From fca6969b0b8918bee9d7601d5e9bf4f5a7b8c053 Mon Sep 17 00:00:00 2001 From: yangdx Date: Sun, 2 Mar 2025 18:33:18 +0800 Subject: [PATCH] Update Gunicorn startup instructions in API documentation --- lightrag/api/README.md | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/lightrag/api/README.md b/lightrag/api/README.md index 5ffbcdce..8f61f2f6 100644 --- a/lightrag/api/README.md +++ b/lightrag/api/README.md @@ -102,8 +102,11 @@ light-server --llm-binding ollama --embedding-binding ollama For production deployments, it's recommended to use Gunicorn as the WSGI server to handle concurrent requests efficiently. LightRAG provides a dedicated Gunicorn startup script that handles shared data initialization, process management, and other critical functionalities. ```bash -# Start with run_with_gunicorn.py -python run_with_gunicorn.py --workers 4 +# Start with lightrag-gunicorn command +lightrag-gunicorn --workers 4 + +# Alternatively, you can use the module directly +python -m lightrag.api.run_with_gunicorn --workers 4 ``` The `--workers` parameter is crucial for performance: