commented out some of the extra print functions (just so it runs faster)

app.py

@@ -14,31 +14,23 @@ with open("luggage.txt", "r", encoding="utf-8") as file:
   # Read the entire contents of the file and store it in a variable
   luggage_text = file.read()
 
-
 #STEP 3 FROM SEMATIC SEARCH
 def preprocess_text(text):
   # Strip extra whitespace from the beginning and the end of the text
   cleaned_text = text.strip()
-
   # Split the cleaned_text by every newline character (\n)
   chunks = cleaned_text.split("***")
-
   # Create an empty list to store cleaned chunks
   cleaned_chunks = []
-
   # Write your for-in loop below to clean each chunk and add it to the cleaned_chunks list
   for chunk in chunks:
     chunk.strip()
-
     if chunk != "":
       cleaned_chunks.append(chunk)
-
   # Print cleaned_chunks
-  print(cleaned_chunks)
-
+  #print(cleaned_chunks)
   # Print the length of cleaned_chunks
-  print(len(cleaned_chunks))
-
+  #print(len(cleaned_chunks))
   # Return the cleaned_chunks
   return cleaned_chunks
 
@@ -53,13 +45,10 @@ model = SentenceTransformer('all-MiniLM-L6-v2')
 def create_embeddings(text_chunks):
   # Convert each text chunk into a vector embedding and store as a tensor
   chunk_embeddings = model.encode(text_chunks, convert_to_tensor=True) # Replace ... with the text_chunks list
-
   # Print the chunk embeddings
-  print(chunk_embeddings)
-
+  #print(chunk_embeddings)
   # Print the shape of chunk_embeddings
-  print(chunk_embeddings.shape)
-
+  #print(chunk_embeddings.shape)
   # Return the chunk_embeddings
   return chunk_embeddings
 
@@ -72,32 +61,23 @@ chunk_embeddings_luggage = create_embeddings(cleaned_chunks_luggage)
 def get_top_chunks(query, chunk_embeddings, text_chunks):
   # Convert the query text into a vector embedding
   query_embedding = model.encode(query, convert_to_tensor = True) # Complete this line
-
   # Normalize the query embedding to unit length for accurate similarity comparison
   query_embedding_normalized = query_embedding / query_embedding.norm()
-
   # Normalize all chunk embeddings to unit length for consistent comparison
   chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
-
   # Calculate cosine similarity between query and all chunks using matrix multiplication
   similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized) # Complete this line
-
   # Print the similarities
-  print(similarities)
-
+  #print(similarities)
   # Find the indices of the 3 chunks with highest similarity scores
   top_indices = torch.topk(similarities, k=3).indices
-
   # Print the top indices
-  print(top_indices)
-
+  #print(top_indices)
   # Create an empty list to store the most relevant chunks
   top_chunks = []
-
   # Loop through the top indices and retrieve the corresponding text chunks
   for top_index in top_indices:
     top_chunks.append(text_chunks[top_index])
-
   # Return the list of most relevant chunks
   return top_chunks
 
@@ -108,7 +88,6 @@ def get_top_chunks(query, chunk_embeddings, text_chunks):
 # # Print the top results
 # print(top_weather)
 
-
 client = InferenceClient("Qwen/Qwen2.5-72B-Instruct")
 
 def respond(message, history):
@@ -137,6 +116,3 @@ def respond(message, history):
     
 chatbot = gr.ChatInterface(respond, type = 'messages')
 chatbot.launch(debug = True) 
-    
-
-