import gradio as gr
from huggingface_hub import InferenceClient
from fastapi import FastAPI, Request
from fastapi.responses import JSONResponse
import os

# Gradio app + FastAPI mount
app = FastAPI()

client = InferenceClient(
    model="HuggingFaceH4/zephyr-7b-beta",
    token=os.getenv("huggingface_token"),
)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    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

# Define FastAPI POST endpoint
@app.post("/chat")
async def chat(request: Request):
    data = await request.json()

    message = data.get("message")
    persona = data.get("persona", "You are a friendly Chatbot.")
    max_tokens = data.get("max_tokens", 512)
    temperature = data.get("temperature", 0.7)
    top_p = data.get("top_p", 0.95)

    messages = [{"role": "system", "content": persona}, {"role": "user", "content": message}]
    full_response = ""

    for chunk in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        full_response += chunk.choices[0].delta.content or ""

    return JSONResponse({"response": full_response})


# Gradio demo for UI access
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", 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)"),
    ],
)

# Mount Gradio app at "/"
app = gr.mount_gradio_app(app, demo, path="/")