app.py

# import streamlit as st
# from transformers import pipeline

# # Load NER model
# ner_model = pipeline("ner", model="has-abi/distilBERT-finetuned-resumes-sections")

# # Create Streamlit app
# st.title("Named Entity Recognition with Hugging Face models")

# # Get user input
# text_input = st.text_input("Enter some text:")

# # Run NER on user input
# if text_input:
#     results = ner_model(text_input)
#     for result in results:
#         st.write(f"{result['word']}: {result['entity']}")
import streamlit as st
from transformers import pipeline

# Set up Resuméner pipeline
summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-6-6")

# Create Streamlit app
st.title("Resuméner")
st.write("Upload your resume below to generate a summary.")

# Upload resume file
uploaded_file = st.file_uploader("Choose a file")

if uploaded_file is not None:
    # Read resume file contents
    resume_text = uploaded_file.read().decode("utf-8")
    
    # Generate summary using Resuméner pipeline
    summary = summarizer(resume_text, max_length=100, min_length=30, do_sample=False)[0]['summary_text']
    
    # Display summary
    st.write("Summary:")
    st.write(summary)