LightRAG - Browse /v1.5.7 at SourceForge.net

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2026-09-02	21.1 kB	0
v1.5.7 source code.tar.gz	2026-09-02	9.0 MB	1
v1.5.7 source code.zip	2026-09-02	9.7 MB	0
Totals: 3 Items		18.7 MB	1

Important Notes

New Feature: Add end-user-facing entry point to WebUI

v1.5.7 adds a second, end-user-facing entry — /workspace — together with the branding and prompt controls a deployment needs before it can be handed to real users.

A query-only entry for end users: /workspace
Customizable welcome, login and empty-state pages
A global USER_PROMPT_PREFIX

/workspace UI shows the chat surface and nothing else — no document management, no knowledge graph, no API-docs links — and is built for mobile use. Point UI_TEMPLATES_DIR at a small directory of Markdown files plus a manifest.json, and LightRAG serves your welcome page, login-page blurb, query empty state, brand logo and copyright line — in several languages, without rebuilding the WebUI. A locale that declares both a login blurb and an agreement document also switches on a login consent checkbox. A ready-to-copy bundle ships in docs/ui_templates_example/.

USER_PROMPT_PREFIX (or USER_PROMPT_PREFIX_FILE for long, multi-paragraph text) prepends deployment-wide instructions to every request's user_prompt. It gives the operator one place to set the LLM's role, tone and output format — Mermaid diagrams, LaTeX delimiters, citation style — for both UI entries and the API alike. Requests can never read or replace it; only the API field disable_user_prompt_prefix opts out.

For more information, please refer to:

docs/LightRAG-API-Server.md (github.com) — § The /workspace Query Entry
docs/UserDefinedUI.md (github.com) — the complete UI customization guide, plus docs/ui_templates_example/
README.md (github.com) — USER_PROMPT_PREFIX / USER_PROMPT_PREFIX_FILE

What's New

Add an offline tool to migrate a graph from Apache AGE to PostgreSQL tables by @ysys143 in https://github.com/HKUDS/LightRAG/pull/3620
feat: support graph-first ingestion with deferred vector indexing by @letsgetai in https://github.com/HKUDS/LightRAG/pull/3473
feat: add explicit custom chunking selector by @er-s-an in https://github.com/HKUDS/LightRAG/pull/3665
feat(api): add ENABLE_API_DOCS switch for API documentation exposure by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3672
perf(nano): defer vector deletes to flush time by @0xPabloxx in https://github.com/HKUDS/LightRAG/pull/3680
perf(faiss): defer vector deletes to flush time by @yzxcj797 in https://github.com/HKUDS/LightRAG/pull/3693
feat(Bedrock): Allow Bedrock default credential providers by @a-bruhn in https://github.com/HKUDS/LightRAG/pull/3726
feat(ollama): report token usage through the TokenTracker contract by @YashvantHange in https://github.com/HKUDS/LightRAG/pull/3747
feat(webui): standalone /workspace query entry for end users (dual-entry WebUI) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3729
feat(webui): add a login-page consent gate driven by the UI bundle by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3755
feat(webui): use WEBUI_TITLE as the browser tab title by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3763
Add user-defined UI customization bundle support (UI_TEMPLATES_DIR) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3765
Use custom logo and deployment title on login page by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3768
feat(webui): customer-defined copyright line at the foot of the pre-login pages by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3773
feat(query): Add global user prompt prefix feature with cache partitioning by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3781
refactor: remove the deprecated GET /documents listing and get_docs_by_status by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3788

