Dockerfile

# Base Image
FROM python:3.10-slim

ENV DEBIAN_FRONTEND=noninteractive \
    PYTHONUNBUFFERED=1 \
    PYTHONDONTWRITEBYTECODE=1

WORKDIR /code

# System Dependencies
RUN apt-get update && apt-get install -y --no-install-recommends \
    build-essential \
    git \
    curl \
    libopenblas-dev \
    libomp-dev \
    ffmpeg \
    poppler-utils \
    tesseract-ocr \
    tesseract-ocr-eng \
    libgl1 \
    libglib2.0-0 \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements and install Python dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

# Hugging Face + model tools
RUN pip install --no-cache-dir huggingface-hub sentencepiece accelerate

# Hugging Face cache environment
ENV HF_HOME=/models/huggingface \
    TRANSFORMERS_CACHE=/models/huggingface \
    HUGGINGFACE_HUB_CACHE=/models/huggingface \
    HF_HUB_CACHE=/models/huggingface

# Create cache dir and set permissions
RUN mkdir -p /models/huggingface && \
    chown -R 1000:1000 /models/huggingface && \
    chmod -R 755 /models/huggingface

# Create EasyOCR directory
RUN mkdir -p ~/.EasyOCR && \
    chmod 777 ~/.EasyOCR

# Pre-download the model during build
RUN python -c "from transformers import pipeline; import torch; pipe = pipeline('text-generation', model='tiiuae/Falcon3-3B-Instruct', dtype=torch.bfloat16, device_map='cpu', model_kwargs={'low_cpu_mem_usage': False})" && \
    chown -R 1000:1000 /models/huggingface && \
    chmod -R 755 /models/huggingface || true

# Copy project files
COPY . .

EXPOSE 7860

CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]