v1.5.4

aidenybai/react-grabv1.5.4Jun 24, 2026by danielaskdd

AI Summary

A feature-rich release improving Markdown parsing capabilities, optimizing large knowledge graph rendering in the web UI, and fixing critical security vulnerabilities.

Key Highlights

  • Native Markdown parsing engine with base64 image support
  • Improved graph rendering efficiency for large knowledge graphs
  • Security fixes preventing guest token bypass and path traversal
  • Enhanced chunking strategy tuning via per-file parameters

New Features

  • Native Markdown parsing including .textpack bundles
  • Per-file engine parameters via hint/rule
  • New 'drop_references' option in P chunking strategy
  • HVTracker trust badge in documentation

Full Release Notes

## What's New
* feat(parser): native engine **support for Markdown parsing**, including **embedded base64 images** and `.textpack` bundle image integration by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3280
* feat(parser): per-file engine parameters via hint/rule (Phase 2 — MinerU + Docling) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3284
* perf(webui): made graph rendering more efficient -> large knowledge graphs now usable by @Xaverrrrr in https://github.com/HKUDS/LightRAG/pull/3304

## What's Changed
* Add parameterized parser hints for chunk strategy tuning by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3282
* feat(chunker): add drop_references option to P chunking strategy by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3285
* feat(webui): reorder query modes and warn on lower-quality modes by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3287
* fix(mineru): drop page_number items from blocks content by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3288
* fix(storage): handle set ids in delete (Issue #3286) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3289
* Fixed typo (Dokcer -> Docker) by @aleksvujic in https://github.com/HKUDS/LightRAG/pull/3291
* refactor(parser): move all chunking out of the docx parser by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3295
* fix(api): stop guest tokens from bypassing X-API-Key auth by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3319
* fix(api): don't pair wildcard CORS origin with credentials by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3317
* docs(README): add optional HVTracker trust badge by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3320
* fix(sidecar): prevent path traversal in asset materialization by @VectorPeak in https://github.com/HKUDS/LightRAG/pull/3316

## New Contributors
* @VectorPeak made their first contribution in https://github.com/HKUDS/LightRAG/pull/3316

**Full Changelog**: https://github.com/HKUDS/LightRAG/compare/v1.5.3...v1.5.4