Last active
January 13, 2024 00:53
-
-
Save jphme/598f3a6881b2c31af10ca03350458c5c to your computer and use it in GitHub Desktop.
Proof of Concept Split by Embeddings
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 random wiki articles copied together, the correct split is found immediately.
Could be improved in various (recursively splitting more granular pieces / smaller windows and parallelize everything) but I think the concept is sound and a good implementation will be very fast and flexible..