gardel/lightrag
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'optimize-config-management' into clear-doc

Browse Source
This commit is contained in:
yangdx
2025-04-04 19:46:45 +08:00
parent e86fda5894 787d91cb26
commit bd2c528dba
6 changed files with 369 additions and 341 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
env.example
View File

@@ -167,6 +167,8 @@ REDIS_URI=redis://localhost:6379
# AUTH_ACCOUNTS='admin:admin123,user1:pass456'
# TOKEN_SECRET=Your-Key-For-LightRAG-API-Server
# TOKEN_EXPIRE_HOURS=4
# GUEST_TOKEN_EXPIRE_HOURS=2
# JWT_ALGORITHM=HS256
### API-Key to access LightRAG Server API
# LIGHTRAG_API_KEY=your-secure-api-key-here

17
lightrag/api/auth.py
View File

@@ -1,9 +1,11 @@
import os
from datetime import datetime, timedelta
import jwt
from dotenv import load_dotenv
from fastapi import HTTPException, status
from pydantic import BaseModel
from dotenv import load_dotenv
from .config import global_args
# use the .env that is inside the current folder
# allows to use different .env file for each lightrag instance
@@ -20,13 +22,12 @@ class TokenPayload(BaseModel):
class AuthHandler:
def __init__(self):
self.secret = os.getenv("TOKEN_SECRET", "4f85ds4f56dsf46")
self.algorithm = "HS256"
self.expire_hours = int(os.getenv("TOKEN_EXPIRE_HOURS", 4))
self.guest_expire_hours = int(os.getenv("GUEST_TOKEN_EXPIRE_HOURS", 2))
self.secret = global_args.token_secret
self.algorithm = global_args.jwt_algorithm
self.expire_hours = global_args.token_expire_hours
self.guest_expire_hours = global_args.guest_token_expire_hours
self.accounts = {}
auth_accounts = os.getenv("AUTH_ACCOUNTS")
auth_accounts = global_args.auth_accounts
if auth_accounts:
for account in auth_accounts.split(","):
username, password = account.split(":", 1)

324
lightrag/api/config.py Normal file
View File

@@ -0,0 +1,324 @@
"""
Configs for the LightRAG API.
"""
import os
import argparse
import logging
class OllamaServerInfos:
# Constants for emulated Ollama model information
LIGHTRAG_NAME = "lightrag"
LIGHTRAG_TAG = os.getenv("OLLAMA_EMULATING_MODEL_TAG", "latest")
LIGHTRAG_MODEL = f"{LIGHTRAG_NAME}:{LIGHTRAG_TAG}"
LIGHTRAG_SIZE = 7365960935 # it's a dummy value
LIGHTRAG_CREATED_AT = "2024-01-15T00:00:00Z"
LIGHTRAG_DIGEST = "sha256:lightrag"
ollama_server_infos = OllamaServerInfos()
class DefaultRAGStorageConfig:
KV_STORAGE = "JsonKVStorage"
VECTOR_STORAGE = "NanoVectorDBStorage"
GRAPH_STORAGE = "NetworkXStorage"
DOC_STATUS_STORAGE = "JsonDocStatusStorage"
def get_default_host(binding_type: str) -> str:
default_hosts = {
"ollama": os.getenv("LLM_BINDING_HOST", "http://localhost:11434"),
"lollms": os.getenv("LLM_BINDING_HOST", "http://localhost:9600"),
"azure_openai": os.getenv("AZURE_OPENAI_ENDPOINT", "https://api.openai.com/v1"),
"openai": os.getenv("LLM_BINDING_HOST", "https://api.openai.com/v1"),
}
return default_hosts.get(
binding_type, os.getenv("LLM_BINDING_HOST", "http://localhost:11434")
) # fallback to ollama if unknown
def get_env_value(env_key: str, default: any, value_type: type = str) -> any:
"""
Get value from environment variable with type conversion
Args:
env_key (str): Environment variable key
default (any): Default value if env variable is not set
value_type (type): Type to convert the value to
Returns:
any: Converted value from environment or default
"""
value = os.getenv(env_key)
if value is None:
return default
if value_type is bool:
return value.lower() in ("true", "1", "yes", "t", "on")
try:
return value_type(value)
except ValueError:
return default
def parse_args() -> argparse.Namespace:
"""
Parse command line arguments with environment variable fallback
Args:
