CogVLM

Class: CogVLMBlockV1

Source: inference.core.workflows.core_steps.models.foundation.cog_vlm.v1.CogVLMBlockV1

CogVLM reached End Of Life

Due to dependencies conflicts with newer models and security vulnerabilities discovered in transformers library patched in the versions of library incompatible with the model we announced End Of Life for CogVLM support in inference, effective since release 0.38.0.

We are leaving this block in ecosystem until release 0.42.0 for clients to get informed about change that was introduced.

Starting as of now, all Workflows using the block stop being functional (runtime error will be raised), after inference release 0.42.0 - this block will be removed and Execution Engine will raise compilation error seeing the block in Workflow definition.

Ask a question to CogVLM, an open source vision-language model.

This model requires a GPU and can only be run on self-hosted devices, and is not available on the Roboflow Hosted API.

This model was previously part of the LMM block.

Type identifier

Use the following identifier in step "type" field: roboflow_core/cog_vlm@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	Text prompt to the CogVLM model.	✅
json_output_format	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 CogVLM in version v1.

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

Input and Output Bindings

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

Bindings

• input

  • images (image): The image to infer on..
  • prompt (string): Text prompt to the CogVLM model.

• 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 CogVLM in version v1

{
    "name": "<your_step_name_here>",
    "type": "roboflow_core/cog_vlm@v1",
    "images": "$inputs.image",
    "prompt": "my prompt",
    "json_output_format": {
        "count": "number of cats in the picture"
    }
}