Update app.py

app.py

@@ -115,12 +115,13 @@ def rag_workflow(query):
     print("Retrieved Document Contexts:", kadiAPY_doc_documents)
     print("Retrieved Code Contexts:", kadiAPY_code_documents)
 
+
+    
     
     formatted_doc_snippets = rag_chain.format_documents(kadiAPY_doc_documents)
     formatted_code_snippets = rag_chain.format_documents(kadiAPY_code_documents)
-    print("FORMATTED Retrieved Document Contexts:", formatted_doc_snippets)
-    print("FORMATTED Retrieved Code Contexts:" , formatted_code_snippets)
-    print(formatted_code_snippets)
+    #print("FORMATTED Retrieved Document Contexts:", formatted_doc_snippets)
+    #print("FORMATTED Retrieved Code Contexts:" , formatted_code_snippets)
     # Step 4: Generate the final response
     response = rag_chain.generate_response(query, formatted_doc_snippets, formatted_code_snippets)
     print("Generated Response:", response)
@@ -150,7 +151,6 @@ def initialize():
     print(f"Total number of code_chunks: {len(code_chunks)}")
     print(f"Total number of doc_chunks: {len(doc_chunks)}")
 
-    filename = "test"
     vector_store = embed_documents_into_vectorstore(doc_chunks + code_chunks, EMBEDDING_MODEL_NAME, f"{DATA_DIR}/{filename}")
     llm = get_groq_llm(LLM_MODEL_NAME, LLM_TEMPERATURE, GROQ_API_KEY)