import requests import json messages = [ {"role": "user", "content": "helo"}, {"role": "assistant", "content": "Hello! How can I assist you today?"}, {"role": "user", "content": "who are you and give me a breif description of who created you "} ] model = "llama-4-scout-17b" url = "http://127.0.0.1:8000/api/v1/text/generate" payload = { "messages": messages, "model": model, "api_key": "" } response = requests.post(url, json=payload, stream=True) if response.status_code == 200: for line in response.iter_lines(): if line: print(line) decoded_line = line.decode('utf-8') if decoded_line.startswith('data: [DONE]'): break elif decoded_line.startswith('data: '): try: json_data = json.loads(decoded_line[6:]) if json_data["choices"] and "text" in json_data["choices"][0]: print(json_data["choices"][0]["text"], end='') except json.JSONDecodeError: continue else: print(f"Request failed with status code {response.status_code}")