Update Dockerfile

Dockerfile

@@ -2,42 +2,23 @@ FROM python:3.10-slim
 
 WORKDIR /code
 
-# Install system dependencies
+# Install build dependencies for llama-cpp-python
 RUN apt-get update && apt-get install -y \
     build-essential \
-    curl \
     git \
+    cmake \
     && rm -rf /var/lib/apt/lists/*
 
-# Copy requirements first for better caching
+# Copy requirements first
 COPY requirements.txt .
 
-# Install Python dependencies
-RUN pip install --no-cache-dir -r requirements.txt
+# Install with specific BLAS backend for better performance
+RUN CMAKE_ARGS="-DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS" \
+    pip install --no-cache-dir -r requirements.txt
 
-# Download model during build (optional - can also download at runtime)
-ARG HF_TOKEN=""
-RUN if [ -n "$HF_TOKEN" ]; then \
-    python -c "from huggingface_hub import hf_hub_download; \
-    hf_hub_download(repo_id='bartowski/Phi-3.1-mini-4k-instruct-GGUF', \
-    filename='Phi-3.1-mini-4k-instruct-IQ2_M.gguf', \
-    local_dir='/code', token='$HF_TOKEN')"; \
-    else \
-    echo "HF_TOKEN not provided, model will download at runtime"; \
-    fi
-
-# Copy application code
+# Copy app
 COPY app.py .
 
-# Create a directory for models if it doesn't exist
-RUN mkdir -p /code
-
-# Expose port (Hugging Face Spaces uses 7860)
 EXPOSE 7860
 
-# Health check
-HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
-    CMD curl -f http://localhost:7860/health || exit 1
-
-# Run the app
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]