News
GLM-OCR: 0.9B Parameters Achieving OCR SOTA Performance
Introducing GLM-OCR, a lightweight professional OCR model with only 0.9B parameters that achieves state-of-the-art performance on OmniDocBench V1.5 with a score of 94.62.
Tutorial
GLM-OCR Quick Start: Complete Document Parsing Guide
Learn how to get started with GLM-OCR for document parsing. This guide covers API integration, Ollama local deployment, vLLM, and SGLang deployment options.
FeatureTutorial
Complex Table Recognition: How GLM-OCR Handles Merged Cells
Learn how GLM-OCR excels at recognizing complex tables with merged cells, multi-level headers, and diverse layouts commonly found in business documents.
FeatureTutorial
Mathematical Formula Recognition: GLM-OCR LaTeX Output Guide
Learn how to use GLM-OCR for high-accuracy mathematical formula recognition with LaTeX output, perfect for academic documents and scientific papers.
FeatureTutorial
Structured Information Extraction: GLM-OCR JSON Output for Documents
Learn how to use GLM-OCR for structured information extraction from invoices, ID cards, receipts, and forms with customizable JSON schema output.
DeploymentTutorial
GLM-OCR Local Deployment: Ollama vs vLLM vs SGLang
Compare different local deployment options for GLM-OCR including Ollama, vLLM, and SGLang. Learn which option is best for your use case.