Update app.py

app.py

@@ -1,70 +1,50 @@
 """
-Basic similarity search example. Used in the original txtai demo.
+Basic similarity search example.  
 """
 
 import os
 
 import streamlit as st
 
-from txtai.embeddings import Embeddings
+from sentence_transformers import SentenceTransformer, util
 
+#model = SentenceTransformer("all-MiniLM-L6-v2")
 
-class Application:
-    """
-    Main application.
-    """
+model = SentenceTransformer('sentence-transformers/all-mpnet-base-v2')
 
-    def __init__(self):
-        """
-        Creates a new application.
-        """
 
-        # Create embeddings model, backed by sentence-transformers & transformers
-        self.embeddings = Embeddings({"path": "sentence-transformers/nli-mpnet-base-v2"})
+listofCachedItems = ["what was the revenue for FIFA 23", "what was the revenue for ApexLegends", "What was the revenue for FIFA 23 in Aug 2023",  "What was the revenue for ApexLegends in Aug 2023"]
 
-    def run(self):
-        """
-        Runs a Streamlit application.
-        """
+emb1 = model.encode("what was the revenue for FIFA 23 for UK" )
 
-        st.title("Similarity Search")
-        st.markdown("This application runs a basic similarity search that identifies the best matching row for a query.")
+maxscore = 0
+bestmatch = ""
 
-        data = [
-            "US tops 5 million confirmed virus cases",
-            "Canada's last fully intact ice shelf has suddenly collapsed, forming a Manhattan-sized iceberg",
-            "Beijing mobilises invasion craft along coast as Taiwan tensions escalate",
-            "The National Park Service warns against sacrificing slower friends in a bear attack",
-            "Maine man wins $1M from $25 lottery ticket",
-            "Make huge profits without work, earn up to $100,000 a day",
-        ]
+for i in listofCachedItems:
+  emb2 = model.encode(i)
+  cos_sim = util.cos_sim(emb1, emb2)
+  print("Cosine-Similarity:" + str(cos_sim) + "\t\t  Sentance "  + str(i) )
+  if cos_sim > maxscore :
+    maxscore = cos_sim
+    bestmatch = i
 
-        data = st.text_area("Data", value="\n".join(data))
-        query = st.text_input("Query")
+print("Final Result:-")
 
-        data = data.split("\n")
+print(bestmatch)
+print(maxscore)
 
-        if query:
-            # Get index of best section that best matches query
-            uid = self.embeddings.similarity(query, data)[0][0]
-            st.write(data[uid])
+print(type(maxscore))
 
+numericscore = maxscore[0].tolist()
+numericscore = numericscore[0]
 
-@st.cache(allow_output_mutation=True)
-def create():
-    """
-    Creates and caches a Streamlit application.
+print(numericscore)
 
-    Returns:
-        Application
-    """
+if numericscore > 0.45: 
+  print(bestmatch)
+  print(maxscore)
+else:
+  print("No matches")
 
-    return Application()
 
-
-if __name__ == "__main__":
-    os.environ["TOKENIZERS_PARALLELISM"] = "false"
-
-    # Create and run application
-    app = create()
-    app.run()
+st.write(bestmatch)