Update app.py

app.py

@@ -13,11 +13,11 @@ df = pd.read_csv("analyticsvidhyacomplete.csv", parse_dates=["Date"])
 df['Date'] = pd.to_datetime(df['Date'], format='mixed', dayfirst=True, errors='coerce')
 df["combined_text"] = df["Title"].astype(str) + " " + df["Description"].astype(str)  + " " + df["Content"].astype(str)
 
-# Load query CSV with columns: Topic, Subtopic, TopN
+# Loading query CSV
 query_df = pd.read_csv("query.csv")
 query_df.dropna(subset=["Topic", "Subtopic", "TopN"], inplace=True)
 
-# Build dropdown options
+# dropdown options
 query_df["QueryOption"] = query_df.apply(
     lambda row: f"{row['Topic']} - {row['Subtopic']} (TopN: {int(row['TopN'])})", axis=1
 )
@@ -33,14 +33,7 @@ text_embeddings = model.encode(df["combined_text"].tolist(), convert_to_tensor=F
 
 
 def retrieve_records(selected_query):
-    # query_embedding = model.encode([query], convert_to_tensor=False)
-    
-    # scores = cosine_similarity(query_embedding, text_embeddings).flatten()
-    # df["similarity"] = scores
-    
-    # top_results = df.sort_values(by=['similarity', 'Date'], ascending=[False, False]).head(top_n)
 
-    # Extract Topic, Subtopic, and TopN from dropdown text
     match = re.match(r"(.+?) - (.+?) \(TopN: (\d+)\)", selected_query)
     if not match:
         return "Invalid query format selected."
@@ -69,8 +62,6 @@ def retrieve_records(selected_query):
 
 
 
-
-
 iface = gr.Interface(
     fn=retrieve_records,
     inputs=[
@@ -81,17 +72,5 @@ iface = gr.Interface(
 )
 
 
-# iface = gr.Interface(
-#     fn=retrieve_records,
-#     inputs=[
-#         gr.Textbox(label="Enter your query"),
-#         gr.Slider(5, 15, step=5, label="Top N results")
-#     ],
-#     outputs=gr.Markdown(label="Top Similar Records"),
-#     title="Top-N Article Retriever with Clickable Links"
-# )
-
-
-
 if __name__ == "__main__":
     iface.launch()