Update Dockerfile

Dockerfile

@@ -1,29 +1,35 @@
-# Use lightweight Python image
-FROM python:3.9-slim
+# Stage 1: Builder for model caching
+FROM python:3.9-slim as builder
+
+WORKDIR /app
+COPY requirements.txt .
 
-# Install system dependencies for transformers
 RUN apt-get update && \
     apt-get install -y --no-install-recommends gcc python3-dev && \
-    rm -rf /var/lib/apt/lists/*
+    pip install --user -r requirements.txt && \
+    python -c "from transformers import pipeline; pipeline('text-generation', model='tiiuae/falcon-7b-instruct')"
+
+# Stage 2: Runtime image
+FROM python:3.9-slim
 
-# Set working directory
 WORKDIR /app
 
-# Install Python dependencies
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
+# Copy only necessary files from builder
+COPY --from=builder /root/.cache /root/.cache
+COPY --from=builder /usr/local/lib/python3.9/site-packages /usr/local/lib/python3.9/site-packages
 
-# Cache the AI model (Falcon-7B)
-RUN python -c """
-from transformers import pipeline
-pipeline('text-generation', model='tiiuae/falcon-7b-instruct')
-"""
+# Install runtime dependencies
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends libgomp1 && \
+    rm -rf /var/lib/apt/lists/*
 
-# Copy application files
+# Copy application code
 COPY app.py text2generation.py ./
 
-# Expose Hugging Face's default port
+# Configure production server
 EXPOSE 7860
+HEALTHCHECK --interval=30s --timeout=30s --start-period=120s --retries=3 \
+    CMD curl -f http://localhost:7860/health || exit 1
 
-# Run the application with Gunicorn for production
-CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--workers", "2", "app:app"]
+# Use gunicorn with 2 workers (optimal for HF Spaces)
+CMD ["gunicorn", "--bind", "0.0.0.0:7860", "--workers", "2", "--timeout", "120", "app:app"]