Find answers from the community

Updated 3 months ago

Hi everyone I am using openai gpt 3 5 as

Hi everyone I am using openai gpt-3.5 as my llm for my chat engine and it is answering questions outside of the knowledge base. Is there anything i can do to either ensure a closed domain or stop the hallucination?
L
z
9 comments
Are you setting a system prompt for your chat engine?
yes I have been setting up a system prompt in addition to testing without a system prompt
What kind of system prompt have you been trying? πŸ‘€
I have tried a few but they are all fairly similar along the lines of specifying the role of the system and then ending with "If the question does not make any sense, explain why it does not make sense. Do not generate false info or give hypothetical answers.
Do you know what information is in the index ahead of time? Might be good to add a line like "If the question does not relate to {X}, inform the user that you can't help them with that."
yes i can definitely try this thank you!
I also noticed in the node postprocessors there was one to set a minimum similarity score for the documents retrieved is there anything to compare the response afterthe fact
Good question! That is something I want to add soon actually

Node post-processors are mainly focused on retrieval (i.e. fetching nodes, post-processing them, and then handing them to the LLM)

We have some output parsing stuff, but It's kind of clunky, and only works with query engines
Ah okay thank you so much for all your help and I look forward to it!
Add a reply
Sign up and join the conversation on Discord