Update app.py

app.py

@@ -11,7 +11,7 @@ pinecone.init(api_key='f5112f8c-f27d-4af1-b427-0c0953c113b5', environment='asia-
 
 #model = SentenceTransformer('all-mpnet-base-v2',device='cpu')
 
-loaded_model = SentenceTransformer(r"finetiuned_model")
+#
 
 def process_string(s):
     return s.lower().replace('&', 'and')
@@ -21,14 +21,18 @@ def process_string(s):
 index = pinecone.Index('ingradientsearch')
 
 
-# Create a Streamlit app
+
+
+@st.cache(allow_output_mutation=True)
+def load_model():
+    return SentenceTransformer(r"finetiuned_model")
+
 def main():
-    st.set_page_config(page_title="Ingradients Matching App", page_icon=":smiley:", layout="wide")
-    st.title("Ingradients name matching App :smiley:")
+    st.set_page_config(page_title="Ingredients Matching App", page_icon=":smiley:", layout="wide")
+    st.title("Ingredients name matching App :smiley:")
 
-   
     st.header("Matches using embeddings (semantic search)")
-    st.write("Enter a ingradient name:")
+    st.write("Enter an ingredient name:")
     st.write("e.g. Chicken")
     input_string = st.text_input("")
 
@@ -37,18 +41,18 @@ def main():
     if st.button("Enter"):
         st.write("Top 5 matches using semantic search:")
 
+        loaded_model = load_model()  # Load the model using the cached function
         xq = loaded_model.encode([input_string]).tolist()
         result = index.query(xq, top_k=5, includeMetadata=True)
 
         Ingredient=[]
-        Group=[]
+        #Group=[]
         score=[]
         for matches in result['matches']:
             Ingredient.append(matches['metadata']['Ingredient'])
-            #Group.append(matches['metadata']['Group'])
             score.append(matches['score'])
         
-        final_result= pd.DataFrame(list(zip(Ingredient, Group, score)),
+        final_result= pd.DataFrame(list(zip(Ingredient, score)),
             columns =['Ingredient','score' ])
 
         st.dataframe(final_result)