Run OpenAI open models locally with Ollama or LM Studio

from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="ollama"  # required but unused
)

response = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[{"role": "user", "content": "Explain quantum entanglement simply."}]
)
print(response.choices[0].message.content)

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather in a given city",
            "parameters": {
                "type": "object",
                "properties": {"city": {"type": "string"}},
                "required": ["city"]
            },
        },
    }
]

response = client.chat.completions.create(
    model="gpt-oss-20b",
    messages=[{"role": "user", "content": "What's the weather in Berlin right now?"}],
    tools=tools
)

print(response.choices[0].message)

import asyncio
from agents import Agent, Runner, function_tool, set_tracing_disabled
from agents.extensions.models.litellm_model import LitellmModel

set_tracing_disabled(True)

@function_tool
def get_weather(city: str):
    return f"The weather in {city} is sunny."

async def main():
    agent = Agent(
        name="Assistant",
        instructions="You are a helpful assistant.",
        model=LitellmModel(model="ollama/gpt-oss-20b", api_key="ollama"),
        tools=[get_weather],
    )
    result = await Runner.run(agent, "What's the weather in Tokyo?")
    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(main())