app.py

import gradio as gr
from huggingface_hub import InferenceClient
from transformers import pipeline

"""
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
"""
print("starting...")

# model_name = "microsoft/DialoGPT-medium" # Works, but isn't very good
model_name = "microsoft/Phi-3.5-mini-instruct"
chat_model = pipeline("text-generation", model=model_name)
print("defining function")
def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens
):
    """The respond method is the main method in the chatbot. It is called when the user hits the enter key."""
    print("enter respond")
    messages = [{"role": "system", "content": system_message}]
    messages.append({"role": "user", "content": message})
    print("getting response",messages)
    response = chat_model(messages)
    print("got response",response)
    return response[-1]['generated_text'][-1]['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")
    ],
)


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