app.py

import streamlit as st
from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline

# โหลด Tokenizer และ Model
model_name = "Nucha/Nucha_SkillNER_BERT"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# สร้าง NER Pipeline
ner_pipeline = pipeline("ner", model=model, tokenizer=tokenizer)

# UI ด้วย Streamlit
col1, col2 = st.columns(2)

with col1:
    st.header("Input")
    default_text="""
            To enhance my programming skills, I took online courses in Python, PHP, and cloud computing technologies. 
            The workshop on machine learning taught me valuable skills in TensorFlow. 
            The developer utilized Python for backend development and JavaScript for frontend, ensuring a seamless user experience. 
            In my previous role, I collaborated with data scientists to implement machine learning models using R and TensorFlow. 
            I have strong communication skills.
    """
    text = st.text_area("Enter text for NER analysis:", value=default_text, height=400, max_chars=None, key=None, help=None, placeholder=None)
    analyze_button = st.button("Analyze")
    
with col2:
    st.header("Output")
    if analyze_button:
        ner_results = ner_pipeline(text)
        
        # Display results in a structured output block
        if ner_results:
            output_data = [{"Entity": entity['word'], "Label": entity['entity'], "Score": f"{entity['score']:.4f}"} for entity in ner_results]
            st.table(output_data)  # Display as a table
        else:
            st.write("No entities found.")