Dockerfile

# Use Python 3.11 slim image for better compatibility with HF Spaces
FROM python:3.11-slim

# Set working directory
WORKDIR /app

# Install system dependencies
RUN apt-get update && apt-get install -y \
    git \
    curl \
    build-essential \
    && rm -rf /var/lib/apt/lists/*

# Copy requirements first for better Docker layer caching
COPY requirements.txt .

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

# Copy application files
COPY . .

# Create directories for models and cache
RUN mkdir -p /app/cache /app/models

# Set environment variables for HF Spaces
ENV PYTHONPATH=/app
ENV PYTHONUNBUFFERED=1
ENV HF_HOME=/app/cache
ENV TRANSFORMERS_CACHE=/app/cache
ENV TORCH_HOME=/app/cache

# Pre-download models to reduce startup time
RUN python -c "\
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM, AutoModelForSequenceClassification; \
import torch; \
print('📦 Pre-downloading DistilGPT-2...'); \
tokenizer = AutoTokenizer.from_pretrained('distilgpt2'); \
model = AutoModelForCausalLM.from_pretrained('distilgpt2'); \
print('📦 Pre-downloading RoBERTa sentiment model...'); \
sentiment_model = AutoModelForSequenceClassification.from_pretrained('cardiffnlp/twitter-roberta-base-sentiment-latest'); \
sentiment_tokenizer = AutoTokenizer.from_pretrained('cardiffnlp/twitter-roberta-base-sentiment-latest'); \
print('✅ Models downloaded successfully!')"

# Expose port 7860 (HF Spaces default)
EXPOSE 7860

# Health check
HEALTHCHECK --interval=30s --timeout=30s --start-period=60s --retries=3 \
    CMD curl -f http://localhost:7860/health || exit 1

# Run the application
CMD ["python", "app.py"]