import gradio as gr
from huggingface_hub import InferenceClient

"""
For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
"""
# client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
# client = InferenceClient("deepseek-ai/DeepSeek-R1-Distill-Qwen-7B")
client = InferenceClient("unsloth/DeepSeek-R1-Distill-Llama-8B-GGUF")


def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
    stream: bool = True,
):
    messages = []
    if system_message:
        messages.append({"role": "system", "content": system_message})
    for val in history:
        if isinstance(val, dict) and "role" in val and "content" in val:
            messages.append(val)
        elif isinstance(val, (tuple, list)):
            messages.append(
                {"role": "user", "content": val[0]}
                if val[0] else
                {"role": "assistant", "content": val[1]}
            )
    messages.append({"role": "user", "content": message})

    response = ""
    if stream:
        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
    else:
        completion = client.chat_completion(
            messages,
            max_tokens=max_tokens,
            temperature=temperature,
            top_p=top_p,
        )
        yield completion.choices[0].message.content

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
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)",
        ),
        gr.Checkbox(value=True, label="Streaming", info="Streaming response vs full completion"),
    ],
)


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