refactor: centralize configuration and utility functions
- Move parse_args and display_splash_screen functions from lightrag_server.py to utils_api.py - Move OllamaServerInfos class and instance from ollama_api.py to utils_api.py
This commit is contained in:
yangdx
@@ -12,17 +12,20 @@ import threading
|
|||||||
import os
|
import os
|
||||||
from fastapi.staticfiles import StaticFiles
|
from fastapi.staticfiles import StaticFiles
|
||||||
import logging
|
import logging
|
||||||
import argparse
|
|
||||||
from typing import Dict
|
from typing import Dict
|
||||||
from pathlib import Path
|
from pathlib import Path
|
||||||
import configparser
|
import configparser
|
||||||
from ascii_colors import ASCIIColors
|
from ascii_colors import ASCIIColors
|
||||||
import sys
|
|
||||||
from fastapi.middleware.cors import CORSMiddleware
|
from fastapi.middleware.cors import CORSMiddleware
|
||||||
from contextlib import asynccontextmanager
|
from contextlib import asynccontextmanager
|
||||||
from dotenv import load_dotenv
|
from dotenv import load_dotenv
|
||||||
|
|
||||||
from .utils_api import get_api_key_dependency
|
from .utils_api import (
|
||||||
|
get_api_key_dependency,
|
||||||
|
parse_args,
|
||||||
|
get_default_host,
|
||||||
|
display_splash_screen,
|
||||||
|
)
|
||||||
|
|
||||||
from lightrag import LightRAG
|
from lightrag import LightRAG
|
||||||
from lightrag.types import GPTKeywordExtractionFormat
|
from lightrag.types import GPTKeywordExtractionFormat
|
||||||
@@ -37,7 +40,7 @@ from .routers.document_routes import (
|
|||||||
)
|
)
|
||||||
from .routers.query_routes import create_query_routes
|
from .routers.query_routes import create_query_routes
|
||||||
from .routers.graph_routes import create_graph_routes
|
from .routers.graph_routes import create_graph_routes
|
||||||
from .routers.ollama_api import OllamaAPI, ollama_server_infos
|
from .routers.ollama_api import OllamaAPI
|
||||||
|
|
||||||
# Load environment variables
|
# Load environment variables
|
||||||
try:
|
try:
|
||||||
@@ -52,14 +55,6 @@ config.read("config.ini")
|
|||||||
# Global configuration
|
# Global configuration
|
||||||
global_top_k = 60 # default value
|
global_top_k = 60 # default value
|
||||||
|
|
||||||
|
|
||||||
class DefaultRAGStorageConfig:
|
|
||||||
KV_STORAGE = "JsonKVStorage"
|
|
||||||
VECTOR_STORAGE = "NanoVectorDBStorage"
|
|
||||||
GRAPH_STORAGE = "NetworkXStorage"
|
|
||||||
DOC_STATUS_STORAGE = "JsonDocStatusStorage"
|
|
||||||
|
|
||||||
|
|
||||||
# Global progress tracker
|
# Global progress tracker
|
||||||
scan_progress: Dict = {
|
scan_progress: Dict = {
|
||||||
"is_scanning": False,
|
"is_scanning": False,
|
||||||
@@ -73,486 +68,6 @@ scan_progress: Dict = {
|
|||||||
progress_lock = threading.Lock()
|
progress_lock = threading.Lock()
|
||||||
|
|
||||||
|
|
||||||
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 display_splash_screen(args: argparse.Namespace) -> None:
|
|
||||||
"""
|
|
||||||
Display a colorful splash screen showing LightRAG server configuration
|
|
||||||
|
|
||||||
Args:
|
|
||||||
args: Parsed command line arguments
|
|
||||||
"""
|
|
||||||
# Banner
|
|
||||||
ASCIIColors.cyan(f"""
|
|
||||||
╔══════════════════════════════════════════════════════════════╗
|
|
||||||
║ 🚀 LightRAG Server v{__api_version__} ║
|
|
||||||
║ Fast, Lightweight RAG Server Implementation ║
|
|
||||||
╚══════════════════════════════════════════════════════════════╝
|
|
||||||
""")
|
|
||||||
|
|
||||||
# Server Configuration
|
|
||||||
ASCIIColors.magenta("\n📡 Server Configuration:")
|
|
||||||
ASCIIColors.white(" ├─ Host: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.host}")
|
|
||||||
