fix: embed a document's passages in small batches
Indexing a very long document (a few hundred pages) pushed all of its passages through the embedding model in a single call, which exhausted memory on a small machine and could stall or kill the process. Passages are now embedded in small chunks, so a document of any length indexes within a steady, small amount of memory. Order is unchanged.
| Repository | wardethan2000-eng/mike |
|---|---|
| Author | Ethan Ward <ethanward321@hotmail.com> |
| Authored | |
| Parents | 9ddfc71a |
| Stats | 1 file changed , +16 , -5 |
| Part of | Matter-wide document search and grounded answers |
Capture this commit into my fork
Download a Markdown prompt that tells Claude how to port this
exact commit into your working tree. Run it via
claude -p < capture-commit-9c473ec2.md
from inside the repo you want the change in.