app.py

import gradio as gr
from huggingface_hub import InferenceClient

# ✅ Predefined knowledge base (Modify this with your data)
KNOWLEDGE_BASE = {
    "what is your name?": "I am a chatbot powered by Zephyr-7B.",
    "who created you?": "I was created using Gradio and Hugging Face's Zephyr model.",
    "what is gradio?": "Gradio is an open-source Python library for building interactive UIs for machine learning models."
}

client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    # ✅ Check if the user question is in knowledge base
    lower_message = message.lower().strip()
    if lower_message in KNOWLEDGE_BASE:
        return KNOWLEDGE_BASE[lower_message]

    # ✅ Otherwise, use the AI model for response
    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


# ✅ Gradio Chat UI
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)",
        ),
    ],
)


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