// Explicit ordered messages, output budget, and sampling settings.
import aner.llm

let model = llm.client(provider: "ollama", model: "llama3.2:3b",
    endpoint: "http://127.0.0.1:11434", timeout_ms: 120000)
let messages = List(
    llm.message(role: "system", content: "Explain concepts precisely and concisely."),
    llm.message(role: "user", content: "Compare a linked list and a fixed array."))
let answer = model.chat(messages, max_tokens: 256, temperature: 0.2)
print(answer.text())
print(answer.model())
print(answer.finish_reason())
print(answer.input_tokens())
print(answer.output_tokens())