from huggingface_hub import InferenceClient
import gradio as gr
import random

API_URL = "https://api-inference.huggingface.co/models/"

client = InferenceClient(
    "mistralai/Mistral-7B-Instruct-v0.1"
)

def format_prompt(message, history):
  prompt = "<s>"
  for user_prompt, bot_response in history:
    prompt += f"[INST] {user_prompt} [/INST]"
    prompt += f" {bot_response}</s> "
  prompt += f"[INST] {message} [/INST]"
  return prompt

def generate(prompt, history, temperature=0.9, max_new_tokens=512, top_p=0.95, repetition_penalty=1.0):
    temperature = float(temperature)
    if temperature < 1e-2:
        temperature = 1e-2
    top_p = float(top_p)

    generate_kwargs = dict(
        temperature=temperature,
        max_new_tokens=max_new_tokens,
        top_p=top_p,
        repetition_penalty=repetition_penalty,
        do_sample=True,
        seed=random.randint(0, 10**7),
    )

    formatted_prompt = format_prompt(prompt, history)

    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
    output = ""

    for response in stream:
        output += response.token.text
        yield output
    return output


additional_inputs=[
    gr.Slider(
        label="Temperature",
        value=0.9,
        minimum=0.0,
        maximum=1.0,
        step=0.05,
        interactive=True,
        info="Higher values produce more diverse outputs",
    ),
    gr.Slider(
        label="Max new tokens",
        value=512,
        minimum=64,
        maximum=1024,
        step=64,
        interactive=True,
        info="The maximum numbers of new tokens",
    ),
    gr.Slider(
        label="Top-p (nucleus sampling)",
        value=0.90,
        minimum=0.0,
        maximum=1,
        step=0.05,
        interactive=True,
        info="Higher values sample more low-probability tokens",
    ),
    gr.Slider(
        label="Repetition penalty",
        value=1.2,
        minimum=1.0,
        maximum=2.0,
        step=0.05,
        interactive=True,
        info="Penalize repeated tokens",
    )
]

customCSS = """
.contain {
  display: flex;
  flex-direction: column;
}
.gradio-container {
  height: 100vh !important;
}
#component-0 {
  height: 100%;
}
#chatbot {
  flex-grow: 1;
  overflow: auto;
}
"""

with gr.Blocks(css=customCSS) as demo:
    gr.ChatInterface(
        generate,
        additional_inputs=additional_inputs,
    )

demo.queue().launch(debug=True)