Update app.py

app.py

@@ -2,61 +2,70 @@ import streamlit as st
 import pandas as pd
 import json
 import numpy as np
-#from fuzzywuzzy import fuzz
-
 import pinecone
 from sentence_transformers import SentenceTransformer
+from concurrent.futures import ThreadPoolExecutor
 
 pinecone.init(api_key='f5112f8c-f27d-4af1-b427-0c0953c113b5', environment='asia-southeast1-gcp')
 
-#model = SentenceTransformer('all-mpnet-base-v2',device='cpu')
-
-#
-
 def process_string(s):
     return s.lower().replace('&', 'and')
 
+index = pinecone.Index('ingradientsearch')
 
+@st.cache_data
+def load_model():
+    return SentenceTransformer(r"finetiuned_model")
 
-index = pinecone.Index('ingradientsearch')
 
+def get_match_score(ingredient):
+    loaded_model = load_model()
+    processed_ingredient = process_string(ingredient)
+    xq = loaded_model.encode([processed_ingredient]).tolist()
+    result = index.query(xq, top_k=1, includeMetadata=True)
 
+    if result['matches']:
+        match = result['matches'][0]
+        return match['metadata']['Ingredient'], round(match['score'], 2)
+    return None, None
 
+def get_top_matches(ingredients):
+    matches = []
+    scores = []
 
-#@st.cache(allow_output_mutation=True)
-@st.cache_data
-def load_model():
-    return SentenceTransformer(r"finetiuned_model")
+    with ThreadPoolExecutor() as executor:
+        results = list(executor.map(get_match_score, ingredients))
+
+    for match, score in results:
+        if match is not None and score is not None:
+            matches.append(match)
+            scores.append(score)
+
+    return matches, scores
 
 def main():
     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 an ingredient name:")
-    st.write("e.g. Chicken")
-    input_string = st.text_input("")
-
-    input_string = process_string(input_string)
-
-    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=[]
-        score=[]
-        for matches in result['matches']:
-            Ingredient.append(matches['metadata']['Ingredient'])
-            score.append(matches['score'])
-        
-        final_result= pd.DataFrame(list(zip(Ingredient, score)),
-            columns =['Ingredient','score' ])
-
-        st.dataframe(final_result)
+    st.write("Enter the JSON input:")
+    json_input = st.text_area("")
+
+    if st.button("Process"):
+        with st.spinner("Processing..."):
+            try:
+                input_data = json.loads(json_input)
+                for menu_item in input_data:
+                    ingredients = menu_item.get("ingredients", [])
+                    matches, scores = get_top_matches(ingredients)
+                    menu_item["Ingradients_matched"] = matches
+                    menu_item["scores"] = scores
+    
+                st.write("Processed JSON:")
+                #st.write(json.dumps(input_data, indent=2))
+                st.write("<pre>" + json.dumps(input_data, indent=4) + "</pre>", unsafe_allow_html=True)
+            except json.JSONDecodeError:
+                st.error("Invalid JSON input. Please check and try again.")
 
 if __name__ == "__main__":
     main()