Dockerfile

# Usar una imagen base de Python
# FROM --platform=linux/amd64 python:3.11-slim
FROM python:3.11-slim

ENV USE_NNPACK=0
ENV HF_HOME=/app/.cache/huggingface

ENV OMP_NUM_THREADS=1
ENV OPENBLAS_NUM_THREADS=1
ENV MKL_NUM_THREADS=1
ENV NUMEXPR_NUM_THREADS=1

# Establecer el directorio de trabajo en el contenedor
WORKDIR /app

# Instalar dependencias del sistema necesarias para spaCy, Transformers y EasyOCR
RUN apt-get update && apt-get install -y \
    git \
    build-essential \
    python3-dev \
    gcc \
    cmake \
    libglib2.0-0 \
    libsm6 \
    libxext6 \
    libxrender-dev \
    libffi-dev \
    libssl-dev \
    libblas-dev \
    liblapack-dev \
    libopenblas-dev \
    gfortran \
    && rm -rf /var/lib/apt/lists/*

# Copiar los archivos necesarios al contenedor
COPY requirements.txt requirements.txt
# COPY app.py app.py

# Instalar las dependencias
RUN python -m pip install --upgrade pip
# RUN pip install --upgrade pip setuptools
RUN pip install --upgrade setuptools pip wheel cython meson

# Evitar fallos al compilar blis en ARM
ENV BLIS_ARCH=generic

RUN pip install --no-cache-dir -r requirements.txt

# Descargar modelos de spaCy y Transformers en la imagen
RUN python -m spacy download es_core_news_lg
RUN python -c "from transformers import pipeline; pipeline('ner', model='dbmdz/bert-large-cased-finetuned-conll03-english')"

COPY . .

# Exponer el puerto en el que correrá Flask
EXPOSE 5002

# Comando para ejecutar la API
# CMD ["python", "app.py"]
CMD ["gunicorn", "--workers", "2", "--threads", "2", "--timeout", "600", "--bind", "0.0.0.0:5002", "app:create_app()"]