LlamaIndex
Log in

Find answers from the community

Updated 2 months ago

Hi the chat example uses

TTiago Freitas
·
Hi, the chat example uses ConversationBufferMemory as the langchain memory. Has anyone used a vector store to save the conversation history long term?
j
T
7 comments
jjerryjliu0
you can actually also use llamaindex modules as memory components too!
jjerryjliu0
would be curious for you to try it out + lmk what you think '
jjerryjliu0
https://gpt-index.readthedocs.io/en/latest/how_to/using_with_langchain.html#llama-demo-notebook-tool-memory-module
TTiago Freitas
I am testing now and will let you know my findings
TTiago Freitas
why do all examples use temperature=0?
jjerryjliu0
to make the outputs a bit less random by default 🙂
jjerryjliu0
easier to reproduce issues
Add a reply
Sign up and join the conversation on Discord