ASCIIColors.white(" ├─ Port: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.port}")
|
|
||||||
ASCIIColors.white(" ├─ CORS Origins: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{os.getenv('CORS_ORIGINS', '*')}")
|
|
||||||
ASCIIColors.white(" ├─ SSL Enabled: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.ssl}")
|
|
||||||
ASCIIColors.white(" └─ API Key: ", end="")
|
|
||||||
ASCIIColors.yellow("Set" if args.key else "Not Set")
|
|
||||||
if args.ssl:
|
|
||||||
ASCIIColors.white(" ├─ SSL Cert: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.ssl_certfile}")
|
|
||||||
ASCIIColors.white(" └─ SSL Key: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.ssl_keyfile}")
|
|
||||||
|
|
||||||
# Directory Configuration
|
|
||||||
ASCIIColors.magenta("\n📂 Directory Configuration:")
|
|
||||||
ASCIIColors.white(" ├─ Working Directory: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.working_dir}")
|
|
||||||
ASCIIColors.white(" └─ Input Directory: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.input_dir}")
|
|
||||||
|
|
||||||
# LLM Configuration
|
|
||||||
ASCIIColors.magenta("\n🤖 LLM Configuration:")
|
|
||||||
ASCIIColors.white(" ├─ Binding: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.llm_binding}")
|
|
||||||
ASCIIColors.white(" ├─ Host: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.llm_binding_host}")
|
|
||||||
ASCIIColors.white(" └─ Model: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.llm_model}")
|
|
||||||
|
|
||||||
# Embedding Configuration
|
|
||||||
ASCIIColors.magenta("\n📊 Embedding Configuration:")
|
|
||||||
ASCIIColors.white(" ├─ Binding: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.embedding_binding}")
|
|
||||||
ASCIIColors.white(" ├─ Host: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.embedding_binding_host}")
|
|
||||||
ASCIIColors.white(" ├─ Model: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.embedding_model}")
|
|
||||||
ASCIIColors.white(" └─ Dimensions: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.embedding_dim}")
|
|
||||||
|
|
||||||
# RAG Configuration
|
|
||||||
ASCIIColors.magenta("\n⚙️ RAG Configuration:")
|
|
||||||
ASCIIColors.white(" ├─ Max Async Operations: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.max_async}")
|
|
||||||
ASCIIColors.white(" ├─ Max Tokens: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.max_tokens}")
|
|
||||||
ASCIIColors.white(" ├─ Max Embed Tokens: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.max_embed_tokens}")
|
|
||||||
ASCIIColors.white(" ├─ Chunk Size: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.chunk_size}")
|
|
||||||
ASCIIColors.white(" ├─ Chunk Overlap Size: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.chunk_overlap_size}")
|
|
||||||
ASCIIColors.white(" ├─ History Turns: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.history_turns}")
|
|
||||||
ASCIIColors.white(" ├─ Cosine Threshold: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.cosine_threshold}")
|
|
||||||
ASCIIColors.white(" └─ Top-K: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.top_k}")
|
|
||||||
|
|
||||||
# System Configuration
|
|
||||||
ASCIIColors.magenta("\n💾 Storage Configuration:")
|
|
||||||
ASCIIColors.white(" ├─ KV Storage: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.kv_storage}")
|
|
||||||
ASCIIColors.white(" ├─ Vector Storage: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.vector_storage}")
|
|
||||||
ASCIIColors.white(" ├─ Graph Storage: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.graph_storage}")
|
|
||||||
ASCIIColors.white(" └─ Document Status Storage: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.doc_status_storage}")
|
|
||||||
