Skip to main content

​
What is DeepSeek OCR?

DeepSeek OCR provides optimized batch processing for multi-page PDFs, processing all pages in a single batch for better performance.

​
Usage

from upsonic.ocr import OCR
from upsonic.ocr.deepseek import DeepSeekOCR

# Create DeepSeek OCR
ocr = OCR(
    DeepSeekOCR,
    model_name="deepseek-ai/DeepSeek-OCR",
    temperature=0.0,
    max_tokens=8192
)

# Automatically uses batch processing for PDFs
result = ocr.process_file('multi_page_document.pdf')
print(f"Processed {result.page_count} pages")

​
Parameters

ParameterTypeDefaultDescription
model_namestr"deepseek-ai/DeepSeek-OCR"DeepSeek model identifier
temperaturefloat0.0Sampling temperature for generation
max_tokensint8192Maximum tokens per request

​
Features

  • Batch Processing: Processes multiple PDF pages in a single batch
  • High Accuracy: Leverages advanced language models for text extraction
  • Multi-page Support: Optimized for multi-page document processing