Update app.py

app.py

@@ -10,7 +10,7 @@ with open("knowledge.txt", "r", encoding="utf-8") as file:
   # opens the text, saves as "file"
   # reads the text and saves as water_cycle_text variable
 
-print(recent)
+
 
 cleaned_text = recent.strip()
 # cleaning up the text
@@ -24,13 +24,13 @@ for chunk in chunks:
   if stripped_chunk:
     cleaned_chunks.append(stripped_chunk)
     # loop through chunks and add not empty chunks to cleaned_chunks list
-print(cleaned_chunks)
+
 
 model = SentenceTransformer('all-MiniLM-L6-v2')
 
 chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True)
 # encode the model, pass through my cleaned chunks and convert to vector embeddings (not arrays)
-print(chunk_embeddings)
+
 
 def get_top_chunks(query):
   # create my function taking query as parameter
@@ -42,10 +42,10 @@ def get_top_chunks(query):
   # normailizing chunks for comparison of meaning
 
   similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized)
-  print(similarities)
+
   # using matmul (matrix multiplication method) to compare query to chunks
   top_indices = torch.topk(similarities, k=3).indices
-  print(top_indices)
+
   # get the indices of the chunks that are most similar to query
 
   top_chunks = []