app.py

import gradio as gr
#from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
#from new_chat import Conversation, ChatgptAPI

import os
from pathlib import Path
from openai import OpenAI

class ChatgptAPI:
    def __init__(self, ):
        self.client = OpenAI(
            api_key = os.environ.get("OPENAI_API_KEY"),
            base_url = "https://api.moonshot.cn/v1",
        )
    def get_single_round_completion(self, file_path, prompt, conversation):
        conversation.append_question(prompt)
        file_object = self.client.files.create(file=Path(file_path), purpose="file-extract")
        file_content = self.client.files.content(file_id=file_object.id).text
        messages = [
            {
                "role": "system",
                "content": "你是 Kimi，由 Moonshot AI 提供的人工智能助手，你更擅长中文和英文的对话。你会为用户提供安全，有帮助，准确的回答。同时，你会拒绝一切涉及恐怖主义，种族歧视，黄色暴力等问题的回答。Moonshot AI 为专有名词，不可翻译成其他语言。",
            },
            {
                "role": "system",
                "content": file_content,
            },
            {"role": "user", "content": prompt},
        ]
        completion = self.client.chat.completions.create(
            model="moonshot-v1-32k",
            messages=messages,
            temperature=0.3,
        )
        message=completion.choices[0].message.content
        conversation.append_answer(message)
        return message, conversation
        
    
    def get_multi_round_completion(self, prompt, conversation, model='gpt-3.5-turbo'):
        conversation.append_question(prompt)
        prompts = conversation.get_prompts()

        response = openai.ChatCompletion.create(
            model=model,
            messages=prompts,
            temperature=0,
            max_tokens=2048,
            top_p=1,
        )
        message = response.choices[0].message['content']
        conversation.append_answer(message)

        return message, conversation

class Conversation:
    def __init__(self, system_prompt='iii', num_of_round = 5):
        self.num_of_round = num_of_round
        self.history = []
        self.initialized = False
        self.history.append({"role": "system", "content": system_prompt})

        if len(system_prompt) > 0:
            #logger.info(f'Conversation initialized with system prompt: {system_prompt}')
            self.initialized = True

    def is_initialized(self):
        return self.initialized
    
    def append_question(self, question):
        self.history.append({"role": "user", "content": question})

    def append_answer(self, answer):
        self.history.append({"role": "assistant", "content": answer})

        if len(self.history) > self.num_of_round * 2:
            del self.history[1:3]

    def clear(self):
        self.history.clear()
        self.initialized = False

    def get_prompts(self):
        return self.history
    
    def round_size(self):
        return 0 if len(self.history) < 2 else len(self.hitory) - 1
    
    def get_history_messages(self):
        return [(u['content'], b['content']) for u,b in zip(self.history[1::2], self.history[2::2])]



chat_api = ChatgptAPI()

def predict(system_input, password_input, user_in_file, user_input, conversation):
    if password_input != os.environ.get("USER_KEY"):
       return [(None, "Wrong password!")], conversation, user_input

    if conversation.is_initialized() == False:
        conversation = Conversation(system_input, 5)
    _, conversation = chat_api.get_single_round_completion(user_in_file, user_input, conversation)
    return conversation.get_history_messages(), conversation, None
    #_, conversation = chat_api.get_multi_round_completion(user_input, conversation)
    #return conversation.get_history_messages(), conversation, None


def clear_history(conversation):
    conversation.clear()
    return None, conversation


with gr.Blocks(css="#chatbot{height:350px} .overflow-y-auto{height:600px}") as demo:
    chatbot = gr.Chatbot(elem_id="chatbot")
    conversation = gr.State(value=Conversation())

    with gr.Row():
        system_in_txt = gr.Textbox(lines=1, label="User Name:", placeholder="Enter user name")
        password_in_txt = gr.Textbox(lines=1, label="Password:", placeholder="Enter password")
       
    with gr.Row():
        user_in_file = gr.File(label="Upload File")
        user_in_txt = gr.Textbox(lines=3, label="User role content:", placeholder="Enter text...", container=False)
    
    with gr.Row():
        reset_button = gr.Button("Reset")
        submit_button = gr.Button("Submit")
    
    submit_button.click(predict, [system_in_txt, password_in_txt, user_in_file, user_in_txt, conversation], [chatbot, conversation, user_in_txt])
    reset_button.click(clear_history, [conversation], [chatbot, conversation], queue=False)

'''
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)
'''

if __name__ == "__main__":
    demo.launch()