is_uvicorn_mode: Whether running under uvicorn mode
Returns:
argparse.Namespace: Parsed arguments
"""
parser = argparse.ArgumentParser(
description="LightRAG FastAPI Server with separate working and input directories"
)
# Server configuration
parser.add_argument(
"--host",
default=get_env_value("HOST", "0.0.0.0"),
help="Server host (default: from env or 0.0.0.0)",
)
parser.add_argument(
"--port",
type=int,
default=get_env_value("PORT", 9621, int),
help="Server port (default: from env or 9621)",
)
# Directory configuration
parser.add_argument(
"--working-dir",
default=get_env_value("WORKING_DIR", "./rag_storage"),
help="Working directory for RAG storage (default: from env or ./rag_storage)",
)
parser.add_argument(
"--input-dir",
default=get_env_value("INPUT_DIR", "./inputs"),
help="Directory containing input documents (default: from env or ./inputs)",
)
def timeout_type(value):
if value is None:
return 150
if value is None or value == "None":
return None
return int(value)
parser.add_argument(
"--timeout",
default=get_env_value("TIMEOUT", None, timeout_type),
type=timeout_type,
help="Timeout in seconds (useful when using slow AI). Use None for infinite timeout",
)
# RAG configuration
parser.add_argument(
"--max-async",
type=int,
default=get_env_value("MAX_ASYNC", 4, int),
help="Maximum async operations (default: from env or 4)",
)
parser.add_argument(
"--max-tokens",
type=int,
default=get_env_value("MAX_TOKENS", 32768, int),
help="Maximum token size (default: from env or 32768)",
)
# Logging configuration
parser.add_argument(
"--log-level",
default=get_env_value("LOG_LEVEL", "INFO"),
choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
help="Logging level (default: from env or INFO)",
)
parser.add_argument(
"--verbose",
action="store_true",
default=get_env_value("VERBOSE", False, bool),
help="Enable verbose debug output(only valid for DEBUG log-level)",
)
parser.add_argument(
"--key",
type=str,
default=get_env_value("LIGHTRAG_API_KEY", None),
help="API key for authentication. This protects lightrag server against unauthorized access",
)
# Optional https parameters
parser.add_argument(
"--ssl",
action="store_true",
default=get_env_value("SSL", False, bool),
help="Enable HTTPS (default: from env or False)",
)
parser.add_argument(
"--ssl-certfile",
default=get_env_value("SSL_CERTFILE", None),
help="Path to SSL certificate file (required if --ssl is enabled)",
)
parser.add_argument(
"--ssl-keyfile",
default=get_env_value("SSL_KEYFILE", None),
help="Path to SSL private key file (required if --ssl is enabled)",
)
parser.add_argument(
"--history-turns",
type=int,
default=get_env_value("HISTORY_TURNS", 3, int),
help="Number of conversation history turns to include (default: from env or 3)",
)
# Search parameters
parser.add_argument(
"--top-k",
type=int,
default=get_env_value("TOP_K", 60, int),
help="Number of most similar results to return (default: from env or 60)",
)
parser.add_argument(
"--cosine-threshold",
type=float,
default=get_env_value("COSINE_THRESHOLD", 0.2, float),
help="Cosine similarity threshold (default: from env or 0.4)",
)
# Ollama model name
parser.add_argument(
"--simulated-model-name",
type=str,
default=get_env_value(
"SIMULATED_MODEL_NAME", ollama_server_infos.LIGHTRAG_MODEL
),
help="Number of conversation history turns to include (default: from env or 3)",
)
# Namespace
parser.add_argument(
"--namespace-prefix",
type=str,
default=get_env_value("NAMESPACE_PREFIX", ""),
help="Prefix of the namespace",
)
parser.add_argument(
"--auto-scan-at-startup",
action="store_true",
default=False,
help="Enable automatic scanning when the program starts",
)
# Server workers configuration
parser.add_argument(
