File size: 1,123 Bytes
fd0c04f 6708e4d fd0c04f | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 | """Example: OCR a single image file."""
from unlimited_ocr import OCRPipeline
# Initialize the pipeline (model loads lazily on first inference)
pipeline = OCRPipeline(
model_path="AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-MXFP8",
verbose=True,
)
# --- Basic document OCR ---
result = pipeline.run("your_document.jpg", format="text")
print(result)
# --- Markdown output ---
result = pipeline.run("your_document.jpg", format="markdown", output_path="output.md")
print("Saved to output.md")
# --- With bounding boxes (grounding mode) ---
result = pipeline.run("your_document.jpg", format="json", grounding=True)
print(result)
# --- With image preprocessing (deskew + contrast enhancement) ---
result = pipeline.run("scanned_page.png", format="text", preprocess=True)
print(result)
# --- Different task types ---
# "document" — general document parsing (default)
# "markdown" — convert to markdown structure
# "figure" — parse figures/diagrams
# "free" — free-form OCR
result = pipeline.run("table.png", task="markdown", format="markdown")
print(result)
# Clean up temporary files
pipeline.cleanup()
|