fix(build): remove ollama from dockerfile & add cpu wheel index

Dockerfile

@@ -1,10 +1,7 @@
 FROM python:3.10-slim
 
 # System setup
-RUN apt-get update && apt-get install -y curl procps zstd && rm -rf /var/lib/apt/lists/*
-
-# Install Ollama via official script
-RUN curl -fsSL https://ollama.com/install.sh | sh
+RUN apt-get update && apt-get install -y procps zstd && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 COPY requirements.txt .
@@ -14,12 +11,7 @@ COPY . .
 
 # Environment Variables
 ENV PORT=8080
-ENV OLLAMA_HOST=127.0.0.1:11434
 ENV PYTHONUNBUFFERED=1
 
-# Execution Script: Starts Ollama, pulls Llama 3.2 (3B - Optimal for CPU), starts App
-RUN echo '#!/bin/bash\nollama serve & sleep 10 && ollama pull llama3.2 && python app.py' > /app/run.sh && \
-    chmod +x /app/run.sh
-
 EXPOSE 8080
-CMD ["/app/run.sh"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "8080"]

requirements.txt

@@ -6,4 +6,6 @@ python-dotenv
 openai
 groq
 google-generativeai
+--extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 llama-cpp-python
+