Find answers from the community

Updated 7 months ago

I’m defining a chat engine and then

I’m defining a chat engine and then passing in a query engine with 10 docs (similarity_top_k) but it still defaults to 2 embeddings. I am using pgvector
L
m
4 comments
@Logan M something like this

query_engine=index.as_query_engine(llm=Settings.llm,streaming=true,similarity_top_k=10)

chat_engine=index.as_chat_engine(chat_mode=“condense_plus_text”, llm=Settings.llm,memory=ChatMemoryBuffer.from_defaults(token_limit=3900),query_engine=query_engine)
the query engine doesn't get passed in that way 👀

Just do chat_engine=index.as_chat_engine(chat_mode=“condense_plus_text”, memory=ChatMemoryBuffer.from_defaults(token_limit=3900), similarity_top_k=10)
This worked ! Thank you so much
Add a reply
Sign up and join the conversation on Discord