LMM

Class: LMMBlockV1

Source: inference.core.workflows.core_steps.models.foundation.lmm.v1.LMMBlockV1

Ask a question to a Large Multimodal Model (LMM) with an image and text.

You can specify arbitrary text prompts 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.

If you want to classify an image into one or more categories, we recommend using the dedicated LMMForClassificationBlock.

Type identifier

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

Properties

Name	Type	Description	Refs
name	str	Enter a unique identifier for this step..	❌
prompt	str	Holds unconstrained text prompt to LMM mode.	✅
lmm_type	str	Type of LMM to be used.	✅
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..	✅
json_output	Dict[str, str]	Holds dictionary that maps name of requested output field into its description.	❌

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 in version v1.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Holds unconstrained text prompt to LMM mode.
  • lmm_type (string): Type of LMM to be used.
  • remote_api_key (Union[string, secret]): Holds API key required to call LMM model - in current state of development, we require OpenAI key when lmm_type=gpt_4v..

• output

  • 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.
  • structured_output (dictionary): Dictionary.
  • raw_output (string): String value.
  • * (*): Equivalent of any element.

Example JSON definition of step LMM in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/lmm@v1",
    "images": "$inputs.image",
    "prompt": "my prompt",
    "lmm_type": "gpt_4v",
    "lmm_config": {
        "gpt_image_detail": "low",
        "gpt_model_version": "gpt-4o",
        "max_tokens": 200
    },
    "remote_api_key": "xxx-xxx",
    "json_output": {
        "count": "number of cats in the picture"
    }
}