|
|
||||||
ASCIIColors.magenta("\n🛠️ System Configuration:")
|
|
||||||
ASCIIColors.white(" ├─ Ollama Emulating Model: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{ollama_server_infos.LIGHTRAG_MODEL}")
|
|
||||||
ASCIIColors.white(" ├─ Log Level: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.log_level}")
|
|
||||||
ASCIIColors.white(" ├─ Verbose Debug: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.verbose}")
|
|
||||||
ASCIIColors.white(" └─ Timeout: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{args.timeout if args.timeout else 'None (infinite)'}")
|
|
||||||
|
|
||||||
# Server Status
|
|
||||||
ASCIIColors.green("\n✨ Server starting up...\n")
|
|
||||||
|
|
||||||
# Server Access Information
|
|
||||||
protocol = "https" if args.ssl else "http"
|
|
||||||
if args.host == "0.0.0.0":
|
|
||||||
ASCIIColors.magenta("\n🌐 Server Access Information:")
|
|
||||||
ASCIIColors.white(" ├─ Local Access: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}")
|
|
||||||
ASCIIColors.white(" ├─ Remote Access: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{protocol}://<your-ip-address>:{args.port}")
|
|
||||||
ASCIIColors.white(" ├─ API Documentation (local): ", end="")
|
|
||||||
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/docs")
|
|
||||||
ASCIIColors.white(" ├─ Alternative Documentation (local): ", end="")
|
|
||||||
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/redoc")
|
|
||||||
ASCIIColors.white(" └─ WebUI (local): ", end="")
|
|
||||||
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/webui")
|
|
||||||
|
|
||||||
ASCIIColors.yellow("\n📝 Note:")
|
|
||||||
ASCIIColors.white(""" Since the server is running on 0.0.0.0:
|
|
||||||
- Use 'localhost' or '127.0.0.1' for local access
|
|
||||||
- Use your machine's IP address for remote access
|
|
||||||
- To find your IP address:
|
|
||||||
• Windows: Run 'ipconfig' in terminal
|
|
||||||
• Linux/Mac: Run 'ifconfig' or 'ip addr' in terminal
|
|
||||||
""")
|
|
||||||
else:
|
|
||||||
base_url = f"{protocol}://{args.host}:{args.port}"
|
|
||||||
ASCIIColors.magenta("\n🌐 Server Access Information:")
|
|
||||||
ASCIIColors.white(" ├─ Base URL: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{base_url}")
|
|
||||||
ASCIIColors.white(" ├─ API Documentation: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{base_url}/docs")
|
|
||||||
ASCIIColors.white(" └─ Alternative Documentation: ", end="")
|
|
||||||
ASCIIColors.yellow(f"{base_url}/redoc")
|
|
||||||
|
|
||||||
# Usage Examples
|
|
||||||
ASCIIColors.magenta("\n📚 Quick Start Guide:")
|
|
||||||
ASCIIColors.cyan("""
|
|
||||||
1. Access the Swagger UI:
|
|
||||||
Open your browser and navigate to the API documentation URL above
|
|
||||||
|
|
||||||
2. API Authentication:""")
|
|
||||||
if args.key:
|
|
||||||
ASCIIColors.cyan(""" Add the following header to your requests:
|
|
||||||
X-API-Key: <your-api-key>
|
|
||||||
""")
|
|
||||||
else:
|
|
||||||
ASCIIColors.cyan(" No authentication required\n")
|
|
||||||
|
|
||||||
ASCIIColors.cyan(""" 3. Basic Operations:
|
|
||||||
- POST /upload_document: Upload new documents to RAG
|
|
||||||
- POST /query: Query your document collection
|
|
||||||
- GET /collections: List available collections
|
|
||||||
|
|
||||||
4. Monitor the server:
|
|
||||||
- Check server logs for detailed operation information
|
|
||||||
- Use healthcheck endpoint: GET /health
|
|
||||||
""")
|
|
||||||
|
|
||||||
# Security Notice
|
|
||||||
if args.key:
|
|
||||||
ASCIIColors.yellow("\n⚠️ Security Notice:")
|
|
||||||
ASCIIColors.white(""" API Key authentication is enabled.
|
|
||||||
Make sure to include the X-API-Key header in all your requests.
