Update app.py

app.py

@@ -22,28 +22,27 @@ template = """Use the following pieces of context to answer the question at the
 
 QA_CHAIN_PROMPT = PromptTemplate(input_variables = ["context", "question"], template = template)
 
-print(0)
-
-qa_chain = None 
+YOUTUBE_DIR = "docs/youtube/" 
+CHROMA_DIR = "docs/chroma/"
 
 def invoke(openai_api_key, youtube_url, prompt):
     openai.api_key = openai_api_key
     global qa_chain
-    if (os.path.isdir("docs/chroma/") == False):
+    if (os.path.isdir(CHROMA_DIR) == False):
         print(1)
-        youtube_dir = "docs/youtube/"
-        loader = GenericLoader(YoutubeAudioLoader([youtube_url], youtube_dir), OpenAIWhisperParser())
+        #youtube_dir = "docs/youtube/"
+        loader = GenericLoader(YoutubeAudioLoader([youtube_url], YOUTUBE_DIR), OpenAIWhisperParser())
         docs = loader.load()
         text_splitter = RecursiveCharacterTextSplitter(chunk_size = 1500, chunk_overlap = 150)
         splits = text_splitter.split_documents(docs)
-        chroma_dir = "docs/chroma/"
-        vectordb = Chroma.from_documents(documents = splits, embedding = OpenAIEmbeddings(), persist_directory = chroma_dir)
+        #chroma_dir = "docs/chroma/"
+        vectordb = Chroma.from_documents(documents = splits, embedding = OpenAIEmbeddings(), persist_directory = CHROMA_DIR)
         llm = ChatOpenAI(model_name = "gpt-4", temperature = 0)
         qa_chain = RetrievalQA.from_chain_type(llm, retriever = vectordb.as_retriever(), return_source_documents = True, chain_type_kwargs = {"prompt": QA_CHAIN_PROMPT})
     print(2)
     result = qa_chain({"query": prompt})
-    shutil.rmtree(youtube_dir)
-    #shutil.rmtree(chroma_dir)
+    #shutil.rmtree(YOUTUBE_DIR)
+    #shutil.rmtree(CHROMA_DIR)
     return result["result"]
 
 description = """The app demonstrates how to use a <strong>Large Language Model</strong> (LLM) with <strong>Retrieval Augmented Generation</strong> (RAG) on external data.