Update Dockerfile

Dockerfile

@@ -1,62 +1,88 @@
-# Hugging Face Spaces optimized image
-FROM python:3.9-slim
+# Official Python base image with explicit version
+FROM python:3.9-slim-buster@sha256:5f2c93f5369d1f41a7b41024bebf5db3e2227ba6830ff8ddb0a5e3a0c5cef8e9
 
-# Set environment variables
+# ===== SYSTEM CONFIGURATION =====
 ENV PYTHONDONTWRITEBYTECODE=1 \
     PYTHONUNBUFFERED=1 \
+    PORT=8000 \
     HF_HOME=/cache \
     HUGGINGFACE_HUB_CACHE=/cache \
     PIP_NO_CACHE_DIR=1 \
-    PORT=8000
-
-# Create directory structure
-RUN mkdir -p /app/{data,src,config,templates,static/css,tests}
+    TOKENIZERS_PARALLELISM=false
 
+# ===== APPLICATION SETUP =====
 WORKDIR /app
 
-# Install system dependencies
+# Create directory structure matching your project
+RUN mkdir -p \
+    /app/data \
+    /app/src \
+    /app/config \
+    /app/templates \
+    /app/static/css \
+    /app/tests \
+    /cache
+
+# ===== DEPENDENCY INSTALLATION =====
+# Install system dependencies in single layer
 RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements first for caching
+# Copy and install Python requirements
 COPY requirements.txt .
-
-# Install Python dependencies
 RUN pip install --upgrade pip && \
-    pip install --no-cache-dir -r requirements.txt
-
-# Copy application files
-COPY app.py .
-COPY src/ /app/src/
-COPY config/ /app/config/
-COPY templates/ /app/templates/
-COPY static/ /app/static/
-COPY tests/ /app/tests/
-
-# Copy data files with correct permissions
-COPY --chown=1000:1000 data/ /app/data/
-
-# Debug: List files in /app/data/
-RUN ls -l /app/data/
+    pip install --no-cache-dir -r requirements.txt && \
+    pip cache purge
 
-# Verify data files or create chat_history.json if missing
-RUN python -c "import os, json; \
-    assert os.path.exists('/app/data/rupeia_document.json'), 'Data file missing'; \
-    if not os.path.exists('/app/data/chat_history.json'): \
-        open('/app/data/chat_history.json', 'w').write('{}')"
-
-# Download models during build
+# ===== MODEL PRELOADING =====
+# Pre-download models with error handling
 RUN python -c "\
+try: \
     from sentence_transformers import SentenceTransformer; \
     SentenceTransformer('all-MiniLM-L6-v2', cache_folder='/cache'); \
     from transformers import AutoModelForCausalLM, AutoTokenizer; \
     AutoModelForCausalLM.from_pretrained('distilgpt2', cache_dir='/cache'); \
-    AutoTokenizer.from_pretrained('distilgpt2', cache_dir='/cache') \
-    "
+    AutoTokenizer.from_pretrained('distilgpt2', cache_dir='/cache'); \
+except Exception as e: \
+    print(f'Model preloading failed: {str(e)}'); \
+    exit(1) \
+"
+
+# ===== APPLICATION FILES =====
+# Copy application code with proper permissions
+COPY --chown=1000:1000 \
+    app.py \
+    src/ \
+    config/ \
+    templates/ \
+    static/ \
+    tests/ \
+    ./
+
+# Copy data files separately with strict permissions
+COPY --chown=1000:1000 data/ /app/data/
+RUN chmod 644 /app/data/*.json
+
+# ===== RUNTIME CONFIGURATION =====
+# Health check (HTTP, not HTTPS)
+HEALTHCHECK --interval=30s --timeout=5s --retries=3 \
+    CMD curl -f http://localhost:$PORT/health || exit 1
+
+EXPOSE $PORT
 
-# Set proper permissions
-RUN chmod a+r /app/data/*.json && \
-    find /app -type d -exec chmod a+rx {} \;
+# Run as non-root user
+USER 1000
 
-CMD gunicorn --bind 0.0.0.0:$PORT --workers 2 --timeout 120 --preload app:app
+# Optimized Gunicorn configuration for Spaces
+CMD ["gunicorn", \
+    "--bind", "0.0.0.0:$PORT", \
+    "--workers", "2", \
+    "--threads", "2", \
+    "--timeout", "120", \
+    "--preload", \
+    "--worker-class", "gthread", \
+    "--access-logfile", "-", \
+    "--error-logfile", "-", \
+    "--log-level", "info", \
+    "app:app"]