Blog post: reasoning-based vectorless retrieval over the wiki#44
Merged
Conversation
New post "Similarity Isn't Relevance: How Draft Retrieves Context by Reasoning, Not Vectors" — explains tree-search retrieval over the OKF knowledge wiki (navigate routing descriptions, descend matching subtrees, terminate on coverage) versus top-k embedding similarity. No vector DB, no chunking, fully traceable. - web/blog/reasoning-retrieval/index.html: the post - web/blog/index.html: post card at top of the list - web/feed.xml: RSS item + lastBuildDate bump - web/sitemap.xml: new URL + blog index lastmod bump Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01PCYuQxnYefqsVGnbMMriXZ
mayurpise
marked this pull request as ready for review
June 20, 2026 16:46
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
A new blog post — "Similarity Isn't Relevance: How Draft Retrieves Context by Reasoning, Not Vectors" — companion to the recently merged tree-search retrieval procedure (#43).
It explains, for a general audience, how Draft locates context by navigating the knowledge wiki (reason over routing descriptions → descend matching subtrees → terminate on coverage) instead of running top-k similarity over embeddings: no vector DB, no chunking, no cloud, and a retrieval path you can audit.
Changes
web/blog/reasoning-retrieval/index.html— the post (modeled on the existing post template: head/meta/JSON-LD, nav, share, footer).web/blog/index.html— post card added at the top of the list (June 20, 2026).web/feed.xml— RSS<item>+lastBuildDatebump.web/sitemap.xml— new URL + blog-indexlastmodbump.Notes
pages.ymlworkflow on merge tomain.🤖 Generated with Claude Code
https://claude.ai/code/session_01PCYuQxnYefqsVGnbMMriXZ
Generated by Claude Code