VLM as Classifier¶
v2¶
Class: VLMAsClassifierBlockV2 (there are multiple versions of this block)
Source: inference.core.workflows.core_steps.formatters.vlm_as_classifier.v2.VLMAsClassifierBlockV2
Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning
The block expects string input that would be produced by blocks exposing Large Language Models (LLMs) and Visual Language Models (VLMs). Input is parsed to classification prediction and returned as block output.
Accepted formats:
-
valid JSON strings
-
JSON documents wrapped with Markdown tags (very common for GPT responses)
Example:
{"my": "json"}
Details regarding block behavior:
-
error_statusis setTruewhenever parsing cannot be completed -
in case of multiple markdown blocks with raw JSON content - only first will be parsed
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/vlm_as_classifier@v2to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
classes |
List[str] |
List of all classes used by the model, required to generate mapping between class name and class id.. | ✅ |
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 VLM as Classifier in version v2.
- inputs:
Image Slicer,Stability AI Inpainting,Pixelate Visualization,Perspective Correction,Clip Comparison,OpenAI,Relative Static Crop,Dimension Collapse,SIFT Comparison,Google Gemini,Grid Visualization,Ellipse Visualization,SIFT,Model Comparison Visualization,Halo Visualization,Image Contours,Crop Visualization,Absolute Static Crop,Camera Focus,Image Blur,Trace Visualization,Circle Visualization,Buffer,Image Preprocessing,Background Color Visualization,Dot Visualization,Clip Comparison,Polygon Zone Visualization,Size Measurement,Florence-2 Model,Classification Label Visualization,Bounding Box Visualization,Corner Visualization,Llama 3.2 Vision,Image Slicer,Florence-2 Model,Dynamic Crop,Reference Path Visualization,Label Visualization,Mask Visualization,Stitch Images,Triangle Visualization,Stability AI Image Generation,Image Threshold,Line Counter Visualization,Dynamic Zone,Keypoint Visualization,Color Visualization,Blur Visualization,Anthropic Claude,Image Convert Grayscale,Polygon Visualization - outputs:
Slack Notification,Segment Anything 2 Model,Pixelate Visualization,Perspective Correction,Instance Segmentation Model,Object Detection Model,Roboflow Custom Metadata,Object Detection Model,Twilio SMS Notification,Detections Consensus,SIFT Comparison,Keypoint Detection Model,Roboflow Dataset Upload,Ellipse Visualization,Model Comparison Visualization,Halo Visualization,Multi-Label Classification Model,Crop Visualization,Trace Visualization,Circle Visualization,Keypoint Detection Model,Multi-Label Classification Model,Dot Visualization,Background Color Visualization,Roboflow Dataset Upload,Polygon Zone Visualization,Gaze Detection,Single-Label Classification Model,Classification Label Visualization,Bounding Box Visualization,Corner Visualization,Reference Path Visualization,Label Visualization,Mask Visualization,Triangle Visualization,Template Matching,Line Counter Visualization,Keypoint Visualization,Model Monitoring Inference Aggregator,Email Notification,Time in Zone,Single-Label Classification Model,Blur Visualization,Color Visualization,Webhook Sink,Time in Zone,Instance Segmentation Model,Detections Classes Replacement,Polygon Visualization
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
VLM as Classifier in version v2 has.
Bindings
-
input
image(image): The image which was the base to generate VLM prediction.vlm_output(language_model_output): The string with raw classification prediction to parse..classes(list_of_values): List of all classes used by the model, required to generate mapping between class name and class id..
-
output
error_status(boolean): Boolean flag.predictions(classification_prediction): Predictions from classifier.inference_id(inference_id): Inference identifier.
Example JSON definition of step VLM as Classifier in version v2
{
"name": "<your_step_name_here>",
"type": "roboflow_core/vlm_as_classifier@v2",
"image": "$inputs.image",
"vlm_output": [
"$steps.lmm.output"
],
"classes": [
"$steps.lmm.classes",
"$inputs.classes",
[
"class_a",
"class_b"
]
]
}
v1¶
Class: VLMAsClassifierBlockV1 (there are multiple versions of this block)
Source: inference.core.workflows.core_steps.formatters.vlm_as_classifier.v1.VLMAsClassifierBlockV1
Warning: This block has multiple versions. Please refer to the specific version for details. You can learn more about how versions work here: Versioning
The block expects string input that would be produced by blocks exposing Large Language Models (LLMs) and Visual Language Models (VLMs). Input is parsed to classification prediction and returned as block output.
