# from huggingface_hub import InferenceClient
# import gradio as gr

# client = InferenceClient(
#     "mistralai/Mistral-7B-Instruct-v0.3"
# )


# 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=256, 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=42,
#     )

#     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=256,
#         minimum=0,
#         maximum=1048,
#         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",
#     )
# ]


# gr.ChatInterface(
#     fn=generate,
#     chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, layout="panel"),
#     additional_inputs=additional_inputs,
#     title="""AI Dermatologist"""
# ).launch(show_api=False)


# gr.load("models/Bhaskar2611/Capstone").launch()
import gradio as gr
from huggingface_hub import InferenceClient

# Initialize the client with your desired model
client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

# Define the system prompt as an AI Dermatologist
def format_prompt(message, history):
    prompt = "<s>"
    # Start the conversation with a system message
    prompt += "[INST] You are an AI Dermatologist designed to assist users with skin and hair care.[/INST]"
    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

# Function to generate responses with the AI Dermatologist context
def generate(
    prompt, history, temperature=0.9, max_new_tokens=256, 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=42,
    )

    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

# Customizable input controls for the chatbot interface
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=256,
        minimum=0,
        maximum=1048,
        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",
    )
]

# Define the chatbot interface with the starting system message as AI Dermatologist
gr.ChatInterface(
    fn=generate,
    chatbot=gr.Chatbot(show_label=False, show_share_button=False, show_copy_button=True, layout="panel"),
    additional_inputs=additional_inputs,
    title="AI Dermatologist"
).launch(show_api=False)

# Load your model after launching the interface
gr.load("models/Bhaskar2611/Capstone").launch()