Dockerfile

FROM python:3.10.9

# Install system dependencies
RUN apt-get update && \
    apt-get install -y \
        tesseract-ocr \
        libtesseract-dev \
        poppler-utils \
        libgl1-mesa-glx && \
    apt-get clean && \
    rm -rf /var/lib/apt/lists/*

# Set MPLCONFIGDIR to avoid Matplotlib caching issues
ENV MPLCONFIGDIR /tmp/matplotlib-cache

# Set TRANSFORMERS_CACHE to a writable directory
ENV TRANSFORMERS_CACHE /tmp/huggingface-cache

# Create a directory for your application
RUN mkdir /app
WORKDIR /app

# Copy your app.py into the container
COPY app.py .
# Install Python dependencies with specific versions
RUN pip install --no-cache-dir \
    chromadb==0.5.3 \
    langchain==0.2.7 \
    langchain-community==0.2.7 \
    langchain-core==0.2.12 \
    langchain-text-splitters==0.2.2 \
    lxml==4.9.4 \
    openai==1.35.10 \
    opencv-python==4.8.0.76 \
    opencv-python-headless==4.10.0.84 \
    pydantic==2.8.0 \
    pydantic-core==2.20.0 \
    pytesseract==0.3.10 \
    tiktoken==0.7.0 \
    unstructured==0.14.9 \
    unstructured-client==0.24.0 \
    unstructured-inference==0.7.36 \
    unstructured.pytesseract==0.3.12 \
    ipython \
    psutil \
    pillow-heif

# # Clone the project from GitHub
# RUN git clone https://github.com/amansoni7477030/fastAPI_production.git /app

# WORKDIR /app

# # Install Python dependencies
# RUN pip install --no-cache-dir --upgrade -r requirements.txt

# # Expose the port on which FastAPI will run
# EXPOSE 7860
# Command to run the app.py script
CMD ["python", "app.py"]
# Command to run the FastAPI server
# CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "7860"]