v1.4.14

HKUDS/LightRAGv1.4.14Apr 12, 2026by danielaskdd

AI Summary

This release adds support for MongoDB Atlas Local Docker and introduces batch graph operations for large-scale imports. It also includes a new AG2 multi-agent demo and fixes for JWT algorithm confusion.

Key Highlights

  • Support for Atlas Local Docker for Mongo vector storage
  • Batch graph operations for large-scale imports
  • Added AG2 multi-agent demo
  • Fixed JWT algorithm confusion attack

New Features

  • MongoDB Atlas Local support
  • Multi-agent demo integration
  • Graph operation performance improvements

Full Release Notes

## What's New
* feat(setup): **support Atlas Local Docker for Mongo vector storage** by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2925
* perf: batch graph operations in ainsert_custom_kg for large-scale imports by @nszhsl in https://github.com/HKUDS/LightRAG/pull/2910
* examples: add AG2 multi-agent demo with LightRAG retrieval by @faridun-ag2 in https://github.com/HKUDS/LightRAG/pull/2867

## What's Fixed
* fix: remove redundant file_path_placeholder lookup in _merge_edges_then_upsert by @jwchmodx in https://github.com/HKUDS/LightRAG/pull/2877
* chore: remove dead config.ini / configparser code by @jwchmodx in https://github.com/HKUDS/LightRAG/pull/2887
* chore: remove dead OLLAMA_NUM_CTX / args.ollama_num_ctx assignment by @jwchmodx in https://github.com/HKUDS/LightRAG/pull/2888
* fix(webui): resolve all bun run lint errors in lightrag_webui by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2891
* chore(webui): migrate ESLint stylistic plugin by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2893
* docs(readme): restructure documentation and consolidate core api by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2896
* fix pipeline status history trimming by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2897
* fix: Corrected exception handling for LLM API timeouts where the subclass incorrectly passes keyword args by @hillct in https://github.com/HKUDS/LightRAG/pull/2902
* Improve LLM API failure diagnostics by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2903
* docs: deprecate config.ini in documentation by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2905
* fix(auth): prevent JWT algorithm confusion attack (GHSA-8ffj-4hx4-9pgf) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2907
* fix(api): add missing metadata field in /query/data error response by @lawrence3699 in https://github.com/HKUDS/LightRAG/pull/2923
* fix(utils): **prevent remove_think_tags from truncating responses with embedded <think> tags** by @sjhddh in https://github.com/HKUDS/LightRAG/pull/2900
* fix(opensearch): **ensure consistent by lazy index refresh and real-time edge lookups** by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2926
* fix(kg): **correct omission of isolated nodes in `get_knowledge_graph` during full graph retrieval** by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2928

## New Contributors
* @jwchmodx made their first contribution in https://github.com/HKUDS/LightRAG/pull/2877
* @hillct made their first contribution in https://github.com/HKUDS/LightRAG/pull/2902
* @faridun-ag2 made their first contribution in https://github.com/HKUDS/LightRAG/pull/2867
* @lawrence3699 made their first contribution in https://github.com/HKUDS/LightRAG/pull/2923
* @sjhddh made their first contribution in https://github.com/HKUDS/LightRAG/pull/2900
* @nszhsl made their first contribution in https://github.com/HKUDS/LightRAG/pull/2910

**Full Changelog**: https://github.com/HKUDS/LightRAG/compare/v1.4.13...v1.4.14