examples/multi_page_pdf.py

"""Example: OCR a multi-page PDF document."""

from unlimited_ocr import OCRPipeline

# Initialize the pipeline
pipeline = OCRPipeline(
    model_path="AutomatosX/AX-Unlimited-OCR-3B-MoE-MLX-MXFP8",
    verbose=True,
)

# --- Basic PDF OCR (all pages) ---
result = pipeline.run("your_document.pdf", format="text", dpi=300)
print(result)

# --- Save as Markdown with page headings ---
result = pipeline.run(
    "your_document.pdf",
    format="markdown",
    dpi=300,
    output_path="output.md",
)
print("Saved to output.md")

# --- JSON output with per-page structure ---
result = pipeline.run(
    "your_document.pdf",
    format="json",
    dpi=300,
    output_path="output.json",
)
print("Saved to output.json")

# --- With preprocessing for scanned PDFs ---
result = pipeline.run(
    "scanned_document.pdf",
    format="text",
    preprocess=True,  # deskew + contrast enhancement per page
    dpi=300,
)
print(result)

# --- With progress tracking ---
def on_progress(current, total):
    print(f"  Processing page {current}/{total}...")

result = pipeline.run(
    "long_document.pdf",
    format="text",
    progress_callback=on_progress,
)

# Clean up
pipeline.cleanup()