// Requires an already served Ollama model named llama3.2:3b.
// Requests cannot change the provider, model, endpoint or credential.
// Ctrl+C stops the foreground API.
import aner.api
import aner.llm

let model = llm.client("ollama", "llama3.2:3b")
let app = api.app("Local completion").llm("/generate", model)
    .output_limit(max_tokens: 256).rate_limit(requests_per_minute: 30)
print(app.openapi())
app.serve()