Update app.py

app.py

@@ -1,46 +1,41 @@
-import streamlit as st
-import pandas as pd
+import os
+import gradio as gr
 from transformers import pipeline
+import huggingface_hub
 
-# Load translation and summarization pipelines
-translator = pipeline("translation_ru_to_en", model="Helsinki-NLP/opus-mt-ru-en")
-summarizer = pipeline("summarization", model="facebook/bart-large-cnn")
 
-# Function to translate and summarize text
-def translate_and_summarize(text):
-    translated_text = translator(text)[0]['translation_text']
-    summary = 'News Alert. ' + summarizer(translated_text, max_length=140, min_length=110, do_sample=False)[0]['summary_text']
-    return summary
 
-# Function to translate and summarize first paragraph
-def translate_and_summarize_first_paragraph(text):
-    first_sentence = text.split('.')[0] + '.'
-    translated_text = translator(first_sentence)[0]['translation_text']
-    summary = summarizer(translated_text, max_length=20, min_length=5, do_sample=False)[0]['summary_text']
-    return summary
+# Load the pre-trained model
+classifier = pipeline("text-classification", model="ICILS/xlm-r-icils-ilo", device=0)
 
-# Streamlit interface
-def main():
-    st.title("CSV Translator and Summarizer")
+# Define the prediction function
+def classify_text(text):
+    """
+    Classify the input text into occupational categories using a pre-trained model.
+    
+    Args:
+        text (str): Job description text.
+    
+    Returns:
+        tuple: (label, score) - The classification label and the associated confidence score.
+    """
+    result = classifier(text)[0]
+    label = result['label']
+    score = result['score']
+    return label, score
 
-    # File uploader
-    uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
-    if uploaded_file is not None:
-        # Read data
-        data = pd.read_csv(uploaded_file)
-        # Check if 'Description' and 'Published' columns exist
-        if 'Description' in data.columns:
-            # Apply full translation and summarization
-            data['DescriptionEn'] = data['Description'].apply(translate_and_summarize)
-            # Apply first paragraph translation and summarization for Title
-            data['Title'] = data['Description'].apply(translate_and_summarize_first_paragraph)
-            # Display data in a table
-            st.write(data[['ID', 'Title', 'DescriptionEn']])
-            # Provide download link for the updated CSV
-            csv = data.to_csv(index=False)
-            st.download_button(label="Download updated CSV", data=csv, file_name="updated_data.csv", mime="text/csv")
-        else:
-            st.error("Uploaded CSV does not contain required 'Description' column.")
+# Create the Gradio interface
+demo = gr.Interface(
+    fn=classify_text,
+    inputs=gr.Textbox(lines=2, label="Job Description Text", placeholder="Enter a job description..."),
+    outputs=[gr.Textbox(label="ISCO-08 Label"), gr.Number(label="Score")],
+    title="XLM-R ISCO Classification",
+    description=(
+        "Classify job descriptions into occupational categories using a pre-trained XLM-R-ISCO model "
+        "from Hugging Face Spaces."
+    ),
+)
 
+# Run the Gradio app
 if __name__ == "__main__":
-    main()
+    demo.launch()