GLM-OCR¶
Class: GLMOCRBlockV1
Source: inference.core.workflows.core_steps.models.foundation.glm_ocr.v1.GLMOCRBlockV1
Recognize text in images using GLM-OCR, a vision language model by Zhipu AI specialized for optical character recognition.
GLM-OCR supports three built-in recognition modes:
- Text Recognition — General-purpose text recognition for serial numbers, labels, scene text, and documents.
- Formula Recognition — Recognizes mathematical formulas and equations.
- Table Recognition — Recognizes table structures and content.
You can also select Custom Prompt to provide your own prompt for specialized recognition tasks, or Structured Output to extract values from the image into a JSON document with a user-defined schema (pair with the JSON Parser block to materialize the keys as workflow outputs).
This block pairs well with detection models and DynamicCropBlock to isolate regions of interest before running OCR. For example, use an object detection model to find labels or text regions, crop them, then pass the crops to GLM-OCR.
Note: GLM-OCR requires a GPU for inference.
Type identifier¶
Use the following identifier in step "type" field: roboflow_core/glm_ocr@v1to add the block as
as step in your workflow.
Properties¶
| Name | Type | Description | Refs |
|---|---|---|---|
name |
str |
Enter a unique identifier for this step.. | ❌ |
task_type |
str |
Recognition task to perform. Determines the prompt sent to GLM-OCR.. | ❌ |
prompt |
str |
Custom text prompt for GLM-OCR. Only used when task_type is 'custom'.. | ✅ |
output_structure |
Dict[str, str] |
Dictionary describing the structure of the expected JSON response. Keys are the JSON field names; values describe what the model should put in each field.. | ❌ |
max_new_tokens |
int |
Maximum number of tokens to generate. If not set, the model default will be used.. | ❌ |
model_version |
str |
The GLM-OCR model to be used for inference.. | ✅ |
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 GLM-OCR in version v1.
- inputs:
Slack Notification,Anthropic Claude,QR Code Generator,Keypoint Detection Model,Clip Comparison,Anthropic Claude,OpenAI,Instance Segmentation Model,Google Vision OCR,Circle Visualization,Bounding Box Visualization,Single-Label Classification Model,Florence-2 Model,VLM As Classifier,Image Slicer,Google Gemini,Image Contours,Image Blur,Keypoint Detection Model,Qwen 3.6 API,Dot Visualization,Polygon Zone Visualization,Single-Label Classification Model,Label Visualization,Icon Visualization,Image Threshold,Roboflow Vision Events,LMM For Classification,Depth Estimation,Line Counter Visualization,Object Detection Model,Stitch Images,Blur Visualization,Morphological Transformation,Relative Static Crop,LMM,Model Comparison Visualization,Trace Visualization,Qwen3.5-VL,Florence-2 Model,Camera Focus,MoonshotAI Kimi,Grid Visualization,Pixelate Visualization,CogVLM,Instance Segmentation Model,Twilio SMS/MMS Notification,OpenAI,Image Convert Grayscale,Llama 3.2 Vision,Keypoint Visualization,Twilio SMS Notification,Polygon Visualization,Qwen-VL,S3 Sink,Halo Visualization,Camera Focus,SIFT Comparison,Keypoint Detection Model,Local File Sink,Classification Label Visualization,Google Gemma,Semantic Segmentation Model,Mask Visualization,Multi-Label Classification Model,Morphological Transformation,Multi-Label Classification Model,Camera Calibration,SIFT,Google Gemini,Email Notification,Anthropic Claude,MoonshotAI Kimi,Roboflow Dataset Upload,Image Preprocessing,Semantic Segmentation Model,Text Display,Image Slicer,Corner Visualization,Multi-Label Classification Model,Absolute Static Crop,Stitch OCR Detections,Llama 3.2 Vision,Halo Visualization,Roboflow Asset Library Attributes,GLM-OCR,Object Detection Model,Roboflow Custom Metadata,Email Notification,Dynamic Crop,Reference Path Visualization,OpenAI,Instance Segmentation