What's Changed

fix(kg): return copies from NetworkXStorage get_node and get_edge by @santhreal in https://github.com/HKUDS/LightRAG/pull/3588
fix(operate): compute most common entity type and normalize keywords on rebuild by @santhreal in https://github.com/HKUDS/LightRAG/pull/3589
fix(kg): return boolean values from get_all_update_flags_status by @santhreal in https://github.com/HKUDS/LightRAG/pull/3590
fix(utils): split GRAPH_FIELD_SEP in merge_source_ids by @santhreal in https://github.com/HKUDS/LightRAG/pull/3592
fix(utils): correct docstring example and harden compute_incremental_chunk_ids by @santhreal in https://github.com/HKUDS/LightRAG/pull/3591
fix(parser): bound native markdown image downloads per document (GHSA-25c3-j78v-83qx) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3605
fix(kg): hydrate track docs via shared row helper and catch TypeError by @santhreal in https://github.com/HKUDS/LightRAG/pull/3595
fix(kg): make get_knowledge_graph truncation deterministic across graph backends by @santhreal in https://github.com/HKUDS/LightRAG/pull/3593
fix(security): bound DOCX decompression and contain sidecar image paths by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3614
fix(rebuild_vdb): drop lossy agtype quote-strip that corrupts quote-bearing entity_ids by @ysys143 in https://github.com/HKUDS/LightRAG/pull/3587
fix(extraction): surface token-limit truncation and fail on empty truncated responses by @pengpengyi92 in https://github.com/HKUDS/LightRAG/pull/3607
build(deps): bump the github-actions group with 2 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3616
fix(parser): enforce OOXML member and DOCX image budgets by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3619
fix(graph): validate attributes on the manual entity/relation APIs (GHSA-c922-pw4m-4wcv) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3623
fix(kg): enforce the graph-attribute contract in the backends that need it by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3624
fix(api): reject unstorable characters in a document source by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3626
fix(graph): preserve self-loops on entity rename by @pengpengyi92 in https://github.com/HKUDS/LightRAG/pull/3622
fix(graph): reject self-loop relations at the manual write paths by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3625
perf(kg): drop the seed-degree round trip from PGTable traversal by @ysys143 in https://github.com/HKUDS/LightRAG/pull/3618
fix(milvus): page vector/id lookups to respect the gRPC response ceiling [#3584] by @El-Tatane in https://github.com/HKUDS/LightRAG/pull/3629
fix: forward embedding_dim to Ollama's embed API by @Vishwamitra in https://github.com/HKUDS/LightRAG/pull/3604
fix: disable thinking for Ollama extract/keyword roles by default by @Vishwamitra in https://github.com/HKUDS/LightRAG/pull/3599
fix(base): tolerate undeclared fields when rehydrating DocProcessingStatus by @qianheng-aws in https://github.com/HKUDS/LightRAG/pull/3633
fix(llm): close OpenAI stream/client when GeneratorExit interrupts a mid-COT close by @AmirF194 in https://github.com/HKUDS/LightRAG/pull/3635
fix(api): fail fast for custom Ollama embedding dimensions by @pengpengyi92 in https://github.com/HKUDS/LightRAG/pull/3636
build(deps-dev): bump the build-tools group in /lightrag_webui with 5 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3641
build(deps): bump the react group across 1 directory with 3 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3639
build(deps): bump lucide-react from 1.26.0 to 1.29.0 in /lightrag_webui in the ui-components group by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3640
build(deps): bump the content-rendering group across 1 directory with 2 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3642
build(deps): bump the frontend-minor-patch group across 1 directory with 4 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3643
fix(kg): refuse PGGraphStorage on Apache AGE >= 1.8.0, which crashes the backend by @ysys143 in https://github.com/HKUDS/LightRAG/pull/3621
Refactor/parser cancellation exception rename by @MasaSN in https://github.com/HKUDS/LightRAG/pull/3637
refactor(neo4j): clarify batch edge read contract by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3648
Add an offline tool to migrate a graph from Apache AGE to PostgreSQL tables by @ysys143 in https://github.com/HKUDS/LightRAG/pull/3620
fix(api): preserve source files when deleting duplicate markers by @pengpengyi92 in https://github.com/HKUDS/LightRAG/pull/3632
docs: fix broken example links in programming guide by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3649
docs: fix outdated defaults and env var names by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3653
fix(parser): bound external result downloads for MinerU and Docling by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3638
fix(webui): harden graph type color resolution against reserved property names by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3655
docs(env.example): add the missing EXTRACT role variables by @torvalstrom in https://github.com/HKUDS/LightRAG/pull/3651
fix(lmdeploy): preserve do_sample setting by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3654
fix(parser): prevent quadratic Markdown image parsing by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3656
feat: support graph-first ingestion with deferred vector indexing by @letsgetai in https://github.com/HKUDS/LightRAG/pull/3473
fix(api): generalize EMBEDDING_DIM startup guard to all embedding bindings by @ClaireXi99 in https://github.com/HKUDS/LightRAG/pull/3646
docs: document OrcaRouter as an OpenAI-compatible LLM binding by @Marc-oss-hub in https://github.com/HKUDS/LightRAG/pull/3650
fix: warn when selectors bypass custom chunking by @er-s-an in https://github.com/HKUDS/LightRAG/pull/3662
fix(chunker): reject negative token overlap by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3663
fix(rerank): reject negative chunk overlap by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3667
fix(lollms): honour configured binding host by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3668
feat: add explicit custom chunking selector by @er-s-an in https://github.com/HKUDS/LightRAG/pull/3665
build(deps): update openai requirement from <3.0.0,>=2.0.0 to >=2.0.0,<4.0.0 by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3670
feat(api): add ENABLE_API_DOCS switch for API documentation exposure by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3672
fix(merge): amerge_entities relation weight must track distinct-source count, not max by @AmirF194 in https://github.com/HKUDS/LightRAG/pull/3674
fix(postgres): make AGE graph initialization idempotent by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3677
fix(hf): exclude padding tokens from embedding pooling by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3675
fix(kg): rank BFS levels by degree then label on mongo and opensearch by @Dhruv-kys in https://github.com/HKUDS/LightRAG/pull/3652
Fix chunk-tracking reseed: distinguish absent row from present-but-empty row (#3609) by @jaideeppyne in https://github.com/HKUDS/LightRAG/pull/3660