Accepted formats:
-
valid JSON strings
-
JSON documents wrapped with Markdown tags (very common for GPT responses)
Example:
{"my": "json"}
Details regarding block behavior:
-
error_statusis setTruewhenever parsing cannot be completed -
in case of multiple markdown blocks with raw JSON content - only first will be parsed
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/vlm_as_classifier@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
classes |
List[str] |
List of all classes used by the model, required to generate mapping between class name and class id.. | ✅ |
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 VLM as Classifier in version v1.
- inputs:
Image Slicer,Stability AI Inpainting,Pixelate Visualization,Perspective Correction,Clip Comparison,OpenAI,Relative Static Crop,Dimension Collapse,SIFT Comparison,Google Gemini,Grid Visualization,Ellipse Visualization,SIFT,Model Comparison Visualization,Halo Visualization,Image Contours,Crop Visualization,Absolute Static Crop,Camera Focus,Image Blur,Trace Visualization,Circle Visualization,Buffer,Image Preprocessing,Background Color Visualization,Dot Visualization,Clip Comparison,Polygon Zone Visualization,Size Measurement,Florence-2 Model,Classification Label Visualization,Bounding Box Visualization,Corner Visualization,Llama 3.2 Vision,Image Slicer,Florence-2 Model,Dynamic Crop,Reference Path Visualization,Label Visualization,Mask Visualization,Stitch Images,Triangle Visualization,Stability AI Image Generation,Image Threshold,Line Counter Visualization,Dynamic Zone,Keypoint Visualization,Color Visualization,Blur Visualization,Anthropic Claude,Image Convert Grayscale,Polygon Visualization - outputs:
Segment Anything 2 Model,Cache Get,Stability AI Inpainting,Clip Comparison,Perspective Correction,Cache Set,Object Detection Model,Roboflow Custom Metadata,Object Detection Model,SIFT Comparison,CogVLM,Ellipse Visualization,Multi-Label Classification Model,OpenAI,Trace Visualization,CLIP Embedding Model,Multi-Label Classification Model,Dot Visualization,Google Vision OCR,Roboflow Dataset Upload,Polygon Zone Visualization,Gaze Detection,Classification Label Visualization,Corner Visualization,Llama 3.2 Vision,Line Counter,Reference Path Visualization,Dynamic Crop,Label Visualization,Mask Visualization,Triangle Visualization,Template Matching,Line Counter Visualization,Model Monitoring Inference Aggregator,Time in Zone,Blur Visualization,Line Counter,Anthropic Claude,Instance Segmentation Model,Webhook Sink,Time in Zone,Instance Segmentation Model,Slack Notification,Pixelate Visualization,Path Deviation,OpenAI,Detections Consensus,Twilio SMS Notification,Keypoint Detection Model,Roboflow Dataset Upload,Google Gemini,Model Comparison Visualization,Halo Visualization,Crop Visualization,Image Blur,Distance Measurement,Circle Visualization,Keypoint Detection Model,Image Preprocessing,Background Color Visualization,Pixel Color Count,Size Measurement,Florence-2 Model,Single-Label Classification Model,Bounding Box Visualization,Florence-2 Model,Local File Sink,LMM For Classification,Stability AI Image Generation,Image Threshold,Detections Stitch,LMM,Keypoint Visualization,Email Notification,Color Visualization,Path Deviation,Single-Label Classification Model,YOLO-World Model,Detections Classes Replacement,Polygon Visualization
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
VLM as Classifier in version v1 has.
Bindings
-
input
image(image): The image which was the base to generate VLM prediction.vlm_output(language_model_output): The string with raw classification prediction to parse..classes(list_of_values): List of all classes used by the model, required to generate mapping between class name and class id..
-
output
error_status(boolean): Boolean flag.predictions(classification_prediction): Predictions from classifier.inference_id(string): String value.
Example JSON definition of step VLM as Classifier in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/vlm_as_classifier@v1",
"image": "$inputs.image",
"vlm_output": [
"$steps.lmm.output"
],
"classes": [
"$steps.lmm.classes",
"$inputs.classes",
[
"class_a",
"class_b"
]
]
}