Release v0.3.3: Advanced chunking methods and Windows CLI fix #44
Conversation
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
* feat: build architectural design for advanced chunking methods * feat: Implement token-based recursive chunking with `js-tiktoken` as the new default, removing word-based chunking and updating chunking configuration and documentation. * feat: Introduce pluggable chunker plugins including semantic, code, agentic, markdown, and hierarchical methods with CLI support. * chore: update .gitignore * lint: fix linter issues * feat: update chunking docs and add chunkers in install wizard * lint: fix linter issues * docs: update agent skills to introduce new chunking methods * feat: wire chunking in /install wizard & doctor command * docs: update chunking docs to match the documentation tone * feat: wire advanced chunkers to installation wizard * fix: lint and type errors * feat: add announcement for advanced chunking --------- Co-authored-by: Subhajit Kundu <subha60kundu@gmail.com>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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Outdated suggestions cannot be applied.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.
Summary
This release introduces pluggable advanced chunking methods as a major feature and fixes a CLI crash on Windows.
Changes
Feature: Advanced Chunking Methods (#43)
js-tiktokenas the new default.unrag add./installwizard and thedoctorcommand for validation.docs/(unrag)/chunking/.js-tiktokenas a new runtime dependency.Fix: Windows CLI Upgrade Crash
upgradeCLI command to crash on Windows.Files Changed
packages/unrag/registry/core/chunking.ts,types.ts,ingest.tspackages/unrag/registry/chunkers/{agentic,code,hierarchical,markdown,semantic}/packages/unrag/registry/chunkers/_shared/packages/unrag/cli/apps/web/app/install/apps/web/content/docs/(unrag)/chunking/packages/unrag/cli/lib/upgrade/snapshot.ts