Model,OpenRouter,Background Color Visualization,Single-Label Classification Model,Model Monitoring Inference Aggregator,Ellipse Visualization,CSV Formatter,Stability AI Outpainting,Contrast Enhancement,VLM As Detector,EasyOCR,Triangle Visualization,OCR Model,Crop Visualization,Webhook Sink,Google Gemma API,Perspective Correction,Qwen 3.5 API,Stability AI Image Generation,Stitch OCR Detections,OpenAI-Compatible LLM,Color Visualization,Heatmap Visualization,Contrast Equalization,Instance Segmentation Model,Object Detection Model,Polygon Visualization,Background Subtraction,Google Gemini,Roboflow Dataset Upload,OpenAI,Stability AI Inpainting - outputs:
Slack Notification,Anthropic Claude,QR Code Generator,Distance Measurement,Clip Comparison,Instance Segmentation Model,Anthropic Claude,OpenAI,Google Vision OCR,Circle Visualization,Bounding Box Visualization,SAM 3,Florence-2 Model,VLM As Classifier,Google Gemini,Image Blur,Keypoint Detection Model,Qwen 3.6 API,Dot Visualization,Polygon Zone Visualization,Label Visualization,CLIP Embedding Model,Icon Visualization,Image Threshold,Roboflow Vision Events,Cache Get,LMM For Classification,Depth Estimation,Line Counter Visualization,Object Detection Model,VLM As Detector,Line Counter,Morphological Transformation,LMM,Model Comparison Visualization,Trace Visualization,Moondream2,Size Measurement,Perception Encoder Embedding Model,MoonshotAI Kimi,Segment Anything 2 Model,Florence-2 Model,CogVLM,Cache Set,Instance Segmentation Model,Twilio SMS/MMS Notification,OpenAI,Detections Classes Replacement,Llama 3.2 Vision,Time in Zone,Keypoint Visualization,Twilio SMS Notification,SAM 3,Polygon Visualization,Qwen-VL,S3 Sink,SAM 3,Halo Visualization,Local File Sink,Semantic Segmentation Model,SIFT Comparison,Multi-Label Classification Model,Line Counter,Google Gemma,Classification Label Visualization,Mask Visualization,Morphological Transformation,Email Notification,Google Gemini,Path Deviation,Anthropic Claude,MoonshotAI Kimi,Roboflow Dataset Upload,Image Preprocessing,Text Display,Corner Visualization,Stitch OCR Detections,Llama 3.2 Vision,Halo Visualization,VLM As Classifier,PTZ Tracking (ONVIF),Path Deviation,GLM-OCR,Roboflow Asset Library Attributes,Email Notification,Seg Preview,Dynamic Crop,Roboflow Custom Metadata,OpenAI,Instance Segmentation Model,Reference Path Visualization,Time in Zone,OpenRouter,Detections Stitch,Background Color Visualization,Single-Label Classification Model,JSON Parser,Model Monitoring Inference Aggregator,Ellipse Visualization,Stability AI Outpainting,VLM As Detector,Triangle Visualization,Crop Visualization,Webhook Sink,Google Gemma API,Qwen 3.5 API,Perspective Correction,Stability AI Image Generation,Stitch OCR Detections,OpenAI-Compatible LLM,Color Visualization,Heatmap Visualization,Contrast Equalization,Instance Segmentation Model,Time in Zone,YOLO-World Model,Polygon Visualization,Pixel Color Count,Google Gemini,Roboflow Dataset Upload,OpenAI,Stability AI Inpainting
Input and Output Bindings¶
The available connections depend on its binding kinds. Check what binding kinds
GLM-OCR in version v1 has.
Bindings
-
input
images(image): The image to infer on..prompt(string): Custom text prompt for GLM-OCR. Only used when task_type is 'custom'..model_version(roboflow_model_id): The GLM-OCR model to be used for inference..
-
output
parsed_output(Union[string,language_model_output]): String value ifstringor LLM / VLM output iflanguage_model_output.
Example JSON definition of step GLM-OCR in version v1
{
"name": "<your_step_name_here>",
"type": "roboflow_core/glm_ocr@v1",
"images": "$inputs.image",
"task_type": "<block_does_not_provide_example>",
"prompt": "Describe the text in the image.",
"output_structure": {
"my_key": "description"
},
"max_new_tokens": "<block_does_not_provide_example>",
"model_version": "glm-ocr"
}