The community member is interested in the kapa-gpt-index and wants to reproduce its effects on their own documents, but they are having difficulty. They ask how kapa organizes knowledge and if there are any best practices for this kind of technical documentation. In the comments, another community member asks whether the code and text should use the same vector or be separated.
I find the kapa-gpt-index is sooo great, and I try to reproduce this effect on our document, but it didn't work out very well. I would like to ask how kapa organizes knowledge, and is there any best practice for this kind of technical documentation?