Update app.py

app.py

@@ -5,3 +5,38 @@ import streamlit as st
 from sentence_transformers import SentenceTransformer, util
 
 st.title("Semantic-Search-Transformer")
+
+# Importing the Data 
+df = pd.read_csv('medium_articles.csv')
+
+# Downloading the sentence transformer model
+
+embedder = SentenceTransformer('all-MiniLM-L6-v2')
+
+#Predictions
+# User-Test function (prediction_script.py)
+# load saved model
+
+all_embeddings = np.load('mediumArticle_embeddings.npy')
+
+# Function
+
+def prediction(query,top_k,corpus_embeddings,df):
+    query_embedding = embedder.encode(query, convert_to_tensor=True)
+    hits = util.semantic_search(query_embedding, corpus_embeddings, top_k=top_k)
+    hits = hits[0] # Get the hits for the first query
+
+    print(f"\nTop {top_k} most similar sentences in corpus:")
+    for hit in hits:
+      hit_id = hit['corpus_id']
+      article_data = df.iloc[hit_id]
+      title = article_data["title"]
+      st.write("-", title, "(Score: {:.4f})".format(hit['score']))
+
+query = 'Artificial Intelligence and Blockchain'
+# query = input("Enter the Input Query:-  ")
+# top_sent = int(input("Enter the number of similarity sentences you want: "))
+top_k = 10
+prediction(query,top_k,all_embeddings,df)
+
+