Update app.py

app.py

@@ -44,7 +44,6 @@ 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("2 Load DB")
         else:
             loader = GenericLoader(YoutubeAudioLoader([YOUTUBE_URL], YOUTUBE_DIR), 
                                    OpenAIWhisperParser())
@@ -55,7 +54,6 @@ def invoke(openai_api_key, use_rag, prompt):
             vector_db = Chroma.from_documents(documents = splits, 
                                               embedding = OpenAIEmbeddings(), 
                                               persist_directory = CHROMA_DIR)
-            print("1 Create DB")
         rag_chain = RetrievalQA.from_chain_type(llm, 
                                                 chain_type_kwargs = {"prompt": RAG_CHAIN_PROMPT}, 
                                                 retriever = vector_db.as_retriever(search_kwargs = {"k": 3}), 
@@ -77,8 +75,6 @@ description = """<strong>Overview:</strong> The app demonstrates how to use a La
                  <li>Set "Retrieval Augmented Generation" to "<strong>True</strong>" and submit prompt "explain gpt-4". The LLM <strong>with</strong> RAG knows the answer.</li>
                  <li>Experiment with different prompts, for example "explain gpt-4 in german", "list pros and cons of gpt-4", or "write a poem about gpt-4".</li>
                  </ul>
-                 In a production system, embedding external data is done in a batch process. An idea for a production system is to perform LLM use cases on the 
-                 <a href='https://www.youtube.com/playlist?list=PL2yQDdvlhXf_hIzmfHCdbcXj2hS52oP9r'>AWS re:Invent playlist</a> (stand by).\n\n
                  <strong>Technology:</strong> <a href='https://www.gradio.app/'>Gradio</a> UI using <a href='https://platform.openai.com/'>OpenAI</a> API via AI-first 
                  <a href='https://www.langchain.com/'>LangChain</a> toolkit with <a href='https://openai.com/research/whisper'>Whisper</a> (speech-to-text) and 
                  <a href='https://openai.com/research/gpt-4'>GPT-4</a> (LLM) foundation models as well as AI-native <a href='https://www.trychroma.com/'>Chroma</a>