fix(graph): enforce relation evidence weight floor by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3676
fix(hf): place generation inputs on model device by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3678
fix(hf): honor generation token limits by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3687
fix(lmdeploy): honor native max_new_tokens by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3689
fix(ollama): map max_tokens to num_predict by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3690
build(deps): bump lucide-react from 1.29.0 to 1.31.0 in /lightrag_webui in the ui-components group by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3682
build(deps-dev): bump the build-tools group in /lightrag_webui with 2 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3683
build(deps): bump the frontend-minor-patch group in /lightrag_webui with 4 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3684
build(deps): bump react-dropzone from 15.0.0 to 19.1.1 in /lightrag_webui by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3685
fix(gemini): map max_tokens to max_output_tokens by @AmirF194 in https://github.com/HKUDS/LightRAG/pull/3696
fix(lollms): map max_tokens to n_predict by @Shizoqua in https://github.com/HKUDS/LightRAG/pull/3692
test(utils): cover validate_file_path_security and subtract_source_ids by @YashvantHange in https://github.com/HKUDS/LightRAG/pull/3702
fix(faiss): materialize an overwrite in one atomic rebuild by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3705
fix(kg): keep unsaved upserts as a redo log and replay them after a reload by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3709
fix(llm): close OpenAI stream on GeneratorExit during error-path COT close by @JessYanCoding in https://github.com/HKUDS/LightRAG/pull/3713
fix(openai): encode embedding input with disallowed_special=() by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3718
fix(embeddings): keep provider API keys request-local by @pengpengyi92 in https://github.com/HKUDS/LightRAG/pull/3717
chore(deps): allow pandas 3.x by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3719
fix(tokenizer): bisect the prefix bracket instead of clamping to one char by @JessYanCoding in https://github.com/HKUDS/LightRAG/pull/3722
fix(pipeline): keep generated failure summary within varchar(255) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3735
fix(llm): stop retrying permanent spend-stop 429s (LiteLLM budget_exceeded / OpenAI insufficient_quota) by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3736
fix(extraction): stop dumping full chunk id list in KEEP skip log by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3737
build(deps-dev): bump @types/react-dom from 19.2.4 to 19.2.5 in /lightrag_webui in the react group by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3730
build(deps): bump lucide-react from 1.31.0 to 1.33.0 in /lightrag_webui in the ui-components group by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3731
build(deps-dev): bump the build-tools group in /lightrag_webui with 2 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3732
build(deps): bump mermaid from 11.16.1 to 11.17.0 in /lightrag_webui in the content-rendering group across 1 directory by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3733
build(deps): bump the frontend-minor-patch group across 1 directory with 4 updates by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3734
fix(kg): save FaissVectorDBStorage off the event loop by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3742
fix: move file-backend persistence off the event loop by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3740
fix: keep LoLLMs stream session alive by @gry67673905 in https://github.com/HKUDS/LightRAG/pull/3741
fix(webui): keep the document list refreshing when the backend stalls by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3743
fix: accept valid empty JSON extraction results in cache rebuild by @AmirF194 in https://github.com/HKUDS/LightRAG/pull/3745
fix(extraction): report an unparseable rebuild payload once, not twice by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3749
🐛 fix(webui): stop the conversation area from scrolling horizontally on phones by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3750
Fix WebUI document refresh after BFCache restore by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3751
fix(webui): show workspace description in tooltip by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3769
fix(setup): enable UI templates in compose by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3770
fix(setup): close the lightrag service at any top-level compose key by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3772
refact(webui): Let the bundle name and render the login consent document by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3771
fix(query): enforce meaningful RAG query length by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3776
fix(query): refuse empty prompts and stop walking whole queries by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3780
fix(reproduce): batch_eval.py always exits with TypeError — give it a CLI by @Anai-Guo in https://github.com/HKUDS/LightRAG/pull/3779
refact(test): add React component tests and test harness isolation checks by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3783
fix: read evaluation datasets as UTF-8 by @zjn20030811 in https://github.com/HKUDS/LightRAG/pull/3782
Fail legibly when bun test runs without the DOM preload by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3784
perf(chunker): defer whole-document encode to the fixed-window path by @hata33 in https://github.com/HKUDS/LightRAG/pull/3758
refac(test): convert five source-text WebUI tests to real renders by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3786
refactor(webui): drop the buildLegacyDocs compatibility layer left over from GET /documents by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3791
test(webui): stop replacing the window global in the workspace entry test by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3793
fix(export): stop aexport_data crashing on backends without client_storage by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3785
perf(operate): encode chunk-invariant extraction prompts once per run by @hata33 in https://github.com/HKUDS/LightRAG/pull/3760
test(extraction): pin the gleaning guard arithmetic and lazy invariant precompute by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3787
docs: clarify file processing concurrency limits by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3794
test(webui): finish converting source-text tests to real renders by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3792
chore(deps): update anthropic requirement from <1.0.0,>=0.18.0 to >=0.18.0,<2.0.0 by @dependabot[bot] in https://github.com/HKUDS/LightRAG/pull/3795
chore(deps): widen spacy ceiling to <3.8.17, lock to 3.8.16 by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3797
docs(workspace): document the query entry, and show its parameter scope in the WebUI by @danielaskdd in https://github.com/HKUDS/LightRAG/pull/3798