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:
Perspective Correction,S3 Sink,Stability AI Inpainting,Image Convert Grayscale,Email Notification,Morphological Transformation,Clip Comparison,VLM As Detector,Qwen-VL,QR Code Generator,Twilio SMS/MMS Notification,OpenRouter,Model Monitoring Inference Aggregator,OpenAI,Llama 3.2 Vision,MoonshotAI Kimi,Polygon Zone Visualization,Image Threshold,Stitch OCR Detections,Anthropic Claude,OpenAI-Compatible LLM,OpenAI,Dynamic Crop,Heatmap Visualization,Keypoint Visualization,Email Notification,Llama 3.2 Vision,Anthropic Claude,Stability AI Image Generation,Google Vision OCR,Camera Focus,Label Visualization,Instance Segmentation Model,Contrast Enhancement,Bounding Box Visualization,Local File Sink,Depth Estimation,Google Gemini,Image Contours,EasyOCR,Relative Static Crop,Polygon Visualization,Google Gemma API,Background Color Visualization,Qwen 3.6 API,Qwen 3.5 API,Image Blur,Polygon Visualization,Google Gemini,SIFT Comparison,Grid Visualization,Anthropic Claude,Florence-2 Model,Triangle Visualization,Object Detection Model,OCR Model,Roboflow Custom Metadata,OpenAI,Slack Notification,VLM As Classifier,Pixelate Visualization,Stitch Images,Single-Label Classification Model,OpenAI,Image Slicer,LMM For Classification,Keypoint Detection Model,Image Preprocessing,SIFT,Line Counter Visualization,Roboflow Dataset Upload,Image Slicer,Corner Visualization,Stability AI Outpainting,Halo Visualization,Multi-Label Classification Model,LMM,Roboflow Dataset Upload,Qwen3.5-VL,Color Visualization,Google Gemini,Blur Visualization,Classification Label Visualization,Camera Focus,Camera Calibration,Morphological Transformation,Trace Visualization,Stitch OCR Detections,Reference Path Visualization,Halo Visualization,Ellipse Visualization,Model Comparison Visualization,Dot Visualization,Mask Visualization,GLM-OCR,Crop Visualization,Background Subtraction,Circle Visualization,CogVLM,Text Display,Absolute Static Crop,CSV Formatter,Florence-2 Model,Contrast Equalization,Roboflow Vision Events,Webhook Sink,Icon Visualization,Twilio SMS Notification,MoonshotAI Kimi,Google Gemma - outputs:
Keypoint Detection Model,VLM As Detector,YOLO-World Model,MoonshotAI Kimi,Polygon Zone Visualization,OpenAI-Compatible LLM,Heatmap Visualization,Email Notification,Llama 3.2 Vision,Anthropic Claude,Label Visualization,Camera Focus,Path Deviation,Qwen3.5,SmolVLM2,Rate Limiter,Byte Tracker,Background Color Visualization,Mask Edge Snap,Moondream2,Velocity,Detection Event Log,Florence-2 Model,Barcode Detection,Single-Label Classification Model,OCR Model,VLM As Classifier,Qwen2.5-VL,Detections Stabilizer,LMM For Classification,SIFT,Roboflow Dataset Upload,Segment Anything 2 Model,Halo Visualization,Multi-Label Classification Model,Qwen3.5-VL,Qwen3-VL,Time in Zone,Stitch OCR Detections,Model Comparison Visualization,QR Code Detection,Detections Combine,Bounding Rectangle,ByteTrack Tracker,Stability AI Inpainting,Image Convert Grayscale,Line Counter,OpenAI,Llama 3.2 Vision,Anthropic Claude,Dynamic Crop,Detections Consensus,Size Measurement,Dominant Color,Continue If,Contrast Enhancement,Bounding Box Visualization,Depth Estimation,CLIP Embedding Model,EasyOCR,Relative Static Crop,Polygon Visualization,Google Gemma API,Qwen 3.6 API,Template Matching,Single-Label Classification Model,Image Blur,Anthropic Claude,Triangle Visualization,Roboflow Custom Metadata,Slack Notification,Image Stack,Pixelate Visualization,Image Slicer,Line Counter Visualization,Image Slicer,Cosine Similarity,Cache Get,Data Aggregator,Expression,Google Gemini,Camera Calibration,Ellipse Visualization,Identify Changes,GLM-OCR,Crop Visualization,Circle Visualization,Dimension Collapse,Webhook Sink,MoonshotAI Kimi,S3 Sink,Email Notification,Clip Comparison,Morphological Transformation,Path Deviation,Qwen-VL,SAM 3,Twilio SMS/MMS Notification,Line Counter,Time in Zone,Stitch OCR Detections,OpenAI,VLM As Detector,Keypoint Visualization,Seg Preview,Stability AI Image Generation,Google Vision OCR,SAM 3,Instance Segmentation Model,Overlap Filter,Local File Sink,Multi-Label Classification Model,Google Gemini,Motion Detection,Instance Segmentation Model,Qwen 3.5 API,Google Gemini,Polygon Visualization,SIFT Comparison,Grid Visualization,Delta Filter,Time in Zone,Detections Filter,Detections Merge,First Non Empty Or Default,Keypoint Detection Model,Image Preprocessing,Dynamic Zone,Corner Visualization,Stability AI Outpainting,Semantic Segmentation Model,Detections List Roll-Up,Blur Visualization,Property Definition,Perception Encoder Embedding Model,Distance Measurement,Morphological Transformation,Trace Visualization,VLM As Classifier,Gaze Detection,Reference Path Visualization,Halo Visualization,Dot Visualization,Pixel Color Count,JSON Parser,Background Subtraction,Text Display,Absolute Static Crop,CSV Formatter,Florence-2 Model,Byte Tracker,Icon Visualization,Identify Outliers,Mask Area Measurement,Object Detection Model,Perspective Correction,SAM 3,BoT-SORT Tracker,Object Detection Model,QR Code Generator,OpenRouter,Model Monitoring Inference Aggregator,Image Threshold,OC-SORT Tracker,Clip Comparison,Cache Set,Detection Offset,Keypoint Detection Model,Image Contours,Multi-Label Classification Model,Per-Class Confidence Filter,Object Detection Model,OpenAI,SIFT Comparison,Single-Label Classification Model,OpenAI,Instance Segmentation Model,Stitch Images,Buffer,Detections Classes Replacement,Semantic Segmentation Model,LMM,Roboflow Dataset Upload,Detections Transformation,Color Visualization,Classification Label Visualization,Camera Focus,Detections Stitch,Byte Tracker,PTZ Tracking (ONVIF),SORT Tracker,Mask Visualization,CogVLM,Inner Workflow,SAM2 Video Tracker,Contrast Equalization,Roboflow Vision Events,Twilio SMS Notification,Google Gemma
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
CogVLM in version v1 has.
Bindings
-
input
-
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"
}
}