import gradio as gr
from huggingface_hub import InferenceClient, hf_hub_download
import json

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

def load_website_data():
    try:
        # Download the latest crawl data
        file_path = hf_hub_download(
            repo_id="SmokeyBandit/SletcherSystems",
            filename="data/latest_crawl.json",
            repo_type="dataset"
        )
        with open(file_path, 'r') as f:
            return json.load(f)
    except Exception as e:
        print(f"Error loading website data: {e}")
        return None

WEBSITE_DATA = load_website_data()

def respond(
    message, 
    history: list[tuple[str, str]], 
    system_message, 
    max_tokens, 
    temperature, 
    top_p,
):
    # Augment system message with website data if available
    if WEBSITE_DATA:
        system_message = f"{system_message}\n\nWebsite Content:\n{WEBSITE_DATA['content'][:2000]}"
    
    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 assistant for SletcherSystems. Answer questions based on the website content.",
            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()