from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr
import torch


title = " AI-test"
description = "A State-of-the-Art Large-scale Pretrained Response generation model (DialoGPT)"
examples = [["How are you?"]]


tokenizer = AutoTokenizer.from_pretrained("microsoft/DialoGPT-large")
model = AutoModelForCausalLM.from_pretrained("microsoft/DialoGPT-large")


def predict(input, history=[]):
    # 将新输入的句子进行分词
    new_user_input_ids = tokenizer.encode(
        input + tokenizer.eos_token, return_tensors="pt"
    )

    # 将新用户输入的令牌附加到聊天历史记录中
    bot_input_ids = torch.cat([torch.LongTensor(history), new_user_input_ids], dim=-1)

    # 生成一个响应
    history = model.generate(
        bot_input_ids, max_length=4000, pad_token_id=tokenizer.eos_token_id
    ).tolist()

    # 将令牌转换为文本，然后将响应拆分为行
    response = tokenizer.decode(history[0]).split("<|endoftext|>")
    # print('decoded_response-->>'+str(response))
    response = [
        (response[i], response[i + 1]) for i in range(0, len(response) - 1, 2)
    ]  # 转换为列表的图元
    # print('response-->>'+str(response))
    return response, history


gr.Interface(
    fn=predict,
    title=title,
    description=description,
    examples=examples,
    inputs=["text", "state"],
    outputs=["chatbot", "state"],
    theme="finlaymacklon/boxy_violet",
).launch()