News for hackers. Stuff that matters.

A comment on GPT-4. Parent comment

Re:GPT-4 by fzliu on Tuesday March 14, 2023 @03:04PM (#35156817)
One way to get around context length is to perform embedding and retrieval of your entire corpus. Langchain (https://langchain.readthedocs.io/en/latest/) and Milvus (https://milvus.io) is one of the stacks you can use.
[ Parent | on HN ]
Re:GPT-4 by ComplexSystems on Tuesday March 14, 2023 @06:21PM (#35159881)
Can you elaborate on how this works?
[ Parent | on HN ]
Re:GPT-4 by teaearlgraycold on Tuesday March 14, 2023 @10:46PM (#35163108)
You run the corpus through the model piecemeal, recording the model's interpretation for each chunk as a vector of floating point numbers. Then when performing a completions request you first query the vectors and include the closest matches as context.
[ Parent | on HN ]