import openai import tiktoken import concurrent import collections import threading import datetime import time import pytz import json import os openai.api_keys = os.getenv('API_KEYs').split("\n") openai.api_key = openai.api_keys[0] #print(os.getenv('API_KEYs')) timezone = pytz.timezone('Asia/Shanghai') timestamp2string = lambda timestamp: datetime.datetime.fromtimestamp(timestamp).astimezone(timezone).strftime('%Y-%m-%d %H:%M:%S') def num_tokens_from_messages(messages, model="gpt-3.5-turbo"): """Returns the number of tokens used by a list of messages.""" try: encoding = tiktoken.encoding_for_model(model) except KeyError: encoding = tiktoken.get_encoding("cl100k_base") if model == "gpt-3.5-turbo": # note: future models may deviate from this num_tokens = 0 len_values = 0 for message in messages: num_tokens += 4 # every message follows {role/name}\n{content}\n for key, value in message.items(): try: num_tokens += len(encoding.encode(value)) except: num_tokens += int(num_tokens/len_values*len(value)) # linear estimation len_values += len(value) if key == "name": # if there's a name, the role is omitted num_tokens += -1 # role is always required and always 1 token num_tokens += 2 # every reply is primed with assistant return num_tokens else: raise NotImplementedError(f"""num_tokens_from_messages() is not presently implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens.""") def read_qs(): qs, qas = [], [] directory = "./dialogues_set" filenames = [ 'dialogues_film.json', 'dialogues_jindong.json', 'dialogues_music.json', 'dialogues_natural.json', 'dialogues_taobao.json', 'dialogues_travel_kd.json' ] for filename in filenames: with open(f"{directory}/{filename}", "r", encoding="utf-8") as f: for idx,line in enumerate(f): idx2query = json.loads(line) query = idx2query[str(idx)] qs.append(query) print(f"read {len(qs)} queries from files") if os.path.exists(f"{directory}/qas.json"): with open(f"{directory}/qas.json", "r", encoding="utf-8") as f: qas = json.loads(f.read()) print(f"read {len(qas)} query-responses from qas.json") qas = [{"q":qa["q"], "a":qa["a"]} for qa in qas if qa["a"] is not None] print(f"keep {len(qas)} query-responses from qas.json") existed_qs = collections.Counter([qa["q"] for qa in qas]) remained_qs = [] for q in qs: if existed_qs[q]>0: existed_qs[q] -= 1 else: remained_qs.append(q) print(f"filter out {len(qs)-len(remained_qs)} with reference to qas.json") qs = remained_qs return qs, qas qs, qas = read_qs() start_time = time.time() num_read_qas = len(qas) def ask(query, max_attempt_times=3): answer = None attempt_times = 0 while answer is None and attempt_times0: time.sleep(delayTime) print(f"{timestamp2string(time.time())}: iterations: {i} / {len(qs)} | elapsed time of this query (s): {elapsed_time:.2f}") return thread = threading.Thread(target=lambda :askingChatGPT(qs, qas)) thread.daemon = True thread.start() import gradio as gr def showcase(access_key): if not access_key==os.getenv('access_key'): chatbot_ret = [(f"Your entered Access Key:
{access_key}
is incorrect.", f"So i cannot provide you any information in this private space.")] else: recent_qas = qas[-10:] chatbot_ret = [(f"Your entered Access Key is correct.", f"The latest {len(recent_qas)} query-responses are displayed below.")] for qa in recent_qas: chatbot_ret += [(qa["q"].replace("\n","
"), str(qa["a"]).replace("\n","
"))] return chatbot_ret def download(access_key): if not access_key==os.getenv('access_key'): chatbot_ret = [(f"Your entered Access Key:
{access_key}
is incorrect.", f"So i cannot provide you any information in this private space.")] file_ret = gr.File.update(value=None, visible=False) else: chatbot_ret = [(f"Your entered Access Key is correct.", f"The file containing all processed query-responses ({len(qas)} in total) can be downloaded below.")] filename = f"qas-{len(qas)}.json" with open(filename, "w", encoding="utf-8") as f: f.write(json.dumps(qas, ensure_ascii=False, indent=2)) file_ret = gr.File.update(value=filename, visible=True) return chatbot_ret, file_ret def display(access_key): if not access_key==os.getenv('access_key'): chatbot_ret = [(f"Your entered Access Key:
{access_key}
is incorrect.", f"So i cannot provide you any information in this private space.")] elif len(qas)-num_read_qas<1: chatbot_ret = [(f"Your entered Access Key is correct.", f"But the progress has just started for a while and has no useful progress information to provide.")] else: num_total_qs, num_processed_qs = len(qs), len(qas) - num_read_qas time_takes = time.time() - start_time time_remains = time_takes * (num_total_qs-num_processed_qs) / num_processed_qs end_time = start_time + time_remains messages = [] for qa in qas: messages.append({"role":"user", "content":qa["q"]}) messages.append({"role":"assistant", "content":qa["a"]}) num_tokens_processed = num_tokens_from_messages(messages) num_tokens_total = int(num_tokens_processed * (num_total_qs+num_read_qas) / (num_processed_qs+num_read_qas)) dollars_tokens_processed = 0.002 * int(num_tokens_processed/1000) dollars_tokens_total = 0.002 * int(num_tokens_total/1000) chatbot_ret = [(f"Your entered Access Key is correct.", f"The information of progress is displayed below.")] chatbot_ret += [(f"The number of processed / total queries:", f"{num_processed_qs} / {num_total_qs} (+{num_read_qas})")] chatbot_ret += [(f"The hours already takes / est. remains:", f"{time_takes/3600:.2f} / {time_remains/3600:.2f}")] chatbot_ret += [(f"The time starts / est. ends:", f"{timestamp2string(start_time)} / {timestamp2string(end_time)}")] chatbot_ret += [(f"The number of processed / est. total tokens:", f"{num_tokens_processed} / {num_tokens_total}")] chatbot_ret += [(f"The dollars of processed / est. total tokens:", f"{dollars_tokens_processed:.2f} / {dollars_tokens_total:.2f}")] return chatbot_ret with gr.Blocks() as demo: gr.Markdown( """ Hello friends, Thanks for your attention on this space. But this space is for my own use, i.e., building a dataset with answers from ChatGPT, and the access key for runtime feedback is only shared to my colleagues. If you want to ask ChatGPT on Huggingface just as the title says, you can try this [one](https://huggingface.co/spaces/zhangjf/chatbot) I built for public. """ ) with gr.Column(variant="panel"): chatbot = gr.Chatbot() txt = gr.Textbox(show_label=False, placeholder="Enter your Access Key to access this private space").style(container=False) with gr.Row(): button_showcase = gr.Button("Show Recent Query-Responses") button_download = gr.Button("Download All Query-Responses") button_display = gr.Button("Display Progress Infomation") downloadfile = gr.File(None, interactive=False, show_label=False, visible=False) button_showcase.click(fn=showcase, inputs=[txt], outputs=[chatbot]) button_download.click(fn=download, inputs=[txt], outputs=[chatbot, downloadfile]) button_display.click(fn=display, inputs=[txt], outputs=[chatbot]) demo.launch()