Re:CustomGPT
by geepytee on Monday February 13, 2023 @03:50PM
(#34780244)
davinci-003 has a 4k tokens cap, you cannot just 'shove all your information in the prompt.' Can parallelize but then rate limits become a problem. Really curious to hear how these guys are handling it.
[ Parent
| on HN ]
Re:CustomGPT
by KidComputer on Monday February 13, 2023 @03:56PM
(#34780317)
You shove the whole corpus in a vector db using embeddings, query the nearest neighbors to an input and inject those into a prompt to pass to GPT.
https://langchain.readthedocs.io/en/latest/modules/chains/co...