examples/single_image.py

"""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()