"--workers",
type=int,
default=get_env_value("WORKERS", 1, int),
help="Number of worker processes (default: from env or 1)",
)
# LLM and embedding bindings
parser.add_argument(
"--llm-binding",
type=str,
default=get_env_value("LLM_BINDING", "ollama"),
choices=["lollms", "ollama", "openai", "openai-ollama", "azure_openai"],
help="LLM binding type (default: from env or ollama)",
)
parser.add_argument(
"--embedding-binding",
type=str,
default=get_env_value("EMBEDDING_BINDING", "ollama"),
choices=["lollms", "ollama", "openai", "azure_openai"],
help="Embedding binding type (default: from env or ollama)",
)
args = parser.parse_args()
# convert relative path to absolute path
args.working_dir = os.path.abspath(args.working_dir)
args.input_dir = os.path.abspath(args.input_dir)
# Inject storage configuration from environment variables
args.kv_storage = get_env_value(
"LIGHTRAG_KV_STORAGE", DefaultRAGStorageConfig.KV_STORAGE
)
args.doc_status_storage = get_env_value(
"LIGHTRAG_DOC_STATUS_STORAGE", DefaultRAGStorageConfig.DOC_STATUS_STORAGE
)
args.graph_storage = get_env_value(
"LIGHTRAG_GRAPH_STORAGE", DefaultRAGStorageConfig.GRAPH_STORAGE
)
args.vector_storage = get_env_value(
"LIGHTRAG_VECTOR_STORAGE", DefaultRAGStorageConfig.VECTOR_STORAGE
)
# Get MAX_PARALLEL_INSERT from environment
args.max_parallel_insert = get_env_value("MAX_PARALLEL_INSERT", 2, int)
# Handle openai-ollama special case
if args.llm_binding == "openai-ollama":
args.llm_binding = "openai"
args.embedding_binding = "ollama"
args.llm_binding_host = get_env_value(
"LLM_BINDING_HOST", get_default_host(args.llm_binding)
)
args.embedding_binding_host = get_env_value(
"EMBEDDING_BINDING_HOST", get_default_host(args.embedding_binding)
)
args.llm_binding_api_key = get_env_value("LLM_BINDING_API_KEY", None)
args.embedding_binding_api_key = get_env_value("EMBEDDING_BINDING_API_KEY", "")
# Inject model configuration
args.llm_model = get_env_value("LLM_MODEL", "mistral-nemo:latest")
args.embedding_model = get_env_value("EMBEDDING_MODEL", "bge-m3:latest")
args.embedding_dim = get_env_value("EMBEDDING_DIM", 1024, int)
args.max_embed_tokens = get_env_value("MAX_EMBED_TOKENS", 8192, int)
# Inject chunk configuration
args.chunk_size = get_env_value("CHUNK_SIZE", 1200, int)
args.chunk_overlap_size = get_env_value("CHUNK_OVERLAP_SIZE", 100, int)
# Inject LLM cache configuration
args.enable_llm_cache_for_extract = get_env_value(
"ENABLE_LLM_CACHE_FOR_EXTRACT", True, bool
)
# Inject LLM temperature configuration
args.temperature = get_env_value("TEMPERATURE", 0.5, float)
# Select Document loading tool (DOCLING, DEFAULT)
args.document_loading_engine = get_env_value("DOCUMENT_LOADING_ENGINE", "DEFAULT")
# For JWT Auth
args.auth_accounts = get_env_value("AUTH_ACCOUNTS", "")
args.token_secret = get_env_value("TOKEN_SECRET", "lightrag-jwt-default-secret")
args.token_expire_hours = get_env_value("TOKEN_EXPIRE_HOURS", 4, int)
args.guest_token_expire_hours = get_env_value("GUEST_TOKEN_EXPIRE_HOURS", 2, int)
args.jwt_algorithm = get_env_value("JWT_ALGORITHM", "HS256")
ollama_server_infos.LIGHTRAG_MODEL = args.simulated_model_name
return args
def update_uvicorn_mode_config():
# If in uvicorn mode and workers > 1, force it to 1 and log warning
if global_args.workers > 1:
original_workers = global_args.workers
global_args.workers = 1
# Log warning directly here
logging.warning(
f"In uvicorn mode, workers parameter was set to {original_workers}. Forcing workers=1"
)
global_args = parse_args()

30
lightrag/api/lightrag_server.py
View File

@@ -19,11 +19,14 @@ from contextlib import asynccontextmanager
from dotenv import load_dotenv
from lightrag.api.utils_api import (
