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 
import pickle


# Load the pre-trained SentenceTransformer model
#pipeline = pipeline(task="Sentence Similarity", model="all-MiniLM-L6-v2")
model = SentenceTransformer('neuml/pubmedbert-base-embeddings')
#sentence_embed = pd.read_csv('Reference_file.csv')
with open("embeddings_1.pkl", "rb") as fIn:
    stored_data = pickle.load(fIn)
    stored_code = stored_data["SBS_code"]
    stored_sentences = stored_data["sentences"]
    stored_embeddings = stored_data["embeddings"]

import streamlit as st

# Define the function for mapping code
def mapping_code(user_input):
    emb1 = model.encode(user_input.lower())
    similarities = []
    for sentence in stored_embeddings:
        similarity = util.cos_sim(sentence, emb1)
        similarities.append(similarity)

    # Combine similarity scores with 'code' and 'description'
    result = list(zip(stored_data["SBS_code"],stored_data["sentences"], similarities))

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

    num_results = min(5, len(result))

    # Return top 5 entries with 'code', 'description', and 'similarity_score'
    top_5_results = []
    if num_results > 0:
        for i in range(num_results):
            code, description, similarity_score = result[i]
            top_5_results.append({"Code": code, "Description": description, "Similarity Score": similarity_score})
    else:
        top_5_results.append({"Code": "", "Description": "No similar sentences found", "Similarity Score": 0.0})

    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: {float(result['Similarity Score']):.4f}")


if __name__ == "__main__":
    main()