feat: find a matter's documents by meaning, not just words (stage 4)
Search now understands what a question means, not only the words in it. Ask "who pays if this goes wrong" and it finds an indemnity clause that never uses those words, alongside the exact-word and typo-tolerant searches that were already there. The three run together and their results are merged, so a passage found by more than one rises to the top; exact words are weighted a little above the rest, so a party name or a section number still lands first. The meaning of each passage is read on our own machine, from a small model (bge-small-en-v1.5) baked into the image, so no document text is sent outside for this. Passages stored before now are filled in with a command (backfillEmbeddings) that reads their text straight from the table, so no document has to be read again.
| Repository | wardethan2000-eng/mike |
|---|---|
| Author | Ethan Ward <ethanward321@hotmail.com> |
| Authored | |
| Parents | b3146cf1 |
| Stats | 9 files changed , +1176 , -7 |
| 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-d92fffd7.md
from inside the repo you want the change in.