import json import requests # For local streaming, the websockets are hosted without ssl - http:// HOST = 'localhost:5000' URI = f'http://{HOST}/api/v1/chat' # For reverse-proxied streaming, the remote will likely host with ssl - https:// # URI = 'https://your-uri-here.trycloudflare.com/api/v1/generate' def run(user_input, history): request = { 'user_input': user_input, 'history': history, 'mode': 'instruct', # Valid options: 'chat', 'chat-instruct', 'instruct' 'character': 'Example', 'instruction_template': 'Vicuna-v1.1', 'regenerate': False, '_continue': False, 'stop_at_newline': False, 'chat_prompt_size': 2048, 'chat_generation_attempts': 1, 'chat-instruct_command': 'Continue the chat dialogue below. Write a single reply for the character "<|character|>".\n\n<|prompt|>', 'max_new_tokens': 250, 'do_sample': True, 'temperature': 0.7, 'top_p': 0.1, 'typical_p': 1, 'epsilon_cutoff': 0, # In units of 1e-4 'eta_cutoff': 0, # In units of 1e-4 'repetition_penalty': 1.18, 'top_k': 40, 'min_length': 0, 'no_repeat_ngram_size': 0, 'num_beams': 1, 'penalty_alpha': 0, 'length_penalty': 1, 'early_stopping': False, 'seed': -1, 'add_bos_token': True, 'truncation_length': 2048, 'ban_eos_token': False, 'skip_special_tokens': True, 'stopping_strings': [] } response = requests.post(URI, json=request) if response.status_code == 200: result = response.json()['results'][0]['history'] print(json.dumps(result, indent=4)) print() print(result['visible'][-1][1]) if __name__ == '__main__': user_input = "Please give me a step-by-step guide on how to plant a tree in my backyard." # Basic example history = {'internal': [], 'visible': []} # "Continue" example. Make sure to set '_continue' to True above # arr = [user_input, 'Surely, here is'] # history = {'internal': [arr], 'visible': [arr]} run(user_input, history)