import gradio as gr
import os
from langchain_openai import ChatOpenAI

api_key = os.environ.get("FEATHERLESS_API_KEY")

def respond(
    message,
    history: list[tuple[str, str]],
    model,
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    llm = ChatOpenAI(
        base_url="https://api.featherless.ai/v1/",
        api_key=api_key,
        streaming=True,
        model=model,
    )

    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})
    llm.max_tokens = max_tokens
    llm.temperature = temperature
    llm.top_p = top_p
    response = ""

    for chunk in llm.stream(messages):
        token = chunk.content
        response += token
        yield response

demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Dropdown(
            [
                "mistralai/Magistral-Small-2506",
                "Qwen/Qwen2.5-72B-Instruct",
                "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
                "unsloth/DeepSeek-R1-Distill-Llama-70B",
                "unsloth/Qwen2.5-72B-Instruct",
                "unsloth/Llama-3.3-70B-Instruct",
            ],
            label="Models"
        ),
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=16384, value=2048, step=1, label="Max tokens"),
        gr.Slider(minimum=0.1, maximum=2.0, 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()