Pi Agent: Multi-Platform Deployment & llama.cpp

python -m venv .venv
source .venv/bin/activate  # macOS/Linux
# .venv\Scripts\activate   # Windows

pip install pi-agent

from pi_agent import Agent

agent = Agent(name="app_agent", config_file=".pi-agent.yaml")

def process_request(user_input: str) -> str:
    return agent.chat(user_input)

FROM python:3.11-slim

WORKDIR /app

COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt

COPY . .

ENV PI_DEEPSEEK_API_KEY=""
ENV PI_DEFAULT_PROVIDER=deepseek

CMD ["python", "agent_service.py"]

version: "3.8"
services:
  pi-agent:
    build: .
    ports:
      - "8000:8000"
    environment:
      - PI_DEEPSEEK_API_KEY=${PI_DEEPSEEK_API_KEY}
    volumes:
      - ./sessions:/app/sessions
    restart: unless-stopped

# /etc/systemd/system/pi-agent.service
[Unit]
Description=Pi Agent Service
After=network.target

[Service]
Type=simple
User=piagent
WorkingDirectory=/opt/pi-agent
Environment=PI_DEEPSEEK_API_KEY=sk-xxxxxxxx
ExecStart=/opt/pi-agent/.venv/bin/python agent_service.py
Restart=always

[Install]
WantedBy=multi-user.target

# macOS
brew install llama.cpp

# Linux
git clone https://github.com/ggerganov/llama.cpp
cd llama.cpp && make

# تحميل نماذج بصيغة GGUF من Hugging Face
wget https://huggingface.co/Qwen/Qwen2.5-7B-Instruct-GGUF/resolve/main/qwen2.5-7b-instruct-q4_k_m.gguf

providers:
  local:
    type: llama_cpp
    model_path: "./models/qwen2.5-7b-instruct-q4_k_m.gguf"
    n_gpu_layers: -1
    n_ctx: 4096
    temperature: 0.7

default_provider: local

curl -fsSL https://ollama.com/install.sh | sh

ollama pull qwen2.5:7b
ollama pull llama3:8b

providers:
  ollama:
    type: ollama
    base_url: "http://localhost:11434"
    model: "qwen2.5:7b"

from pi_agent import Agent

models = {
    "qwen2.5-7b": Agent(provider="ollama", model="qwen2.5:7b"),
    "llama3-8b": Agent(provider="ollama", model="llama3:8b"),
}

question = "Implement quicksort in Python"

for name, agent in models.items():
    print(f"=== {name} ===")
    result = agent.chat(question)
    print(result[:200])