Function Calling & Agents

llama-server -hf LiquidAI/LFM2.5-1.2B-Instruct-GGUF:Q4_K_M -c 8192 --port 8080 --jinja

import json
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8080/v1", api_key="not-needed")

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get the current weather for a city.",
        "parameters": {
            "type": "object",
            "properties": {
                "city": {"type": "string", "description": "City name, e.g. 'Paris'"},
                "unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
            },
            "required": ["city"],
        },
    },
}]

messages = [{"role": "user", "content": "What's the weather like in Paris right now?"}]

response = client.chat.completions.create(
    model="lfm2.5-1.2b-instruct",
    messages=messages,
    tools=tools,
    tool_choice="auto",
    temperature=0.1,
    max_tokens=512,
    extra_body={"top_k": 50, "repeat_penalty": 1.05},
)

message = response.choices[0].message
for call in message.tool_calls or []:
    print(call.function.name, json.loads(call.function.arguments))
# get_weather {'city': 'Paris'}

def get_weather(city: str, unit: str = "celsius") -> dict:
    # Replace with a real API call.
    return {"city": city, "temperature": 21, "unit": unit, "condition": "sunny"}

TOOL_IMPLS = {"get_weather": get_weather}

def run_agent(user_text: str, max_steps: int = 5) -> str:
    messages = [
        {"role": "system", "content": "You are a helpful assistant. Use tools when they help."},
        {"role": "user", "content": user_text},
    ]
    for _ in range(max_steps):
        response = client.chat.completions.create(
            model="lfm2.5-1.2b-instruct",
            messages=messages,
            tools=tools,
            temperature=0.1,
            max_tokens=512,
            extra_body={"top_k": 50, "repeat_penalty": 1.05},
        )
        message = response.choices[0].message
        messages.append(message)                      # keep the assistant turn (incl. tool_calls)

        if not message.tool_calls:
            return message.content                    # final answer

        for call in message.tool_calls:               # LFM2.5 may request several calls at once
            args = json.loads(call.function.arguments)
            result = TOOL_IMPLS[call.function.name](**args)
            messages.append({
                "role": "tool",
                "tool_call_id": call.id,
                "content": json.dumps(result),
            })
    return "Stopped after too many tool calls."

print(run_agent("What's the weather like in Paris right now?"))