Update Dockerfile

Dockerfile

@@ -1,40 +1,52 @@
+# Use official Python 3.12 image
 FROM python:3.12-slim
 
+# Set working directory
 WORKDIR /app
 
-# Install minimal system dependencies
+# Install system dependencies
 RUN apt-get update && apt-get install -y \
+    build-essential \
+    curl \
     git \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements first for better caching
-COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-RUN python -m spacy download en_core_web_sm
-
-# Verify transformers installation and explicitly install if needed
-RUN pip install --no-cache-dir transformers[torch] pytorch-transformers
-
-# Pre-download model with simplified import approach
-RUN python -c "from transformers import pipeline; \
-    nlp = pipeline('question-answering', model='deepset/deberta-v3-base-squad2', cache_dir='/tmp/huggingface');"
-
-# Create accessible directories
+# Create directories with proper permissions
 RUN mkdir -p /tmp/uploads /tmp/huggingface \
     && chmod -R 777 /tmp/uploads /tmp/huggingface
 
-# Streamlit config
-RUN mkdir -p .streamlit && echo '[server]\nenableCORS=false\nenableXsrfProtection=false\n\n[browser]\nserverAddress="0.0.0.0"\nserverPort=7860' > .streamlit/config.toml
-
-# Environment variables
-ENV TRANSFORMERS_CACHE=/tmp/huggingface
-ENV HF_HOME=/tmp/huggingface
+# Set environment variables
 ENV PYTHONUNBUFFERED=1
 ENV UPLOAD_FOLDER=/tmp/uploads
+ENV TRANSFORMERS_CACHE=/tmp/huggingface
+ENV HF_HOME=/tmp/huggingface
+
+# Copy requirements file first to leverage Docker cache
+COPY requirements.txt .
+
+# Install Python dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Install spaCy model
+RUN python -m spacy download en_core_web_sm
+
+# Pre-download Hugging Face models and tokenizers
+RUN python -c "\
+from transformers import AutoTokenizer; \
+AutoTokenizer.from_pretrained('deepset/deberta-v3-base-squad2', cache_dir='/tmp/huggingface'); \
+AutoTokenizer.from_pretrained('distilbert-base-uncased', cache_dir='/tmp/huggingface')"
+
+# Create Streamlit config
+RUN mkdir -p .streamlit && \
+    echo '[server]\n\
+enableCORS=false\n\
+enableXsrfProtection=false\n' > .streamlit/config.toml
 
-# Copy app code
+# Copy application code
 COPY . .
 
+# Expose port
 EXPOSE 7860
 
+# Run the application
 CMD ["streamlit", "run", "app.py", "--server.port=7860", "--server.address=0.0.0.0"]