Update app.py

app.py

@@ -8,8 +8,13 @@ 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.csv')
+model = SentenceTransformer('neuml/pubmedbert-base-embeddings')
+#sentence_embed = pd.read_csv('Reference_file.csv')
+with open("embeddings.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
 
@@ -17,12 +22,12 @@ import streamlit as st
 def mapping_code(user_input):
     emb1 = model.encode(user_input.lower())
     similarities = []
-    for sentence in sentence_embed['embeds']:
+    for sentence in stored_embeddings:
         similarity = util.cos_sim(sentence, emb1)
         similarities.append(similarity)
 
     # Combine similarity scores with 'code' and 'description'
-    result = list(zip(sentence_embed['SBS Code'], sentence_embed['Long Description'], similarities))
+    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)