The web demo version of ChatGPT can sometimes, as you say, make things up! I asked it a question about an ancient war in Greece and it stated two facts and then just inventing stuff.
However, I would ask you to also consider something: when you supply prompt input text (this is the "context text" in the ChatGPT API calls) and then ask questions about the context text, it is very accurate. It also does a very good job when you give it context text from a few different sources, and it integrates them nicely.
It is more efficient to use embeddings for context text, as Llama-Index does.
However, I would ask you to also consider something: when you supply prompt input text (this is the "context text" in the ChatGPT API calls) and then ask questions about the context text, it is very accurate. It also does a very good job when you give it context text from a few different sources, and it integrates them nicely.
It is more efficient to use embeddings for context text, as Llama-Index does.