Update Dockerfile

Dockerfile

@@ -1,34 +1,39 @@
 FROM python:3.11-slim
 
-WORKDIR /app
-
+# Install build dependencies for llama-cpp-python
 RUN apt-get update && apt-get install -y \
     build-essential \
     cmake \
-    git \
     curl \
+    git \
+    wget \
     && rm -rf /var/lib/apt/lists/*
 
+# Create app directory
+WORKDIR /app
+
+# Create model directory
+RUN mkdir -p /app/models
+
+# Copy requirements first for caching
 COPY requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Download Qwen3-0.6B GGUF model
-RUN python -c "from huggingface_hub import hf_hub_download; \
-    import os; \
-    os.makedirs('/app/models', exist_ok=True); \
-    hf_hub_download( \
-        repo_id='unsloth/Qwen3-0.6B-GGUF', \
-        filename='Qwen3-0.6B-Q4_K_M.gguf', \
-        local_dir='/app/models', \
-        local_dir_use_symlinks=False, \
-        resume_download=True \
-    ); \
-    size = os.path.getsize('/app/models/Qwen3-0.6B-Q4_K_M.gguf'); \
-    print(f'Model size: {size/1024/1024:.1f} MB'); \
-    assert size > 300000000, f'Model download incomplete: {size} bytes'"
-
-COPY . .
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir -r requirements.txt
+
+# Download the GGUF model (Q4_K_M quantization - good balance of quality and speed)
+RUN wget -q "https://huggingface.co/unsloth/Qwen3-0.6B-GGUF/resolve/main/Qwen3-0.6B-Q4_K_M.gguf" \
+    -O /app/models/Qwen3-0.6B-Q4_K_M.gguf
 
+# Copy application code
+COPY server.py .
+COPY templates/ templates/
+
+# HuggingFace Spaces uses port 7860
 EXPOSE 7860
 
-CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "1"]
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+ENV MODEL_PATH=/app/models/Qwen3-0.6B-Q4_K_M.gguf
+
+# Run the server
+CMD ["python", "server.py"]