docs: add effi-ocr-legacy for OCR comparison

effi-ocr runs on port 8301 alongside Kreuzberg on 8300 for quality comparison
This commit is contained in:
Folzo
2026-04-11 01:04:48 +02:00
parent e9d6de3513
commit e4009f22ce
7 changed files with 748 additions and 0 deletions
+20
View File
@@ -0,0 +1,20 @@
FROM python:3.11-slim
# Installer Tesseract et les langues
RUN apt-get update && apt-get install -y \
tesseract-ocr \
tesseract-ocr-fra \
tesseract-ocr-eng \
libtesseract-dev \
&& rm -rf /var/lib/apt/lists/*
# Créer le répertoire de travail
WORKDIR /app
# Copier les dépendances
COPY requirements.txt .
# Installer les dépendances Python
RUN pip install --no-cache-dir -r requirements.txt
# Copier le code
COPY main.py .
# Exposer le port
EXPOSE 8300
# Lancer l'application
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8300"]