generator, Dynamic Crop, CLIP Embedding Model, Google Gemini, LMM, SAM 3, Path Deviation, Image Blur, Corner Visualization, Line Counter, Stability AI Outpainting, Cache Set, Segment Anything 2 Model, Halo Visualization, Stability AI Inpainting, Path Deviation, Trace Visualization, Google Vision OCR, Morphological Transformation, Triangle Visualization, Instance Segmentation Model, Detections Stitch, Text Display, Google Gemini, Slack Notification, Local File Sink, Roboflow Dataset Upload, PTZ Tracking (ONVIF).md), Color Visualization, Dot Visualization, Polygon Visualization, Anthropic Claude, Llama 3.2 Vision, Line Counter Visualization, LMM For Classification, Contrast Equalization, Distance Measurement, Detections Classes Replacement, SIFT Comparison, Perception Encoder Embedding Model, Time in Zone, Circle Visualization, Moondream2, Seg Preview, Halo Visualization, Florence-2 Model, Twilio SMS/MMS Notification, Label Visualization, Clip Comparison, Email Notification, Ellipse Visualization, OpenAI, Image Preprocessing, Model Monitoring Inference Aggregator, SAM 3, OpenAI, Image Threshold, Model Comparison Visualization, Background Color Visualization, Size Measurement, OpenAI, Depth Estimation, Cache Get, Line Counter, Time in Zone, CogVLM, Roboflow Custom Metadata, Stitch OCR Detections, Perspective Correction, Anthropic Claude, Stability AI Image Generation, Reference Path Visualization, Keypoint Visualization, Twilio SMS Notification, Polygon Visualization, SAM 3, Bounding Box Visualization, Polygon Zone Visualization, YOLO-World Model, Icon Visualization, Time in Zone, Stitch OCR Detections, Crop Visualization, Google Gemini, Pixel Color Count, OpenAI, Florence-2 Model, Roboflow Dataset Upload

Input and Output Bindings

The available connections depend on its binding kinds. Check what binding kinds LMM For Classification in version v1 has.

Bindings

• input

  • images (image): The image to infer on..
  • lmm_type (string): Type of LMM to be used.
  • classes (list_of_values): List of classes that LMM shall classify against.
  • remote_api_key (Union[secret, string]): Holds API key required to call LMM model - in current state of development, we require OpenAI key when lmm_type=gpt_4v..

• output

  • raw_output (string): String value.
  • top (top_class): String value representing top class predicted by classification model.
  • parent_id (parent_id): Identifier of parent for step output.
  • root_parent_id (parent_id): Identifier of parent for step output.
  • image (image_metadata): Dictionary with image metadata required by supervision.
  • prediction_type (prediction_type): String value with type of prediction.

Example JSON definition of step LMM For Classification in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/lmm_for_classification@v1",
    "images": "$inputs.image",
    "lmm_type": "gpt_4v",
    "classes": [
        "a",
        "b"
    ],
    "lmm_config": {
        "gpt_image_detail": "low",
        "gpt_model_version": "gpt-4o",
        "max_tokens": 200
    },
    "remote_api_key": "xxx-xxx"
}