Update main.py

main.py

@@ -7,11 +7,11 @@ from langchain.schema.runnable.config import RunnableConfig
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.chains import ConversationalRetrievalChain
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
-from langchain.chains import LLMChain
+#from langchain.chains import LLMChain
 from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain.schema import StrOutputParser
 #from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT
-from langchain.chains.question_answering import load_qa_chain
+#from langchain.chains.question_answering import load_qa_chain
 from langchain.chains.qa_with_sources import load_qa_with_sources_chain
 from langchain.vectorstores import Pinecone
 import pinecone
@@ -157,19 +157,21 @@ async def start():
             chat_memory=message_history,
             return_messages=True,
         )
-        llm = ChatAnthropic()
+        #llm = ChatAnthropic()
         streaming_llm = ChatAnthropic(
             streaming=True,
             temperature=1,
             max_tokens=4000
         )
-        question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)
-        doc_chain = load_qa_chain(streaming_llm, chain_type="stuff")
+        #question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)
+        #doc_chain = load_qa_chain(streaming_llm, chain_type="stuff")
 
-        qa = ConversationalRetrievalChain(
+        qa = ConversationalRetrievalChain.from_llm(
+            streaming_llm,
+            chain_type="stuff",
             retriever=retriever,
-            combine_docs_chain=doc_chain,
-            question_generator=question_generator,
+            #combine_docs_chain=doc_chain,
+            #question_generator=question_generator,
             memory=memory,
             return_source_documents=True,
         )