import requests URL = "http://localhost:8080/v1/chat/completions" messages = [] while True: user_input = input("You: ") if user_input.lower() in {"exit", "quit"}: break messages.append({ "role": "user", "content": user_input }) response = requests.post( URL, json={ "messages": messages, "max_tokens": 256, "temperature": 0.7, } ) if not response.ok: print("Server error: ", response.text) continue data = response.json() answer = data["choices"][0]["message"]["content"] print(f"Agent: {answer}") messages.append({ "role": "assistant", "content": answer })