Update app.py

app.py

@@ -28,7 +28,7 @@ YOUTUBE_DIR = "docs/youtube"
 MODEL_NAME  = "gpt-4"
 
 def invoke(openai_api_key, youtube_url, process_video, prompt):
-    openai.api_key = openai_api_key
+    #openai.api_key = openai_api_key
     if (process_video):
         if (os.path.isdir(CHROMA_DIR)):
             shutil.rmtree(CHROMA_DIR)
@@ -41,11 +41,10 @@ def invoke(openai_api_key, youtube_url, process_video, prompt):
         vector_db = Chroma.from_documents(documents = splits, embedding = OpenAIEmbeddings(), persist_directory = CHROMA_DIR)
     else:
         vector_db = Chroma(persist_directory = CHROMA_DIR, embedding_function = OpenAIEmbeddings())
-    llm = ChatOpenAI(model_name = MODEL_NAME, temperature = 0)
+    llm = ChatOpenAI(model_name = MODEL_NAME, openai_api_key = openai_api_key, temperature = 0)
     qa_chain = RetrievalQA.from_chain_type(llm, retriever = vector_db.as_retriever(search_kwargs = {"k": 3}), return_source_documents = True, chain_type_kwargs = {"prompt": QA_CHAIN_PROMPT})
     result = qa_chain({"query": prompt})
     #print(result)
-    print(openai.api_key)
     return result["result"]
 
 description = """<strong>Overview:</strong> The app demonstrates how to use a Large Language Model (LLM) with Retrieval Augmented Generation (RAG) on external data