ERP-DocIQ / scripts /test_ocr.py
kenmandal's picture
Deploy latest: ERP DocIQ NLQ chatbot + reasoning models (MiniCPM3-4B/Command R7B) + ERP fine-tuning + extreme OCR docs
082d661 verified
Raw
History Blame Contribute Delete
1.69 kB
#!/usr/bin/env python3
"""Quick OCR backend tester.
python scripts/test_ocr.py <sample_id_or_path> [--backend auto|minicpm|cohere|llamaparse|tesseract|easyocr|sidecar]
Examples:
python scripts/test_ocr.py invoice_scanned_basic
python scripts/test_ocr.py invoice_scanned_basic --backend minicpm
python scripts/test_ocr.py /path/to/receipt.png --backend cohere
"""
from __future__ import annotations
import argparse
import sys
from pathlib import Path
ROOT = Path(__file__).resolve().parent.parent
sys.path.insert(0, str(ROOT / "backend"))
from app.config import get_settings # noqa: E402
from app.ocr.backends import build_ocr_registry # noqa: E402
def resolve(arg: str, settings) -> Path | None:
p = Path(arg)
if p.exists():
return p
for ext in (".pdf", ".png", ".jpg", ".jpeg"):
cand = settings.evals_dataset_dir / f"{arg}{ext}"
if cand.exists():
return cand
return None
def main() -> None:
ap = argparse.ArgumentParser()
ap.add_argument("doc")
ap.add_argument("--backend", default="auto")
args = ap.parse_args()
s = get_settings()
path = resolve(args.doc, s)
if not path:
print(f"not found: {args.doc}")
sys.exit(1)
reg = build_ocr_registry(s)
print(f"available backends: {reg.available_names()}")
res, attempts = reg.extract(path, args.backend)
print(f"\nattempts: {attempts}")
print(f"\nengine={res.engine} tier={res.tier} pages={res.pages} "
f"conf={res.confidence} chars={len(res.text)} simulated={res.simulated}")
print("\n--- text (first 1200 chars) ---")
print(res.text[:1200])
if __name__ == "__main__":
main()