app.py

import gradio as gr
from confidence import run_nli

DESCRIPTION = """\
# Llama-2 13B Chat
This Space demonstrates model [Llama-2-13b-chat](https://huggingface.co/meta-llama/Llama-2-13b-chat) by Meta, a Llama 2 model with 13B parameters fine-tuned for chat instructions. Feel free to play with it, or duplicate to run generations without a queue! If you want to run your own service, you can also [deploy the model on Inference Endpoints](https://huggingface.co/inference-endpoints).
🔎 For more details about the Llama 2 family of models and how to use them with `transformers`, take a look [at our blog post](https://huggingface.co/blog/llama2).
🔨 Looking for an even more powerful model? Check out the large [**70B** model demo](https://huggingface.co/spaces/ysharma/Explore_llamav2_with_TGI).
🐇 For a smaller model that you can run on many GPUs, check our [7B model demo](https://huggingface.co/spaces/huggingface-projects/llama-2-7b-chat).
"""

def greet(query, history):
    results = run_nli(query, sample_size=3)
    return results
    #return "this is the result"


sample_list = [
    "Tell me something about Albert Einstein, e.g., a short bio with birth date and birth place",
    "Tell me something about Lihu Chen, e.g., a short bio with birth date and birth place",
]

iface = gr.ChatInterface(
    fn=greet,
    stop_btn=None,
    # inputs="text",
    # outputs="text",
    examples=sample_list,
    cache_examples=True
)

with gr.Blocks() as demo:
    gr.Markdown(DESCRIPTION)
    iface.render()
    #gr.Markdown(LICENSE)


iface.launch()