LightRAG · Issues· 247 open

[Feature Request]: per-call provider context — no supported way to attach request-scoped data to a query's LLM, embedding, or rerank calls

[Feature Request]: vector/source count reconciliation in kg_integrity_repair, repaired through rebuild_vdb

clear_documents leaves other embedding models' vector containers intact

LightRAG evaluation with reproduce gives me very different results with local LLMs

Vector storage: a model or dimension change must fail closed, and lightrag-rebuild-vdb must be able to recover on every backend

[Question]: Support specifying a custom .env file for lightrag-server (e.g. --env-file flag)

[Security] /health endpoint leaks LLM provider, model, and working directory on all instances (including auth-enabled)

RFC: Add C strategy for Server-injected custom chunking callbacks

_generate_collection_suffix folds distinct model names onto one container name

OpenSearch vector storage does not use the model-isolation suffix, so switching embedding models wedges the index

LightRAG Chat (微信交流群)

Google cloud platform ecosystem?

[Question]: TimeoutError: Embedding func: Worker execution timeout after 60s

[Bug]:LLM func: Worker execution timeout after 360s

RFC: cross-worker propagation for runtime configuration (`addon_params` and role LLM config)