get_combined_auth_dependency,
parse_args,
get_default_host,
display_splash_screen,
check_env_file,
)
from .config import (
global_args,
update_uvicorn_mode_config,
get_default_host,
)
import sys
from lightrag import LightRAG, __version__ as core_version
from lightrag.api import __api_version__
@@ -490,7 +493,7 @@ def create_app(args):
def get_application(args=None):
"""Factory function for creating the FastAPI application"""
if args is None:
args = parse_args()
args = global_args
return create_app(args)
@@ -611,30 +614,31 @@ def main():
# Configure logging before parsing args
configure_logging()
args = parse_args(is_uvicorn_mode=True)
display_splash_screen(args)
update_uvicorn_mode_config()
display_splash_screen(global_args)
# Create application instance directly instead of using factory function
app = create_app(args)
app = create_app(global_args)
# Start Uvicorn in single process mode
uvicorn_config = {
"app": app, # Pass application instance directly instead of string path
"host": args.host,
"port": args.port,
"host": global_args.host,
"port": global_args.port,
"log_config": None, # Disable default config
}
if args.ssl:
if global_args.ssl:
uvicorn_config.update(
{
"ssl_certfile": args.ssl_certfile,
"ssl_keyfile": args.ssl_keyfile,
"ssl_certfile": global_args.ssl_certfile,
"ssl_keyfile": global_args.ssl_keyfile,
}
)
print(f"Starting Uvicorn server in single-process mode on {args.host}:{args.port}")
print(
f"Starting Uvicorn server in single-process mode on {global_args.host}:{global_args.port}"
)
uvicorn.run(**uvicorn_config)

18
lightrag/api/routers/document_routes.py
View File

@@ -16,10 +16,8 @@ from pydantic import BaseModel, Field, field_validator
from lightrag import LightRAG
from lightrag.base import DocProcessingStatus, DocStatus
from lightrag.api.utils_api import (
get_combined_auth_dependency,
global_args,
)
from lightrag.api.utils_api import get_combined_auth_dependency
from ..config import global_args
router = APIRouter(
prefix="/documents",
@@ -472,7 +470,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
)
return False
case ".pdf":
if global_args["main_args"].document_loading_engine == "DOCLING":
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
@@ -491,7 +489,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
for page in reader.pages:
content += page.extract_text() + "\n"
case ".docx":
if global_args["main_args"].document_loading_engine == "DOCLING":
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
@@ -511,7 +509,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
[paragraph.text for paragraph in doc.paragraphs]
)
case ".pptx":
if global_args["main_args"].document_loading_engine == "DOCLING":
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
@@ -532,7 +530,7 @@ async def pipeline_enqueue_file(rag: LightRAG, file_path: Path) -> bool:
if hasattr(shape, "text"):
content += shape.text + "\n"
case ".xlsx":
if global_args["main_args"].document_loading_engine == "DOCLING":
if global_args.document_loading_engine == "DOCLING":
if not pm.is_installed("docling"): # type: ignore
pm.install("docling")
from docling.document_converter import DocumentConverter # type: ignore
@@ -673,8 +671,8 @@ async def run_scanning_process(rag: LightRAG, doc_manager: DocumentManager):
if not new_files:
return
# Get MAX_PARALLEL_INSERT from global_args["main_args"]
max_parallel = global_args["main_args"].max_parallel_insert
# Get MAX_PARALLEL_INSERT from global_args
max_parallel = global_args.max_parallel_insert
# Calculate batch size as 2 * MAX_PARALLEL_INSERT
batch_size = 2 * max_parallel

319
lightrag/api/utils_api.py
View File

@@ -7,7 +7,6 @@ import argparse
from typing import Optional, List, Tuple
import sys
from ascii_colors import ASCIIColors
import logging
from lightrag.api import __api_version__ as api_version
from lightrag import __version__ as core_version
from fastapi import HTTPException, Security, Request, status
@@ -15,6 +14,7 @@ from dotenv import load_dotenv
from fastapi.security import APIKeyHeader, OAuth2PasswordBearer
from starlette.status import HTTP_403_FORBIDDEN
from .auth import auth_handler
from .config import ollama_server_infos
from ..prompt import PROMPTS
@@ -41,8 +41,6 @@ def check_env_file():
# the OS environment variables take precedence over the .env file
load_dotenv(dotenv_path=".env", override=False)
global_args = {"main_args": None}
# Get whitelist paths from environment variable, only once during initialization
default_whitelist = "/health,/api/*"
whitelist_paths = os.getenv("WHITELIST_PATHS", default_whitelist).split(",")
@@ -63,19 +61,6 @@ for path in whitelist_paths:
auth_configured = bool(auth_handler.accounts)
class OllamaServerInfos:
# Constants for emulated Ollama model information
LIGHTRAG_NAME = "lightrag"
LIGHTRAG_TAG = os.getenv("OLLAMA_EMULATING_MODEL_TAG", "latest")
LIGHTRAG_MODEL = f"{LIGHTRAG_NAME}:{LIGHTRAG_TAG}"
LIGHTRAG_SIZE = 7365960935 # it's a dummy value
LIGHTRAG_CREATED_AT = "2024-01-15T00:00:00Z"
LIGHTRAG_DIGEST = "sha256:lightrag"
ollama_server_infos = OllamaServerInfos()
def get_combined_auth_dependency(api_key: Optional[str] = None):
"""
Create a combined authentication dependency that implements authentication logic
@@ -186,299 +171,6 @@ def get_combined_auth_dependency(api_key: Optional[str] = None):
return combined_dependency
class DefaultRAGStorageConfig:
KV_STORAGE = "JsonKVStorage"
VECTOR_STORAGE = "NanoVectorDBStorage"
GRAPH_STORAGE = "NetworkXStorage"
DOC_STATUS_STORAGE = "JsonDocStatusStorage"
def get_default_host(binding_type: str) -> str:
default_hosts = {
"ollama": os.getenv("LLM_BINDING_HOST", "http://localhost:11434"),
"lollms": os.getenv("LLM_BINDING_HOST", "http://localhost:9600"),
"azure_openai": os.getenv("AZURE_OPENAI_ENDPOINT", "https://api.openai.com/v1"),
"openai": os.getenv("LLM_BINDING_HOST", "https://api.openai.com/v1"),
}
return default_hosts.get(
binding_type, os.getenv("LLM_BINDING_HOST", "http://localhost:11434")
) # fallback to ollama if unknown
def get_env_value(env_key: str, default: any, value_type: type = str) -> any:
"""
Get value from environment variable with type conversion
Args:
env_key (str): Environment variable key
default (any): Default value if env variable is not set
value_type (type): Type to convert the value to
Returns:
any: Converted value from environment or default
"""
value = os.getenv(env_key)
if value is None:
return default
if value_type is bool:
return value.lower() in ("true", "1", "yes", "t", "on")
try:
return value_type(value)
except ValueError:
return default
def parse_args(is_uvicorn_mode: bool = False) -> argparse.Namespace:
"""
Parse command line arguments with environment variable fallback
Args:
is_uvicorn_mode: Whether running under uvicorn mode
Returns:
argparse.Namespace: Parsed arguments
"""
parser = argparse.ArgumentParser(
description="LightRAG FastAPI Server with separate working and input directories"
)
# Server configuration
parser.add_argument(
"--host",
default=get_env_value("HOST", "0.0.0.0"),
help="Server host (default: from env or 0.0.0.0)",
)
parser.add_argument(
"--port",
type=int,
default=get_env_value("PORT", 9621, int),
help="Server port (default: from env or 9621)",
)
# Directory configuration
parser.add_argument(
"--working-dir",
default=get_env_value("WORKING_DIR", "./rag_storage"),
