app.py

import openai
import tiktoken

import collections
import datetime
import time
import pytz
import json
import os

openai.api_key = os.getenv('API_KEY')

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
        for message in messages:
            num_tokens += 4  # every message follows <im_start>{role/name}\n{content}<im_end>\n
            for key, value in message.items():
                num_tokens += len(encoding.encode(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 <im_start>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.""")

qas = []
qs = []
start_time = None

def read_qs():
    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("qas.json"):
        with open("qas.json", "r", encoding="utf-8") as f:
            qas = json.loads(f.read())
        print(f"read {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


def ask(query, max_attempt_times=3):
    answer = None
    attempt_times = 0
    while answer is None and attempt_times<max_attempt_times:
        attempt_times += 1
        try:
            response = openai.ChatCompletion.create(
                model="gpt-3.5-turbo",
                messages=[
                    {"role": "user", "content": query}
                ]
            )["choices"][0]["message"]["content"]
        except Exception as e:
            print(e)
            print(f"retry in {attempt_times*10} seconds...")
            time.sleep(attempt_times*10)
    return answer


def askingChatGPT(min_interval_seconds=10):
    qs = read_qs()
    
    start_time = time.time()
    for i, q in enumerate(qs):
        ask_start_time = time.time()
        
        a = ask(q)
        qas.append({"q":q, "a":a})
        
        ask_end_time = time.time()
        elapsed_time = ask_end_time - ask_start_time
        delayTime = min_interval_seconds - elapsed_time
        if delayTime>0:
            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=my_function)
thread.daemon = True
thread.start()


import gradio as gr


def showcase(api_key):
    if not api_key==openai.api_key:
        chatbot_ret = [(f"Your entered api_key:<br>{api_key}<br>is incorrect.", f"So i cannot provide you any information in this private space.")]
    else:
        recent_qas = qas[:10]
        chatbot_ret = [(f"Your entered api_key is correct.", f"The latest {len(recent_qas)} query-responses are displayed below.")]
        for qa in recent_qas:
            chatbot_ret += [(qa["q"],qa["a"])]
    return chatbot_ret


def download(api_key):
    if not api_key==openai.api_key:
        chatbot_ret = [(f"Your entered api_key:<br>{api_key}<br>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 api_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(api_key):
    if not api_key==openai.api_key:
        chatbot_ret = [(f"Your entered api_key:<br>{api_key}<br>is incorrect.", f"So i cannot provide you any information in this private space.")]
    elif len(qas)<1:
        chatbot_ret = [(f"Your entered api_key is correct.", f"But the progress has just started for a while and has no useful progress information to provide.")]
    else:
        time_takes = time.time() - start_time
        time_remains = time_takes * (len(qs)-len(qas)) / len(qas)
        end_time = start_time + time_remains
        
        messages = []
        for qa in qas:
            messages.append({"role":"user", "content":qas["q"]})
            messages.append({"role":"assistant", "content":qas["a"]})
        num_tokens_processed = num_tokens_from_messages(messages)
        num_tokens_total = num_tokens_processed * len(qs) / len(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 api_key is correct.", f"The information of progress is displayed below.")]
        chatbot_ret += [(f"The number of processed / total queries:", f"{len(qas)} / {len(qs)}")]
        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} / {dollars_tokens_total}")]
        
    return chatbot_ret


with gr.Blocks() as demo:
    
    with gr.Column(variant="panel"):
        chatbot = gr.Chatbot()
        txt = gr.Textbox(show_label=False, placeholder="Enter my API_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()