Update Dockerfile

Dockerfile

@@ -1,4 +1,4 @@
-# Use the official Hugging Face Docker image as base
+# Hugging Face Spaces optimized image
 FROM python:3.9-slim
 
 # Set environment variables
@@ -9,7 +9,9 @@ ENV PYTHONDONTWRITEBYTECODE=1 \
     PIP_NO_CACHE_DIR=1 \
     PORT=8000
 
-# Create and set working directory
+# Create directory structure
+RUN mkdir -p /app/{data,src,config,templates,static/css,tests}
+
 WORKDIR /app
 
 # Install system dependencies
@@ -17,31 +19,42 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
     build-essential \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements first for better caching
+# Copy requirements first for caching
 COPY requirements.txt .
 
 # Install Python dependencies
 RUN pip install --upgrade pip && \
     pip install --no-cache-dir -r requirements.txt
 
-# Copy the rest of the application
-COPY . .
+# 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/
 
-# Create necessary directories
-RUN mkdir -p /app/data /cache
+# Copy data files with correct permissions
+COPY --chown=1000:1000 data/ /app/data/
 
-# Download models during build (optional)
+# Verify data files
 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'); \
-except Exception as e: \
-    print(f'Model preloading failed: {str(e)}'); \
-    raise \
+import os, json; \
+assert os.path.exists('/app/data/rupeia_document.json'), 'Data file missing'; \
+assert os.path.exists('/app/data/chat_history.json'), 'History file missing' \
 "
 
-# Run the application
+# Download models during build
+RUN python -c "\
+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') \
+"
+
+# Set proper permissions
+RUN chmod a+r /app/data/*.json && \
+    find /app -type d -exec chmod a+rx {} \;
+
 CMD gunicorn --bind 0.0.0.0:$PORT --workers 2 --timeout 120 --preload app:app