Dockerfile

FROM python:3.10

WORKDIR /code

# 1. Install system dependencies required for numpy
RUN apt-get update && apt-get install -y \
    build-essential \
    libatlas-base-dev \
    gfortran \
    libblas-dev \
    liblapack-dev

# 2. Clean cache and install numpy first to lock ABI
RUN pip install --no-cache-dir numpy==1.23.5

# 3. Install spacy and thinc using binary wheels
RUN pip install --no-cache-dir spacy==3.5.4 thinc==8.1.10 && \
    python -m spacy download en_core_web_sm

# 4. Copy requirements and install rest of the packages
COPY requirements.txt . 
RUN pip install --no-cache-dir -r requirements.txt

# Setup NLTK
ENV NLTK_DATA=/code/nltk_data
RUN mkdir -p $NLTK_DATA && \
    python -m nltk.downloader -d $NLTK_DATA stopwords wordnet

# 5. Copy all project files
COPY . .

# 6. Force reinstall numpy to ensure internal _core module is intact
RUN pip install --force-reinstall --no-cache-dir numpy==1.23.5

# 7. Debugging step: Verify numpy version
RUN python -c "import numpy; print('Numpy version:', numpy.__version__); print('Numpy location:', numpy.__file__)"

EXPOSE 7860

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