app.py

import streamlit as st
import torch
from sentence_transformers import SentenceTransformer,util
#from transformers import pipeline
import pandas as pd 
import numpy as np 


# Load the pre-trained SentenceTransformer model
#pipeline = pipeline(task="Sentence Similarity", model="all-MiniLM-L6-v2")
model = SentenceTransformer('all-MiniLM-L6-v2')
sentence_embed = pd.read_csv('Reference_file_2 (1).csv')

#st.write(sentence_embed.head(5))

# Function to compute cosine similarity
def cosine_similarity(v1, v2):
    """Compute cosine similarity between two vectors."""
    return np.dot(v1, v2) / (np.linalg.norm(v1) * np.linalg.norm(v2))

# Backend function for mapping
def mapping_code(user_input):
    emb1 = model.encode(user_input, convert_to_tensor=True).astype(float)
    similarities = []
    for sentence_emb in sentence_embed['embeds']:
        sentence_emb = np.array(sentence_emb).astype(float)
        similarity = cosine_similarity(sentence_emb, emb1)
        similarities.append(similarity)

    # Combine similarity scores with 'code' and 'description'
    result = list(zip(sentence_embed['SBS Code'], sentence_embed['Long Description'], similarities))

    # Sort results by similarity scores
    result.sort(key=lambda x: x[2], reverse=True)

    # Return top 5 entries with 'code', 'description', and 'similarity_score'
    top_5_results = []
    for i in range(5):
        code, description, similarity_score = result[i]
        top_5_results.append({"Code": code, "Description": description, "Similarity Score": similarity_score})
    return top_5_results


# Streamlit frontend interface
def main():
    st.title("CPT Description Mapping")

    # Input text box for user input
    user_input = st.text_input("Enter CPT description:")

    # Button to trigger mapping
    if st.button("Map"):
        if user_input:
            st.write("Please wait for a moment .... ")

            # Call backend function to get mapping results
            mapping_results = mapping_code(user_input)

            # Display top 5 similar sentences
            st.write("Top 5 similar sentences:")
            for i, result in enumerate(mapping_results, 1):
                st.write(f"{i}. Code: {result['Code']}, Description: {result['Description']}, Similarity Score: {result['Similarity Score']:.4f}")

if __name__ == "__main__":
    main()