Update custom_utils.py

custom_utils.py

@@ -102,11 +102,7 @@ def rag_inference(openai_api_key, prompt, retrieval_result):
         f"Question: {prompt}\n"
         "Helpful Answer: "
     )
-
-    print("###")
-    print(content)
-    print("###")
-    
+   
     return invoke_llm(openai_api_key, content)
 
 def invoke_llm(openai_api_key, content):
@@ -137,10 +133,6 @@ def vector_search_naive(openai_api_key,
                         vector_index="vector_index"):
     query_embedding = get_text_embedding(openai_api_key, prompt)
 
-    print("\n\n\n\n\n### Embedding:")
-    print(query_embedding)
-    print("###")
-    
     if query_embedding is None:
         return "Invalid query or embedding generation failed."
 
@@ -154,22 +146,12 @@ def vector_search_naive(openai_api_key,
         }
     }
 
-    print("\n\n\n\n\n### Vector Search Stage:")
-    print(vector_search_stage)
-    print("###")
-    
     pipeline = [
         vector_search_stage, 
         get_stage_include_fields(), 
         get_stage_filter_result(accomodates, bedrooms)
     ]
 
-    print("\n\n\n\n\n### DB, Collection, Pipeline:")
-    print(db)
-    print(collection)
-    print(pipeline)
-    print("###")
-    
     return invoke_search(db, collection, pipeline)
 
 def vector_search_advanced(openai_api_key, 
@@ -341,11 +323,7 @@ def get_stage_sorting():
 def invoke_search(db, collection, pipeline):
     results = collection.aggregate(pipeline)
 
-    print("###")
-    print(results)
-    print("###")
-    
-    #print(f"Vector search millis elapsed: {get_millis_elapsed(db, collection, pipeline)}")
+    print(f"Vector search millis elapsed: {get_millis_elapsed(db, collection, pipeline)}")
     
     return list(results)