vincent
@pixel
FarcasterGPT
5 replies
1 recast
8 reactions
vincent
@pixel
1 reply
0 recast
0 reaction
vincent
@pixel
I actually tried building this, and the RAG was such a cumbersome process. But now OpenAI just abstracted the RAG away. Damn. No need to slice sentences, pick embedding model, worry about embedding DB. Upload then chat. Insane.
1 reply
0 recast
1 reaction
six
@six
What did you upload in this case?
1 reply
0 recast
0 reaction