app.py

import sklearn
import gradio as gr
import joblib
import requests.exceptions
from huggingface_hub import HfApi, hf_hub_download
from huggingface_hub.repocard import metadata_load

pipe = joblib.load("./pipeline.pkl")
inputs = [gr.Textbox(value = "The customer service was satisfactory.")]
outputs = [gr.Label(label = "Sentiment")]
title = "Sentiment Analysis"
app = gr.Blocks()

def load_agent(model_id_1, model_id_2):
    """
    This function load the agent's video and results
    :return: video_path
    """
    # Load the metrics
    metadata_1 = get_metadata(model_id_1)
    
    # Get the accuracy
    results_1 = parse_metrics_accuracy(metadata_1)
    
    # Load the metrics
    metadata_2 = get_metadata(model_id_2)
    
    # Get the accuracy
    results_2 = parse_metrics_accuracy(metadata_2)

    return model_id_1, results_1, model_id_2, results_2

def parse_metrics_accuracy(meta):
    if "model-index" not in meta:
        return None
    result = meta["model-index"][0]["results"]
    metrics = result[0]["metrics"]
    accuracy = metrics[0]["value"]
    return accuracy

def get_metadata(model_id):
    """
    Get the metadata of the model repo
    :param model_id:
    :return: metadata
    """
    try:
        readme_path = hf_hub_download(model_id, filename="README.md")
        metadata = metadata_load(readme_path)
        print(metadata)
        return metadata
    except requests.exceptions.HTTPError:
        return None


with app:
    gr.Markdown(
    """
    # Compare Sentiment Analysis Models 
    
    Type two models id you want to compare or check examples below.
    """)
    with gr.Row():
      model1_input = gr.Textbox(label="Model 1")
      model2_input = gr.Textbox(label="Model 2")
    with gr.Row():
      app_button = gr.Button("Compare models")
    with gr.Row():
      with gr.Column():
        model1_name = gr.Markdown()
        #model1_video_output = gr.Video()
        model1_score_output = gr.Textbox(label="Sentiment")
      with gr.Column():
        model2_name = gr.Markdown()
        #model2_video_output = gr.Video()
        model2_score_output = gr.Textbox(label="Sentiment")

    app_button.click(load_agent, inputs=[model1_input, model2_input], outputs=[model1_name, model1_score_output, model2_name, model2_score_output])
    
    examples = gr.Examples(examples=[["scikit-learn/sentiment-analysis","microsoft/Multilingual-MiniLM-L12-H384"],
        ["distilbert-base-uncased-finetuned-sst-2-english", "microsoft/Multilingual-MiniLM-L12-H384"]],
                           inputs=[model1_input, model2_input])

    
app.launch()