|
|
||||||
""")
|
|
||||||
|
|
||||||
ASCIIColors.green("Server is ready to accept connections! 🚀\n")
|
|
||||||
|
|
||||||
# Ensure splash output flush to system log
|
|
||||||
sys.stdout.flush()
|
|
||||||
|
|
||||||
|
|
||||||
def parse_args() -> argparse.Namespace:
|
|
||||||
"""
|
|
||||||
Parse command line arguments with environment variable fallback
|
|
||||||
|
|
||||||
Returns:
|
|
||||||
argparse.Namespace: Parsed arguments
|
|
||||||
"""
|
|
||||||
|
|
||||||
parser = argparse.ArgumentParser(
|
|
||||||
description="LightRAG FastAPI Server with separate working and input directories"
|
|
||||||
)
|
|
||||||
|
|
||||||
parser.add_argument(
|
|
||||||
"--kv-storage",
|
|
||||||
default=get_env_value(
|
|
||||||
"LIGHTRAG_KV_STORAGE", DefaultRAGStorageConfig.KV_STORAGE
|
|
||||||
),
|
|
||||||
help=f"KV storage implementation (default: {DefaultRAGStorageConfig.KV_STORAGE})",
|
|
||||||
)
|
|
||||||
parser.add_argument(
|
|
||||||
"--doc-status-storage",
|
|
||||||
default=get_env_value(
|
|
||||||
"LIGHTRAG_DOC_STATUS_STORAGE", DefaultRAGStorageConfig.DOC_STATUS_STORAGE
|
|
||||||
),
|
|
||||||
help=f"Document status storage implementation (default: {DefaultRAGStorageConfig.DOC_STATUS_STORAGE})",
|
|
||||||
)
|
|
||||||
parser.add_argument(
|
|
||||||
"--graph-storage",
|
|
||||||
default=get_env_value(
|
|
||||||
"LIGHTRAG_GRAPH_STORAGE", DefaultRAGStorageConfig.GRAPH_STORAGE
|
|
||||||
),
|
|
||||||
help=f"Graph storage implementation (default: {DefaultRAGStorageConfig.GRAPH_STORAGE})",
|
|
||||||
)
|
|
||||||
parser.add_argument(
|
|
||||||
"--vector-storage",
|
|
||||||
default=get_env_value(
|
|
||||||
"LIGHTRAG_VECTOR_STORAGE", DefaultRAGStorageConfig.VECTOR_STORAGE
|
|
||||||
),
|
|
||||||
help=f"Vector storage implementation (default: {DefaultRAGStorageConfig.VECTOR_STORAGE})",
|
|
||||||
)
|
|
||||||
|
|
||||||
# Bindings configuration
|
|
||||||
parser.add_argument(
|
|
||||||
"--llm-binding",
|
|
||||||
default=get_env_value("LLM_BINDING", "ollama"),
|
|
||||||
help="LLM binding to be used. Supported: lollms, ollama, openai (default: from env or ollama)",
|
|
||||||
)
|
|
||||||
parser.add_argument(
|
|
||||||
"--embedding-binding",
|
|
||||||
default=get_env_value("EMBEDDING_BINDING", "ollama"),
|
|
||||||
help="Embedding binding to be used. Supported: lollms, ollama, openai (default: from env or ollama)",
|
|
||||||
)
|
|
||||||
|
|
||||||
# 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)",
|
|
||||||
)
|
|
||||||
|
|
||||||
# LLM Model configuration
|
|
||||||
parser.add_argument(
|
|
||||||
"--llm-binding-host",
|
|
||||||
default=get_env_value("LLM_BINDING_HOST", None),
|
|
||||||
help="LLM server host URL. If not provided, defaults based on llm-binding:\n"
|
|
||||||
+ "- ollama: http://localhost:11434\n"
|
|
||||||
+ "- lollms: http://localhost:9600\n"
|
|
||||||
+ "- openai: https://api.openai.com/v1",
|
|
||||||
)
|
|
||||||
|
|
||||||
default_llm_api_key = get_env_value("LLM_BINDING_API_KEY", None)
|
|
||||||
|
|
||||||
parser.add_argument(
|
|
||||||
"--llm-binding-api-key",
|
|
||||||
default=default_llm_api_key,
|
|
||||||
help="llm server API key (default: from env or empty string)",
|
|
||||||
)
|
|
||||||
|
|
||||||
parser.add_argument(
|
|
||||||
"--llm-model",
|
|
||||||
default=get_env_value("LLM_MODEL", "mistral-nemo:latest"),
|
|
||||||
help="LLM model name (default: from env or mistral-nemo:latest)",
|
|
||||||
)
|
|
||||||
|
|
||||||
# Embedding model configuration
|
|
||||||
parser.add_argument(
|
|
||||||
"--embedding-binding-host",
|
|
||||||
default=get_env_value("EMBEDDING_BINDING_HOST", None),
|
|
||||||
help="Embedding server host URL. If not provided, defaults based on embedding-binding:\n"
|
|
