File size: 1,182 Bytes
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 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 | """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()
|