Find answers from the community

Updated 2 months ago

Hey guys - Quick one - is there a way of

Hey guys - Quick one - is there a way of using llama index without using RAG? i.e. just for generating a response using Azure OpenAI ?

3 comments

The LLM objects all have complete() and chat() functions -- you can use those directly

awesome, sorry to sound dumb, do you have an example?

Plain Text

resp = llm.complete("Hello world")
resp = llm.chat([ChatMessage(role="user", content="Hello world")])

Add a reply