Repository navigation
docs: say precisely when an import stops on an embedding failure - #1607
Merged
Merged
Conversation
Writing a vector can fail softly; generating one still stops the import, as before.
🔍 Cora AI Code Review✅ No issues found. Code looks good! Review powered by cora-code · BYOK · MIT |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Wording of one CHANGELOG entry (0.22.0, "Import writes a memory like
rememberdoes", #1514 part 2): a vector that cannot be written leaves the row FTS5-only, but a vector that cannot be generated (backend down or rate-limited) still stops the import at that row, as before; rows already imported stay and importing again skips them through the duplicate check; a store with no backend imports keyword-only.Why
The Cora review of the v0.22.0 release PR (#1603) read the sentence as "import never fails on an embedding problem". The code did not change since v0.21.1; the sentence was imprecise. Stopping on a dead backend is deliberate for a bulk import (no silent import of thousands of rows without vectors).
Testing
Documentation only. The behaviour is covered by the existing import tests and the new keyword-only test of #1606.