Your coding model, on your machine

ollama pull qwen2.5-coder:7b

curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "qwen2.5-coder:7b",
       "messages": [{"role": "user", "content": "Write a Python function that reverses a string"}]}'

from openai import OpenAI

# The client requires a key; Ollama ignores it.
client = OpenAI(base_url="http://localhost:11434/v1", api_key="ollama")

reply = client.chat.completions.create(
    model="qwen2.5-coder:7b",
    messages=[{"role": "user", "content": "Explain this error: KeyError on line 12"}],
)
print(reply.choices[0].message.content)