Update Dockerfile

Dockerfile

@@ -1,48 +1,41 @@
-# Use official Python runtime as base image
-FROM python:3.9-slim
+# 1. Use an official Python image
+FROM python:3.10-slim
 
-# Set working directory
+# 2. Set environment variables to keep things running smoothly
+ENV PYTHONDONTWRITEBYTECODE=1 \
+    PYTHONUNBUFFERED=1 \
+    PORT=7860
+
+# 3. Set the working directory inside the container
 WORKDIR /app
 
-# Install system dependencies required for PDF processing and libraries
-RUN apt-get update && apt-get install -y \
+# 4. Install system tools needed to build certain Python packages (like LanceDB and PyArrow)
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends \
     build-essential \
-    libopenblas-dev \
+    gcc \
     curl \
-    && rm -rf /var/lib/apt/lists/*
-
-# Copy application files
-COPY . /app
-
-# Create requirements.txt with all dependencies
-RUN echo "fastapi==0.104.1\n\
-uvicorn==0.24.0\n\
-aiofiles==23.2.1\n\
-pydantic==2.5.0\n\
-haystack-ai==0.5.0\n\
-sentence-transformers==2.2.2\n\
-lancedb==0.3.11\n\
-pyarrow==14.0.1\n\
-huggingface-hub==0.19.4\n\
-torch==2.1.1\n\
-nltk==3.9.1\n\
-scikit-learn==1.3.2" > requirements.txt
-
-# Install Python dependencies
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Download required NLTK data for text processing
-RUN python -c "import nltk; nltk.download('punkt'); nltk.download('averaged_perceptron_tagger')"
-
-# Create directory for vector database
+    && apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# 5. Create the directory where LanceDB will store its files
 RUN mkdir -p /tmp/data
 
-# Expose port (HuggingFace Spaces uses 7860 by default)
-EXPOSE 7860
+# 6. Copy your requirements.txt first (this speeds up future builds using Docker cache)
+COPY requirements.txt .
+
+# 7. Install all your Python dependencies from your actual requirements.txt
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
 
-# Health check
-HEALTHCHECK --interval=30s --timeout=10s --start-period=40s --retries=3 \
-    CMD curl -f http://localhost:7860/docs || exit 1
+# 8. Pre-download NLTK data so the app doesn't crash trying to download it on startup
+RUN python -c "import nltk; nltk.download('punkt'); nltk.download('punkt_tab'); nltk.download('averaged_perceptron_tagger')"
+
+# 9. Copy the rest of your project files (app.py, loader.py, etc.)
+COPY . .
+
+# 10. Expose the port Hugging Face Spaces expects
+EXPOSE 7860
 
-# Run the application
-CMD ["python", "app.py"]
+# 11. Run your FastAPI app
+CMD ["python", "app.py"]