help="Working directory for RAG storage (default: from env or ./rag_storage)",
)
parser.add_argument(
"--input-dir",
default=get_env_value("INPUT_DIR", "./inputs"),
help="Directory containing input documents (default: from env or ./inputs)",
)
def timeout_type(value):
if value is None:
return 150
if value is None or value == "None":
return None
return int(value)
parser.add_argument(
"--timeout",
default=get_env_value("TIMEOUT", None, timeout_type),
type=timeout_type,
help="Timeout in seconds (useful when using slow AI). Use None for infinite timeout",
)
# RAG configuration
parser.add_argument(
"--max-async",
type=int,
default=get_env_value("MAX_ASYNC", 4, int),
help="Maximum async operations (default: from env or 4)",
)
parser.add_argument(
"--max-tokens",
type=int,
default=get_env_value("MAX_TOKENS", 32768, int),
help="Maximum token size (default: from env or 32768)",
)
# Logging configuration
parser.add_argument(
"--log-level",
default=get_env_value("LOG_LEVEL", "INFO"),
choices=["DEBUG", "INFO", "WARNING", "ERROR", "CRITICAL"],
help="Logging level (default: from env or INFO)",
)
parser.add_argument(
"--verbose",
action="store_true",
default=get_env_value("VERBOSE", False, bool),
help="Enable verbose debug output(only valid for DEBUG log-level)",
)
parser.add_argument(
"--key",
type=str,
default=get_env_value("LIGHTRAG_API_KEY", None),
help="API key for authentication. This protects lightrag server against unauthorized access",
)
# Optional https parameters
parser.add_argument(
"--ssl",
action="store_true",
default=get_env_value("SSL", False, bool),
help="Enable HTTPS (default: from env or False)",
)
parser.add_argument(
"--ssl-certfile",
default=get_env_value("SSL_CERTFILE", None),
help="Path to SSL certificate file (required if --ssl is enabled)",
)
parser.add_argument(
"--ssl-keyfile",
default=get_env_value("SSL_KEYFILE", None),
help="Path to SSL private key file (required if --ssl is enabled)",
)
parser.add_argument(
"--history-turns",
type=int,
default=get_env_value("HISTORY_TURNS", 3, int),
help="Number of conversation history turns to include (default: from env or 3)",
)
# Search parameters
parser.add_argument(
"--top-k",
type=int,
default=get_env_value("TOP_K", 60, int),
help="Number of most similar results to return (default: from env or 60)",
)
parser.add_argument(
"--cosine-threshold",
type=float,
default=get_env_value("COSINE_THRESHOLD", 0.2, float),
help="Cosine similarity threshold (default: from env or 0.4)",
)
# Ollama model name
parser.add_argument(
"--simulated-model-name",
type=str,
default=get_env_value(
"SIMULATED_MODEL_NAME", ollama_server_infos.LIGHTRAG_MODEL
),
help="Number of conversation history turns to include (default: from env or 3)",
)
# Namespace
parser.add_argument(
"--namespace-prefix",
type=str,
default=get_env_value("NAMESPACE_PREFIX", ""),
help="Prefix of the namespace",
)
parser.add_argument(
"--auto-scan-at-startup",
action="store_true",
default=False,
help="Enable automatic scanning when the program starts",
)
# Server workers configuration
parser.add_argument(
"--workers",
type=int,
default=get_env_value("WORKERS", 1, int),
help="Number of worker processes (default: from env or 1)",
)
# LLM and embedding bindings
parser.add_argument(
"--llm-binding",
type=str,
default=get_env_value("LLM_BINDING", "ollama"),
choices=["lollms", "ollama", "openai", "openai-ollama", "azure_openai"],
help="LLM binding type (default: from env or ollama)",
)
parser.add_argument(
"--embedding-binding",
type=str,
default=get_env_value("EMBEDDING_BINDING", "ollama"),
choices=["lollms", "ollama", "openai", "azure_openai"],
help="Embedding binding type (default: from env or ollama)",
