app.py

import os
import openai
import tiktoken

openai.api_key = os.getenv("OPENAI_API_KEY")


class Conversation:
    def __init__(self, prompt, model="gpt-3.5-turbo", temperature=0.8, max_tokens=250):
        self.prompt = prompt
        self.model = model
        self.temperature = temperature
        self.max_tokens = max_tokens

        self._init_messages()

    def _init_messages(self):
        self.messages = [{"role": "system", "content": self.prompt}]

    def reset(self):
        self._init_messages()

    def ask(self, question, pprint=False):
        self.messages.append({"role": "user", "content": question})

        if self.num_tokens(self.messages, self.model) >= self.max_tokens:
            if len(self.messages) > 3:
                self.messages = self.messages[:1] + self.messages[3:] # remove the first user message
            else:
                return "Error: max tokens exceeded."
        
        try:
            response = openai.ChatCompletion.create(
                model=self.model,
                messages=self.messages
            )
        except Exception as e:
            return e

        if pprint:
            print(f"tiktoken: {self.num_tokens(self.messages, self.model)}\ntokens: {response['usage']}")
        
        assistant_message = response["choices"][0]["message"]["content"]
        self.messages.append({"role": "assistant", "content": assistant_message})

        return assistant_message
    
    def num_tokens(self, messages, model):
        """Returns the number of tokens used by a list of messages."""
        try:
            encoding = tiktoken.encoding_for_model(model)
        except KeyError:
            print("Warning: model not found. Using cl100k_base encoding.")
            encoding = tiktoken.get_encoding("cl100k_base")
        if model == "gpt-3.5-turbo":
            print("Warning: gpt-3.5-turbo may change over time. Returning num tokens assuming gpt-3.5-turbo-0301.")
            return self.num_tokens(messages, model="gpt-3.5-turbo-0301")
        elif model == "gpt-4":
            print("Warning: gpt-4 may change over time. Returning num tokens assuming gpt-4-0314.")
            return self.num_tokens(messages, model="gpt-4-0314")
        elif model == "gpt-3.5-turbo-0301":
            tokens_per_message = 4  # every message follows <|start|>{role/name}\n{content}<|end|>\n
            tokens_per_name = -1  # if there's a name, the role is omitted
        elif model == "gpt-4-0314":
            tokens_per_message = 3
            tokens_per_name = 1
        else:
            raise NotImplementedError(f"""num_tokens_from_messages() is not implemented for model {model}. See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens.""")
        num_tokens = 0
        for message in messages:
            num_tokens += tokens_per_message
            for key, value in message.items():
                num_tokens += len(encoding.encode(value))
                if key == "name":
                    num_tokens += tokens_per_name
        num_tokens += 3  # every reply is primed with <|start|>assistant<|message|>
        return num_tokens


import gradio as gr

system_prompt_foodie = "您是一名美食家，帮助别人了解美食的信息，回答要简洁有效并控制在100字左右。"

conv = Conversation(system_prompt_foodie, max_tokens=1024)

with gr.Blocks(title="ChatGPT 助手") as demo:
    chatbot = gr.Chatbot(elem_id="chatbot")#.style(height=700)
    msg = gr.Textbox(show_label=False).style(container=False)
    clear = gr.Button("Clear")

    def ask(message, chat_history):
        bot_message = conv.ask(message)
        chat_history.append((message, bot_message))
        return "", chat_history

    msg.submit(ask, [msg, chatbot], [msg, chatbot])
    clear.click(lambda: conv.reset(), None, chatbot, queue=False)

demo.launch()