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
"""

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


def predict(prompt):
    completion = model(prompt)[0]["generated_text"]
    return completion


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.Interface(fn=predict, inputs="text", outputs="text").launch()