Dockerfile

# 1. Use Python 3.11 (Required for GECToR)
FROM python:3.11-slim

# 2. Install System Tools & Java 21
RUN apt-get update && \
    apt-get install -y \
    git \
    wget \
    openjdk-21-jre-headless \
    build-essential \
    python3-dev \
    gcc \
    && apt-get clean

ENV JAVA_HOME=/usr/lib/jvm/java-21-openjdk-amd64

# 3. Setup Directories
WORKDIR /app
ENV XDG_CACHE_HOME=/app/cache
ENV TRANSFORMERS_CACHE=/app/cache
ENV HF_HOME=/app/cache
RUN mkdir -p /app/cache && chmod 777 /app/cache

# 4. Install Python Dependencies
COPY requirements.txt .
RUN pip install --no-cache-dir --upgrade pip && \
    pip install --no-cache-dir -r requirements.txt

# 5. Setup data directory
RUN mkdir -p /app/data

# 5a. Download verb dictionary (needed by GECToR)
# If you already have this file in your repo, this will just overwrite with same content.
RUN echo "Downloading verb-form-vocab.txt for GECToR..." && \
    wget -O /app/data/verb-form-vocab.txt \
    https://github.com/grammarly/gector/raw/master/data/verb-form-vocab.txt

# 6. Copy App Code
COPY . .

# 7. Run App
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]