Deploy FastAPI on Hugging Face

Dockerfile

@@ -1,26 +1,30 @@
-# Use official Python slim image
-FROM python:3.9-slim
+# Use a newer Python version for better wheel support
+FROM python:3.10-slim
 
-# Install Java Runtime Environment (REQUIRED for tabula-py to process PDFs)
+# Install a LIGHTER Java Runtime (Headless is much faster to install)
 RUN apt-get update && \
-    apt-get install -y --no-install-recommends default-jre && \
+    apt-get install -y --no-install-recommends openjdk-17-jre-headless && \
     apt-get clean && \
     rm -rf /var/lib/apt/lists/*
 
-# Set working directory
-WORKDIR /app
+# Set up a non-root user (Hugging Face standard)
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:$PATH
+WORKDIR $HOME/app
 
 # Set PYTHONPATH to ensure imports work correctly
-ENV PYTHONPATH=/app
+ENV PYTHONPATH=$HOME/app
 
-# Copy requirements and install
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# Copy requirements first to leverage Docker cache
+COPY --chown=user requirements.txt .
+RUN pip install --no-cache-dir --user -r requirements.txt
 
 # Copy the rest of the application
-COPY . .
+COPY --chown=user . .
 
-# Create necessary directories (though the app is configured not to save, logic uses them)
+# Create necessary directories
 RUN mkdir -p data/raw_csv_temp data/output_process_data data/strictly_cleaned_data data/output data/save_pdf logs
 
 # Expose port 7860 (Hugging Face default)

requirements.txt

@@ -16,8 +16,3 @@ fpdf2>=2.7.0
 # Visualization (if needed for exports)
 matplotlib>=3.4.0
 seaborn>=0.11.0
-
-# Development
-pytest>=6.2.0
-black>=21.0.0
-flake8>=3.9.0