Update app.py

app.py

@@ -22,7 +22,12 @@ from llama_index.core import PromptTemplate
 from llama_index.core.llms import ChatMessage, MessageRole
 from llama_index.core.chat_engine import CondenseQuestionChatEngine
 
+# Helps asyncio run within Jupyter
+import nest_asyncio
+import asyncio
+nest_asyncio.apply()
 
+# load env file
 load_dotenv()
 GROQ_API_KEY = os.getenv('GROQ_API_KEY')
 LLAMAINDEX_API_KEY = os.getenv('LLAMAINDEX_API_KEY')
@@ -69,7 +74,7 @@ else:
     )
     documents = reader.load_data()
     print("index creating with `%d` documents", len(documents))
-    index = VectorStoreIndex.from_documents(documents, embed_model=embed_model, transformations=[splitter])
+    index = VectorStoreIndex.from_documents(documents, embed_model=embed_model, transformations=[splitter], use_async=True)
     index.storage_context.persist(persist_dir="./vectordb")
 
 """
@@ -113,6 +118,7 @@ retriever = DocumentSummaryIndexEmbeddingRetriever(
 retriever = VectorIndexRetriever(
     index = index,
     similarity_top_k = 10,
+    use_async=True
     #vector_store_query_mode="mmr",
     #vector_store_kwargs={"mmr_threshold": 0.4}
 )
@@ -197,7 +203,7 @@ with gr.Blocks() as demo:
     def bot(history):
         user_message = history[-1][0]
         #bot_message = chat_engine.chat(user_message)
-        bot_message = query_engine.query(user_message + "Let's think step by step to get the correct answer. If you cannot provide an answer, say you don't know.")
+        bot_message = query_engine.aquery(user_message + "Let's think step by step to get the correct answer. If you cannot provide an answer, say you don't know.")
         history[-1][1] = ""
         for character in bot_message.response:
             history[-1][1] += character