)
args = parser.parse_args()
# If in uvicorn mode and workers > 1, force it to 1 and log warning
if is_uvicorn_mode and args.workers > 1:
original_workers = args.workers
args.workers = 1
# Log warning directly here
logging.warning(
f"In uvicorn mode, workers parameter was set to {original_workers}. Forcing workers=1"
)
# convert relative path to absolute path
args.working_dir = os.path.abspath(args.working_dir)
args.input_dir = os.path.abspath(args.input_dir)
# Inject storage configuration from environment variables
args.kv_storage = get_env_value(
"LIGHTRAG_KV_STORAGE", DefaultRAGStorageConfig.KV_STORAGE
)
args.doc_status_storage = get_env_value(
"LIGHTRAG_DOC_STATUS_STORAGE", DefaultRAGStorageConfig.DOC_STATUS_STORAGE
)
args.graph_storage = get_env_value(
"LIGHTRAG_GRAPH_STORAGE", DefaultRAGStorageConfig.GRAPH_STORAGE
)
args.vector_storage = get_env_value(
"LIGHTRAG_VECTOR_STORAGE", DefaultRAGStorageConfig.VECTOR_STORAGE
)
# Get MAX_PARALLEL_INSERT from environment
args.max_parallel_insert = get_env_value("MAX_PARALLEL_INSERT", 2, int)
# Handle openai-ollama special case
if args.llm_binding == "openai-ollama":
args.llm_binding = "openai"
args.embedding_binding = "ollama"
args.llm_binding_host = get_env_value(
"LLM_BINDING_HOST", get_default_host(args.llm_binding)
)
args.embedding_binding_host = get_env_value(
"EMBEDDING_BINDING_HOST", get_default_host(args.embedding_binding)
)
args.llm_binding_api_key = get_env_value("LLM_BINDING_API_KEY", None)
args.embedding_binding_api_key = get_env_value("EMBEDDING_BINDING_API_KEY", "")
# Inject model configuration
args.llm_model = get_env_value("LLM_MODEL", "mistral-nemo:latest")
args.embedding_model = get_env_value("EMBEDDING_MODEL", "bge-m3:latest")
args.embedding_dim = get_env_value("EMBEDDING_DIM", 1024, int)
args.max_embed_tokens = get_env_value("MAX_EMBED_TOKENS", 8192, int)
# Inject chunk configuration
args.chunk_size = get_env_value("CHUNK_SIZE", 1200, int)
args.chunk_overlap_size = get_env_value("CHUNK_OVERLAP_SIZE", 100, int)
# Inject LLM cache configuration
args.enable_llm_cache_for_extract = get_env_value(
"ENABLE_LLM_CACHE_FOR_EXTRACT", True, bool
)
# Inject LLM temperature configuration
args.temperature = get_env_value("TEMPERATURE", 0.5, float)
# Select Document loading tool (DOCLING, DEFAULT)
args.document_loading_engine = get_env_value("DOCUMENT_LOADING_ENGINE", "DEFAULT")
ollama_server_infos.LIGHTRAG_MODEL = args.simulated_model_name
global_args["main_args"] = args
return args
def display_splash_screen(args: argparse.Namespace) -> None:
"""
Display a colorful splash screen showing LightRAG server configuration
@@ -519,8 +211,10 @@ def display_splash_screen(args: argparse.Namespace) -> None:
ASCIIColors.yellow(f"{args.verbose}")
ASCIIColors.white(" ├─ History Turns: ", end="")
ASCIIColors.yellow(f"{args.history_turns}")
ASCIIColors.white(" └─ API Key: ", end="")
ASCIIColors.white(" ├─ API Key: ", end="")
ASCIIColors.yellow("Set" if args.key else "Not Set")
ASCIIColors.white(" └─ JWT Auth: ", end="")
ASCIIColors.yellow("Enabled" if args.auth_accounts else "Disabled")
# Directory Configuration
ASCIIColors.magenta("\n📂 Directory Configuration:")
@@ -628,6 +322,11 @@ def display_splash_screen(args: argparse.Namespace) -> None:
ASCIIColors.white(""" API Key authentication is enabled.
Make sure to include the X-API-Key header in all your requests.
""")
if args.auth_accounts:
ASCIIColors.yellow("\n⚠️ Security Notice:")
ASCIIColors.white(""" JWT authentication is enabled.
Make sure to login before making the request, and include the 'Authorization' in the header.
""")
# Ensure splash output flush to system log
sys.stdout.flush()