[rolisz]

Well you wouldn't input the whole Vault to the model, you would use embeddings to find the content that is most relevant to the question being asked.

[moffkalast]

Is that actually a thing yet? Proper vector DB integration? I sure would like to see some demos of that, as it's been hyped up a lot but I haven't really seen anyone deploy anything proper with it yet.

[rolisz]

Even PrivateGPT does that, using Chroma as vector DB