Update app.py

app.py

@@ -45,6 +45,7 @@ def invoke(openai_api_key, use_rag, prompt):
         if (os.path.isdir(CHROMA_DIR)):
             vector_db = Chroma(embedding_function = OpenAIEmbeddings(),
                                persist_directory = CHROMA_DIR)
+            print(os.listdir("Load DB"))
         else:
             loader = GenericLoader(YoutubeAudioLoader([YOUTUBE_URL], YOUTUBE_DIR), 
                                    OpenAIWhisperParser())
@@ -55,6 +56,7 @@ def invoke(openai_api_key, use_rag, prompt):
             vector_db = Chroma.from_documents(documents = splits, 
                                               embedding = OpenAIEmbeddings(), 
                                               persist_directory = CHROMA_DIR)
+            print(os.listdir("Make DB"))
         rag_chain = RetrievalQA.from_chain_type(llm, 
                                                 chain_type_kwargs = {"prompt": RAG_CHAIN_PROMPT}, 
                                                 retriever = vector_db.as_retriever(search_kwargs = {"k": 3}), 
@@ -65,7 +67,7 @@ def invoke(openai_api_key, use_rag, prompt):
     else:
         chain = LLMChain(llm = llm, prompt = LLM_CHAIN_PROMPT)
         result = chain.run({"question": prompt})
-        print(os.listdir("/data/chroma/"))
+    print(os.listdir("/data/chroma/"))
     return result
 
 description = """<strong>Overview:</strong> The app demonstrates how to use a Large Language Model (LLM) with Retrieval Augmented Generation (RAG) on external data