import os
from transformers import AutoModel, AutoTokenizer
import gradio as gr
import mdtex2html
from utils import load_model_on_gpus
import torch

MODEL_PATH = os.environ.get('MODEL_PATH', 'THUDM/chatglm3-6b')
TOKENIZER_PATH = os.environ.get("TOKENIZER_PATH", MODEL_PATH)
DEVICE = 'cuda' if torch.cuda.is_available() else 'cpu'

tokenizer = AutoTokenizer.from_pretrained(TOKENIZER_PATH, trust_remote_code=True)
if 'cuda' in DEVICE: # AMD, NVIDIA GPU can use Half Precision
    model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).to(DEVICE).eval()
else: # CPU, Intel GPU and other GPU can use Float16 Precision Only
    model = AutoModel.from_pretrained(MODEL_PATH, trust_remote_code=True).float().to(DEVICE).eval()

# 多显卡支持，使用下面两行代替上面一行，将num_gpus改为你实际的显卡数量
# from utils import load_model_on_gpus
# model = load_model_on_gpus("THUDM/chatglm3-6b", num_gpus=2)

"""Override Chatbot.postprocess"""

def postprocess(self, y):
    if y is None:
        return []
    for i, (message, response) in enumerate(y):
        y[i] = (
            None if message is None else mdtex2html.convert((message)),
            None if response is None else mdtex2html.convert(response),
        )
    return y


gr.Chatbot.postprocess = postprocess


def parse_text(text):
    """copy from https://github.com/GaiZhenbiao/ChuanhuChatGPT/"""
    lines = text.split("\n")
    lines = [line for line in lines if line != ""]
    count = 0
    for i, line in enumerate(lines):
        if "```" in line:
            count += 1
            items = line.split('`')
            if count % 2 == 1:
                lines[i] = f'<pre><code class="language-{items[-1]}">'
            else:
                lines[i] = f'<br></code></pre>'
        else:
            if i > 0:
                if count % 2 == 1:
                    line = line.replace("`", "\`")
                    line = line.replace("<", "&lt;")
                    line = line.replace(">", "&gt;")
                    line = line.replace(" ", "&nbsp;")
                    line = line.replace("*", "&ast;")
                    line = line.replace("_", "&lowbar;")
                    line = line.replace("-", "&#45;")
                    line = line.replace(".", "&#46;")
                    line = line.replace("!", "&#33;")
                    line = line.replace("(", "&#40;")
                    line = line.replace(")", "&#41;")
                    line = line.replace("$", "&#36;")
                lines[i] = "<br>" + line
    text = "".join(lines)
    return text


def predict(input, chatbot, max_length, top_p, temperature, history, past_key_values):
    chatbot.append((parse_text(input), ""))
    for response, history, past_key_values in model.stream_chat(tokenizer, input, history,
                                                                past_key_values=past_key_values,
                                                                return_past_key_values=True,
                                                                max_length=max_length, top_p=top_p,
                                                                temperature=temperature):
        chatbot[-1] = (parse_text(input), parse_text(response))

        yield chatbot, history, past_key_values


def reset_user_input():
    return gr.update(value='')


def reset_state():
    return [], [], None


with gr.Blocks() as demo:
    gr.HTML("""<h1 align="center">ChatGLM3-6B</h1>""")

    chatbot = gr.Chatbot()
    with gr.Row():
        with gr.Column(scale=4):
            with gr.Column(scale=12):
                user_input = gr.Textbox(show_label=False, placeholder="Input...", lines=10).style(
                    container=False)
            with gr.Column(min_width=32, scale=1):
                submitBtn = gr.Button("Submit", variant="primary")
        with gr.Column(scale=1):
            emptyBtn = gr.Button("Clear History")
            max_length = gr.Slider(0, 32768, value=8192, step=1.0, label="Maximum length", interactive=True)
            top_p = gr.Slider(0, 1, value=0.8, step=0.01, label="Top P", interactive=True)
            temperature = gr.Slider(0, 1, value=0.6, step=0.01, label="Temperature", interactive=True)

    history = gr.State([])
    past_key_values = gr.State(None)

    submitBtn.click(predict, [user_input, chatbot, max_length, top_p, temperature, history, past_key_values],
                    [chatbot, history, past_key_values], show_progress=True)
    submitBtn.click(reset_user_input, [], [user_input])

    emptyBtn.click(reset_state, outputs=[chatbot, history, past_key_values], show_progress=True)

demo.queue().launch(share=False, server_name="127.0.0.1", server_port=8501, inbrowser=True)