import gradio as gr
from huggingface_hub import InferenceClient

AVAILABLE_MODELS = [
    "openai/gpt-oss-20b",
    "openai/gpt-oss-mini-20b",
    "meta-llama/Llama-3.3-70B-Instruct",
    "meta-llama/Llama-3.1-8B-Instruct",
    "mistralai/Mixtral-8x7B-Instruct-v0.1",
    "mistralai/Mistral-7B-Instruct-v0.3",
    "Qwen/Qwen2.5-72B-Instruct",
    "google/gemma-2-27b-it",
    "hydffgg/HOS-OSS-270M",
    "Hyggshi-AI/HOS-OSS-200M",
]

def respond(
    message,
    history: list[dict[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    selected_model,
    hf_token: gr.OAuthToken,
):
    client = InferenceClient(token=hf_token.token, model=selected_model)

    messages = [{"role": "system", "content": system_message}]
    messages.extend(history)
    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,
    ):
        choices = message.choices
        token = ""
        if len(choices) and choices[0].delta.content:
            token = choices[0].delta.content
        response += token
        yield response


chatbot = 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)",
        ),
        gr.Dropdown(
            choices=AVAILABLE_MODELS,
            value=AVAILABLE_MODELS[0],
            label="🤖 Model",
            info="Select the model to use for chat completion",
        ),
    ],
)

with gr.Blocks() as demo:
    with gr.Sidebar():
        gr.LoginButton()
        gr.Markdown("## ⚙️ Settings")
        gr.Markdown(
            "Select your preferred model and adjust parameters in the chat panel below."
        )
        gr.Markdown("### 📋 Available Models")
        for model in AVAILABLE_MODELS:
            gr.Markdown(f"- `{model.split('/')[-1]}`")

    chatbot.render()

if __name__ == "__main__":
    demo.launch()