Update Dockerfile

Dockerfile

@@ -1,34 +1,37 @@
-FROM python:3.11-slim
+FROM python:3.10-slim
 
-# System dependencies
-RUN apt-get update && apt-get install -y --no-install-recommends \
-    ffmpeg git \
+# Install build dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    cmake \
+    git \
+    curl \
     && rm -rf /var/lib/apt/lists/*
 
-# Setup user for Hugging Face (UID 1000)
-RUN useradd -m -u 1000 user
-USER user
-ENV PATH="/home/user/.local/bin:$PATH"
-ENV HF_HOME="/home/user/.cache/huggingface"
-
-WORKDIR /home/user/app
-
-# Install dependencies
-RUN pip install --no-cache-dir --upgrade pip && \
-    pip install --no-cache-dir --extra-index-url https://download.pytorch.org/whl/cpu \
-    torch==2.6.0+cpu \
-    transformers>=4.49.0 \
-    accelerate>=1.3.0 \
-    flask==3.1.1 \
-    gunicorn \
-    huggingface_hub>=0.27.0 \
-    edge-tts
-
-# Copy files and create image directory
-COPY --chown=user:user . .
-RUN mkdir -p /home/user/app/img
+# Build llama.cpp from source (CPU only)
+RUN git clone https://github.com/ggerganov/llama.cpp /opt/llama.cpp && \
+    cd /opt/llama.cpp && \
+    mkdir build && \
+    cd build && \
+    cmake .. -DGGML_CUDA=OFF -DGGML_METAL=OFF && \
+    cmake --build . --config Release -j$(nproc)
+
+# The main server binary (new name after recent refactor)
+# It could be: llama-server, llama-cli, or server depending on version
+RUN ls -la /opt/llama.cpp/build/bin/ || ls -la /opt/llama.cpp/build/
+
+# Download a small GGUF model (~1-2B params)
+RUN mkdir -p /opt/models && \
+    curl -L -o /opt/models/smollm2-1.7b-instruct-q4_k_m.gguf \
+    "https://huggingface.co/bartowski/SmolLM2-1.7B-Instruct-GGUF/resolve/main/SmolLM2-1.7B-Instruct-Q4_K_M.gguf"
+
+# Install Python dependencies
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+COPY . .
 
 EXPOSE 7860
 
-# Start with Gunicorn for better stability
-CMD ["gunicorn", "-b", "0.0.0.0:7860", "app:app", "--timeout", "120"]
+CMD ["python", "app.py"]