app.py

import gradio as gr
import os
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("nvidia/Llama-3.1-Nemotron-8B-UltraLong-4M-Instruct") 

api_key = os.environ.get("NINJA_API")
   
PERSONALITY = os.environ.get("CHATBOT_PERSONALITY")

def role(message, history):
   
    history.append({"role": "user", "content": message})

    prompt = PERSONALITY + "\n\n"
    for msg in history:
        prompt += f"{msg['role'].capitalize()}: {msg['content']}\n"
    prompt += "Role:"

    response = client.text_generation(prompt, max_new_tokens=250)
   
    history.append({"role": "assistant", "content": response})

    return history, history

"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    role,
    title="Shinobi - Japanese Culture Specialist",
    description="A chatbot specializing in Japanese culture.",
    chatbot=gr.Chatbot(),
    examples=["Tell me about the history of Samurai", "What is Bushido?", "Recommend a Japanese film"]
)


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