Update app.py

app.py

@@ -17,44 +17,13 @@ from langchain.agents import Tool, ZeroShotAgent, AgentExecutor
 from langchain.agents.agent_toolkits import create_retriever_tool, create_conversational_retrieval_agent
 from langchain import LLMChain
 
-text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=100)
-
-system_template = """
-Use the following pieces of context to answer the user's question.
-Please respond as if you were Ken from the movie Barbie. Ken is a well-meaning but naive character who loves to Beach. He talks like a typical Californian Beach Bro, but he doesn't use the word "Dude" so much.
-If you don't know the answer, just say that you don't know, don't try to make up an answer.
-You can make inferences based on the context as long as it still faithfully represents the feedback.
-
-Example of your response should be:
-
-```
-The answer is foo
-```
-
-Begin!
-----------------
-{context}"""
-
-messages = [
-    SystemMessagePromptTemplate.from_template(system_template),
-    HumanMessagePromptTemplate.from_template("{question}"),
-]
-prompt = ChatPromptTemplate(messages=messages)
-chain_type_kwargs = {"prompt": prompt}
-
-# @cl.author_rename
-# def rename(orig_author: str):
-#     rename_dict = {"RetrievalQA": "Consulting The Kens"}
-#     return rename_dict.get(orig_author, orig_author)
+llm = ChatOpenAI(model="gpt-3.5-turbo", temperature = 0)
 
 @cl.on_chat_start
 async def init():
     msg = cl.Message(content=f"Building Index...")
     await msg.send()
 
-    ### start building retrievers, stores and agents
-    llm = ChatOpenAI(model="gpt-3.5-turbo", temperature = 0)
-    
     barbie_wikipedia_docs = WikipediaLoader(query="Barbie (film)", load_max_docs=1, doc_content_chars_max=1_000_000).load()
     barbie_csv_docs = CSVLoader(file_path="./barbie_data/barbie.csv", source_column="Review_Url").load()
     oppenheimer_wikipedia_docs = WikipediaLoader(query="Oppenheimer (film)", load_max_docs=1, doc_content_chars_max=1_000_000).load()
@@ -106,8 +75,12 @@ async def init():
     opp_wikipedia_faiss_retriever = opp_wikipedia_faiss_store.as_retriever(search_kwargs={"k": 1})
     
     # set up ensemble retriever
-    barbie_ensemble_retriever = EnsembleRetriever(retrievers=[barbie_wikipedia_bm25_retriever, barbie_wikipedia_faiss_retriever],weights=[0.25, 0.75])
-    opp_ensemble_retriever = EnsembleRetriever(retrievers=[opp_wikipedia_bm25_retriever, opp_wikipedia_faiss_retriever],weights=[0.25, 0.75])
+    barbie_ensemble_retriever = await cl.make_async(EnsembleRetriever)(
+        retrievers=[barbie_wikipedia_bm25_retriever, barbie_wikipedia_faiss_retriever],
+        weights=[0.25, 0.75])
+    opp_ensemble_retriever = await cl.make_async(EnsembleRetriever(
+        retrievers=[opp_wikipedia_bm25_retriever, opp_wikipedia_faiss_retriever],
+        weights=[0.25, 0.75])
 
     # #### Retrieval Agent
     barbie_wikipedia_retrieval_tool = create_retriever_tool(