Update query_data.py

query_data.py

@@ -1,6 +1,7 @@
 from langchain.prompts.prompt import PromptTemplate
 from langchain.chains import ConversationalRetrievalChain
 from langchain.chat_models import ChatOpenAI
+
 # from langchain.llms import OpenAI
 
 # from langchain.chains.conversational_retrieval.prompts import CONDENSE_QUESTION_PROMPT,QA_PROMPT
@@ -30,11 +31,12 @@ Follow Up Input: {question}
 Standalone question:"""
 CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)
 
-prompt_template = """Give an answer to the question based on the context below and try to explain in detail and do 
-add source links if exist in context, and if you don't find the answer in the context, then simply say "That's a great 
-question, and I want to make sure I provide you with the most accurate and helpful information possible. 
-Unfortunately, our current pool of insights does not have an answer to this.", don't try to make up an answer And 
-also don't use "According to the information provided in the given links, " while giving an answer. 
+prompt_template = """Give an answer to the question based on the context below and try to explain in detail and use 
+bullet points if answer is long and do add source links if exist in context, and if you don't find the answer in the 
+context, then simply say "That's a great question, and I want to make sure I provide you with the most accurate and 
+helpful information possible. Unfortunately, our current pool of insights does not have an answer to this.", 
+don't try to make up an answer And also don't use "According to the information provided in the given links, 
+" while giving an answer. 
 
 {context}
 
@@ -50,7 +52,7 @@ def get_chain(vectorstore):
     # from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
     from langchain.chains.question_answering import load_qa_chain
     llm = ChatOpenAI(temperature=0)
-    streaming_llm = ChatOpenAI(streaming=True, temperature=0, max_tokens=300)
+    streaming_llm = ChatOpenAI(streaming=False, temperature=0, max_tokens=300, top_p=1)
     question_generator = LLMChain(llm=llm, prompt=CONDENSE_QUESTION_PROMPT)
     doc_chain = load_qa_chain(streaming_llm, chain_type="stuff", prompt=QA_PROMPT)
 
@@ -63,6 +65,6 @@ def get_chain(vectorstore):
 
     qa_chain = ConversationalRetrievalChain(return_source_documents=True,
                                             retriever=vectorstore.as_retriever(
-                                                search_kwargs={"k": 8, "include_metadata": True}),
+                                                search_kwargs={"k": 5, "include_metadata": True}),
                                             combine_docs_chain=doc_chain, question_generator=question_generator)
     return qa_chain