Skip to content

feat: add Phase 1 RAG note chunking#60

Open
AliBenrami wants to merge 2 commits into
developfrom
Ali/phase-1-rag-chunking
Open

feat: add Phase 1 RAG note chunking#60
AliBenrami wants to merge 2 commits into
developfrom
Ali/phase-1-rag-chunking

Conversation

@AliBenrami

Copy link
Copy Markdown
Collaborator

What changed

  • Added a pure chunkNoteDocument RAG chunking utility for structured Editor.js note documents.
  • Added H1-H3 semantic heading boundaries with heading context carried into each chunk.
  • Added token-limit chunk splitting, oversized atomic block handling, and iterative nested-list serialization.

Why

Phase 1 of #57 needs chunk-level note units so later embedding, diffing, and retrieval phases can avoid broad whole-note embeddings.

How tested

  • ./node_modules/.bin/vitest.cmd run lib/rag/chunking.test.ts
  • ./node_modules/.bin/vitest.cmd run
  • ./node_modules/.bin/tsc.cmd --noEmit
  • ./node_modules/.bin/eslint.cmd .

@AliBenrami AliBenrami requested a review from hamizfaraz as a code owner June 11, 2026 02:49
@vercel

vercel Bot commented Jun 11, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
task-master Ready Ready Preview, Comment Jun 11, 2026 3:00am

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant