Update app.py

app.py

@@ -37,7 +37,7 @@ def load_and_preprocess_text(filename):
 
 segments = load_and_preprocess_text(filename)
 
-def find_relevant_segment(user_query, book, segments):
+def find_relevant_segment(user_query, segments):
     """
     Find the most relevant text segment for a user's query using cosine similarity among sentence embeddings.
     This version finds the best match based on the content of the query.
@@ -47,7 +47,7 @@ def find_relevant_segment(user_query, book, segments):
         lower_query = user_query.lower()
         
         # Encode the query and the segments
-        query_embedding = retrieval_model.encode(lower_query, book)
+        query_embedding = retrieval_model.encode(lower_query)
         segment_embeddings = retrieval_model.encode(segments)
         
         # Compute cosine similarities between the query and the segments