LightRAG Files

Important Notes

• Integrated OpenSearch as a unified storage backend, providing comprehensive support for all four LightRAG storage types: KV, Vector, Graph, and DocStatus.
• Introduced an interactive setup wizard to streamline configuration, replacing manual .env file editing. Support for local deployment of embedding, reranking, and storage backends via Docker Compose is now available. For further details, please refer to Interactive Setup Guide.

What's New

• Add OpenSearch as unified storage backend by @LantaoJin in https://github.com/HKUDS/LightRAG/pull/2739
• Add OpenSearchKVStorage support to LLM cache tools by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2790
• Add Makefile for quick deployment by @mlimarenko in https://github.com/HKUDS/LightRAG/pull/2548
• Refactor(Makefile): split monolithic wizard into modular env-base/storage/server targets by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2763
• Add OpenSearch storage configuration support to the interactive setup wizard by @LantaoJin in https://github.com/HKUDS/LightRAG/pull/2797
• perf(postgres): optimize KV storage upsert using executemany by @wkpark in https://github.com/HKUDS/LightRAG/pull/2742

What's Fixed

• Fix Qdrant large upsert payload failures with bounded batching by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2740
• build(deps): bump the github-actions group with 2 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/2737
• perf: use deque for BFS queue in get_knowledge_subgraph() by @giulio-leone in https://github.com/HKUDS/LightRAG/pull/2725
• perf: batch pre-compute query embeddings to eliminate sequential API round-trips by @errajibadr in https://github.com/HKUDS/LightRAG/pull/2729
• fix: reduce FaissVectorDBStorage meta.json file size by excluding vectors by @Br1an67 in https://github.com/HKUDS/LightRAG/pull/2733
• Enhance current MilvusVectorDBStorage with parameterized configuration by @hanlianlu in https://github.com/HKUDS/LightRAG/pull/2672
• fix: preserve failed-doc chunk metadata for reliable deletion cleanup by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2749
• fix: align zhipu adapter with official thinking and dimensions api by @ChenJiahao1 in https://github.com/HKUDS/LightRAG/pull/2775
• fix(operate,utils): correct typos in log messages and remove dead code by @lailoo in https://github.com/HKUDS/LightRAG/pull/2781
• perf(opensearch): Remove refresh="wait_for" from OpenSearch storage backends by @LantaoJin in https://github.com/HKUDS/LightRAG/pull/2786
• fix(api): sanitize workspace from CLI args and HTTP headers to prevent injection by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2792
• fix(api): normalize missing document file paths by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/2793
• fix: prevent None file_path from propagating as unknown_source by @he-yufeng in https://github.com/HKUDS/LightRAG/pull/2796

New Contributors

• @giulio-leone made their first contribution in https://github.com/HKUDS/LightRAG/pull/2725
• @errajibadr made their first contribution in https://github.com/HKUDS/LightRAG/pull/2729
• @Br1an67 made their first contribution in https://github.com/HKUDS/LightRAG/pull/2733
• @hanlianlu made their first contribution in https://github.com/HKUDS/LightRAG/pull/2672
• @LantaoJin made their first contribution in https://github.com/HKUDS/LightRAG/pull/2739
• @ChenJiahao1 made their first contribution in https://github.com/HKUDS/LightRAG/pull/2775
• @lailoo made their first contribution in https://github.com/HKUDS/LightRAG/pull/2781
• @he-yufeng made their first contribution in https://github.com/HKUDS/LightRAG/pull/2796

Full Changelog: https://github.com/HKUDS/LightRAG/compare/v1.4.10...v1.4.11