Set default TIMEOUT value to 150, and gunicorn timeout to TIMEOUT+30

env.example

@@ -8,6 +8,8 @@ PORT=9621
 WEBUI_TITLE='My Graph KB'
 WEBUI_DESCRIPTION="Simple and Fast Graph Based RAG System"
 # WORKERS=2
+### gunicorn worker timeout(as default LLM request timeout if LLM_TIMEOUT is not set)
+# TIMEOUT=150
 # CORS_ORIGINS=http://localhost:3000,http://localhost:8080
 
 ### Optional SSL Configuration
@@ -151,8 +153,6 @@ LLM_BINDING_API_KEY=your_api_key
 ### lightrag-server --llm-binding openai --help
 
 ### Ollama Server Specific Parameters
-### Time out in seconds, None for infinite timeout
-TIMEOUT=240
 ### OLLAMA_LLM_NUM_CTX must be larger than MAX_TOTAL_TOKENS + 2000
 OLLAMA_LLM_NUM_CTX=32768
 ### Stop sequences for Ollama LLM

lightrag/api/README-zh.md

@@ -478,7 +478,7 @@ SUMMARY_LANGUAGE=Chinese
 MAX_PARALLEL_INSERT=2
 
 ### LLM Configuration (Use valid host. For local services installed with docker, you can use host.docker.internal)
-TIMEOUT=200
+TIMEOUT=150
 MAX_ASYNC=4
 
 LLM_BINDING=openai

lightrag/api/README.md

@@ -485,7 +485,7 @@ SUMMARY_LANGUAGE=Chinese
 MAX_PARALLEL_INSERT=2
 
 ### LLM Configuration (Use valid host. For local services installed with docker, you can use host.docker.internal)
-TIMEOUT=200
+TIMEOUT=150
 MAX_ASYNC=4
 
 LLM_BINDING=openai

lightrag/api/run_with_gunicorn.py

@@ -153,7 +153,7 @@ def main():
 
             # Timeout configuration prioritizes command line arguments
             gunicorn_config.timeout = (
-                global_args.timeout * 2
+                global_args.timeout + 30
                 if global_args.timeout is not None
                 else get_env_value(
                     "TIMEOUT", DEFAULT_TIMEOUT + 30, int, special_none=True

lightrag/constants.py

@@ -49,7 +49,7 @@ DEFAULT_MAX_PARALLEL_INSERT = 2  # Default maximum parallel insert operations
 DEFAULT_EMBEDDING_FUNC_MAX_ASYNC = 8  # Default max async for embedding functions
 DEFAULT_EMBEDDING_BATCH_NUM = 10  # Default batch size for embedding computations
 
-# Ollama Server Timetout in seconds
+# gunicorn worker timeout(as default LLM request timeout if LLM_TIMEOUT is not set)
 DEFAULT_TIMEOUT = 150
 
 # Logging configuration defaults