Roadmap: SQLite vector quantization at scale; drop competitor numbers#260
Merged
Conversation
…umbers The quantize-and-rescore item targets the documented on-ramp scale boundary. The Zep/mem0 parenthetical goes: a fact-check showed those reference points aren't like-for-like (and one was never the vendor's own number) — the receipts-first framing stands on its own. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
There was a problem hiding this comment.
Your trial has ended. Reactivate Greptile to resume code reviews.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds the quantized-embeddings + rescore roadmap item for the SQLite on-ramp's vector-scale boundary (inspired by Google's TurboQuant results, shipped as boring proven int8/binary + rescore, no new dependencies). Also removes the Zep/mem0 parenthetical from the baseline line — the pre-launch fact-check found those numbers not like-for-like comparable, and our receipts-first framing doesn't need them.
🤖 Generated with Claude Code