Optimize: Use pre-built llama-cpp-python wheels for faster builds

Dockerfile

@@ -7,10 +7,16 @@ RUN apt-get update && apt-get install -y \
     gcc \
     g++ \
     make \
+    wget \
     && rm -rf /var/lib/apt/lists/*
 
 # Copy requirements and install
 COPY requirements.txt .
+
+# Install llama-cpp-python with pre-built wheels (much faster)
+RUN pip install --no-cache-dir llama-cpp-python==0.3.14 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
+
+# Install remaining requirements
 RUN pip install --no-cache-dir -r requirements.txt
 
 # Copy application code

requirements.txt

@@ -37,7 +37,7 @@ joblib==1.5.1
 jsonschema==4.25.0
 jsonschema-specifications==2025.4.1
 kubernetes==33.1.0
-llama_cpp_python==0.3.14
+# llama_cpp_python is installed separately with pre-built wheels in Dockerfile
 markdown-it-py==3.0.0
 MarkupSafe==3.0.2
 mdurl==0.1.2