Files
LegacyHUB/app/ingestion/ocr.py
Vadim Malanov 4fcec8039b
Some checks failed
CI / Backend (lint + tests + compose) (push) Has been cancelled
CI / Frontend (lint + type-check + build) (push) Has been cancelled
chore: pin document recognition engine
2026-06-25 11:43:29 +03:00

23 lines
666 B
Python

"""LegacyHUB adapter for the shared document recognition engine."""
from __future__ import annotations
from pathlib import Path
from teamhub_document_recognition_engine import OcrResult
from teamhub_document_recognition_engine import run_ocr as _engine_run_ocr
from app.config import settings
def run_ocr(input_pdf: Path, output_pdf: Path, languages: str | None = None) -> OcrResult:
return _engine_run_ocr(
input_pdf,
output_pdf,
languages=languages or settings.ocr_languages,
enabled=settings.ocr_enabled,
deskew=settings.ocr_deskew,
clean=settings.ocr_clean,
optimize=settings.ocr_optimize,
)