Update Dockerfile

Dockerfile

@@ -1,5 +1,5 @@
-# Use NVIDIA CUDA base image with Ubuntu and Python support
-FROM nvidia/cuda:12.1.1-devel-ubuntu22.04
+# Use NVIDIA CUDA base image with Python support
+FROM nvidia/cuda:12.1.1-runtime-ubuntu22.04
 
 # Set working directory
 WORKDIR /app
@@ -9,26 +9,22 @@ RUN apt-get update && apt-get install -y \
     python3.10 \
     python3-pip \
     python3.10-venv \
-    build-essential \
-    cmake \
     git \
     curl \
     wget \
     && rm -rf /var/lib/apt/lists/*
 
-# Use python3.10 as default
+# Make python3.10 the default
 RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.10 1
 
 # Upgrade pip
 RUN pip install --upgrade pip
 
-# Set CUDA build flag for llama-cpp-python
-ENV CMAKE_ARGS="-DGGML_CUDA=on"
+# ✅ Install prebuilt llama-cpp-python CUDA wheel (cu121)
+RUN pip install --no-cache-dir llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121
 
-# Copy requirements first for layer caching
+# Copy requirements.txt and install remaining dependencies
 COPY requirements.txt .
-
-# Install dependencies (llama-cpp-python will compile with CUDA here)
 RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy app code
@@ -37,12 +33,12 @@ COPY . .
 # Create models directory
 RUN mkdir -p models
 
-# Expose Gradio port
+# Expose Gradio or web port
 EXPOSE 7860
 
-# Environment for Gradio
+# Gradio settings
 ENV GRADIO_SERVER_NAME="0.0.0.0"
 ENV GRADIO_SERVER_PORT=7860
 
-# Run the app
+# Start app
 CMD ["python", "app.py"]