github HKUDS/LightRAG v1.5.0rc1

8 hours ago

Breaking Changes

  • The ENTITY_TYPES environment variable has been deprecated; Please replace it with ENTITY_TYPE_PROMPT_FILE before launching this new version.

Major Improvements

  • Implement role-specific LLM configuration support, introducing four distinct roles—EXTRACT, QUERY, KEYWORDS, and VLM—each with independent LLM settings.
  • Enable task-aware embedding support for asymmetric models, including voyage-3, text-embedding-004, embed-multilingual-v3.0, and jina-embeddings-v3.
  • Add optional JSON-formatted LLM output to enhance stability in the entity and relation extraction pipeline.
  • Introduce ENTITY_TYPE_PROMPT_FILE to empower users with enhanced guidance for LLM-driven entity type recognition and extraction.
  • Fully support Amazon and Anthropic models on *AWS Bedrock API.

What's Changed

  • feat: explicit voyageai embed support by @laszukdawid in #2484
  • feat: Add task-aware embedding support by @StoreksFeed in #2560
  • feat: integrate structured extraction and multimodal processing pipeline by @MrGidea in #2830
  • ♻️ refactor(documentManager): reorganize document status filtering by @danielaskdd in #2851
  • feat: enhance entity extraction stability dev by @yunzhongxiaxi in #2864
  • Remove config.ini from compose samples by @danielaskdd in #2906
  • fix: handle OpenAI length finish reason fallback by @danielaskdd in #2913
  • feat(extraction): configurable per-response entity/relation limits by @danielaskdd in #2950
  • ♻️ refactor(llm): unify keyword extraction across providers by @danielaskdd in #2953
  • ♻️ refactor(llm): unify structured output control via response_format by @danielaskdd in #2956
  • refactor(bedrock): support default and custom endpoints by @danielaskdd in #2958
  • refactor(gemini): improve default endpoint handling and sdk integration by @danielaskdd in #2957
  • refactor(setup): use sentinel endpoints for Gemini and Bedrock defaults by @danielaskdd in #2959
  • fix: remove stream parameter from .parse() call when response_format is present by @PaulTitto in #2965
  • perf(postgres): use binary parameter for vector similarity queries by @wkpark in #2949
    #2966
  • feat(bedrock): Rename aws_bedrock to bedrock and implement comprehensive option support by @danielaskdd in #2966
  • chore(deps): bump react-router-dom from 7.14.0 to 7.14.1 in /lightrag_webui in the react group by @dependabot[bot] in #2967
  • feat(prompt): externalize entity type extraction profiles by @danielaskdd in #2964
  • chore(deps-dev): bump the build-tools group in /lightrag_webui with 3 updates by @dependabot[bot] in #2968
  • chore(deps): bump the frontend-minor-patch group across 1 directory with 3 updates by @dependabot[bot] in #2969
  • Fix role LLM max async fallback by @danielaskdd in #2973
  • fix(llm): tighten client and stream cleanup across LLM bindings by @danielaskdd in #2974
  • chore(deps): bump lucide-react from 0.577.0 to 1.6.0 in /lightrag_webui by @dependabot[bot] in #2970
  • docs: add role-specific LLM configuration guide by @danielaskdd in #2976
  • refactor: unify role LLM config via ROLES registry + queue observability by @danielaskdd in #2978
  • feat(status): role-based LLM observability and storage workspace info by @danielaskdd in #2980
  • feat(rerank): add independent concurrency and timeout configuration by @danielaskdd in #2981
  • Fix LLM cache role identity isolation by @danielaskdd in #2982
  • Add Podman-compatible compose file by @tears710 in #2983
  • Add role LLM provider options logging and change role provider options to start from empty not default by @danielaskdd in #2984
  • Fix bedrock/gemini host leak from env.example on make server/storage by @danielaskdd in #2985

New Contributors

Full Changelog: v1.4.15...v1.5.0rc1

Don't miss a new LightRAG release

NewReleases is sending notifications on new releases.