||||||
+ "- ollama: http://localhost:11434\n"
|
|
||||||
+ "- lollms: http://localhost:9600\n"
|
|
||||||
+ "- openai: https://api.openai.com/v1",
|
|
||||||
)
|
|
||||||
|
|
||||||
default_embedding_api_key = get_env_value("EMBEDDING_BINDING_API_KEY", "")
|
|
||||||
parser.add_argument(
|
|
||||||
"--embedding-binding-api-key",
|
|
||||||
default=default_embedding_api_key,
|
|
||||||
help="embedding server API key (default: from env or empty string)",
|
|
||||||
)
|
|
||||||
|
|
||||||
parser.add_argument(
|
|
||||||
"--embedding-model",
|
|
||||||
default=get_env_value("EMBEDDING_MODEL", "bge-m3:latest"),
|
|
||||||
help="Embedding model name (default: from env or bge-m3:latest)",
|
|
||||||
)
|
|
||||||
|
|
||||||
parser.add_argument(
|
|
||||||
"--chunk_size",
|
|
||||||
default=get_env_value("CHUNK_SIZE", 1200),
|
|
||||||
help="chunk chunk size default 1200",
|
|
||||||
)
|
|
||||||
|
|
||||||
parser.add_argument(
|
|
||||||
"--chunk_overlap_size",
|
|
||||||
default=get_env_value("CHUNK_OVERLAP_SIZE", 100),
|
|
||||||
help="chunk overlap size default 100",
|
|
||||||
)
|
|
||||||
|
|
||||||
def timeout_type(value):
|
|
||||||
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)",
|
|
||||||
)
|
|
||||||
parser.add_argument(
|
|
||||||
"--embedding-dim",
|
|
||||||
type=int,
|
|
||||||
default=get_env_value("EMBEDDING_DIM", 1024, int),
|
|
||||||
help="Embedding dimensions (default: from env or 1024)",
|
|
||||||
)
|
|
||||||
parser.add_argument(
|
|
||||||
"--max-embed-tokens",
|
|
||||||
type=int,
|
|
||||||
default=get_env_value("MAX_EMBED_TOKENS", 8192, int),
|
|
||||||
help="Maximum embedding token size (default: from env or 8192)",
|
|
||||||
)
|
|
||||||
|
|
||||||
# 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(
|
|
||||||
"--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(
|
|
||||||
"--auto-scan-at-startup",
|
|
||||||
action="store_true",
|
|
||||||
default=False,
|
|
||||||
help="Enable automatic scanning when the program starts",
|
|
||||||
)
|
|
||||||
|
|
||||||
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(
|
|
||||||
"--verbose",
|
|
||||||
type=bool,
|
|
||||||
default=get_env_value("VERBOSE", False, bool),
|
|
||||||
help="Verbose debug output(default: from env or false)",
|
|
||||||
)
|
|
||||||
|
|
||||||
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)
|
|
||||||
|
|
||||||
ollama_server_infos.LIGHTRAG_MODEL = args.simulated_model_name
|
|
||||||
|
|
||||||
return args
|
|
||||||
|
|
||||||
|
|
||||||
def create_app(args):
|
def create_app(args):
|
||||||
# Set global top_k
|
# Set global top_k
|
||||||
global global_top_k
|
global global_top_k
|
||||||
|
|||||||
@@ -5,31 +5,13 @@ import logging
|
|||||||
import time
|
import time
|
||||||
import json
|
import json
|
||||||
import re
|
import re
|
||||||
import os
|
|
||||||
from enum import Enum
|
from enum import Enum
|
||||||
from fastapi.responses import StreamingResponse
|
from fastapi.responses import StreamingResponse
|
||||||
import asyncio
|
import asyncio
|
||||||
from ascii_colors import trace_exception
|
from ascii_colors import trace_exception
|
||||||
from lightrag import LightRAG, QueryParam
|
from lightrag import LightRAG, QueryParam
|
||||||
from lightrag.utils import encode_string_by_tiktoken
|
from lightrag.utils import encode_string_by_tiktoken
|
||||||
from dotenv import load_dotenv
|
from ..utils_api import ollama_server_infos
|
||||||
|
|
||||||
|
|
||||||
# Load environment variables
|
|
||||||
load_dotenv(override=True)
|
|
||||||
|
|
||||||
|
|
||||||
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()
|
|
||||||
|
|
||||||
|
|
||||||
# query mode according to query prefix (bypass is not LightRAG quer mode)
|
# query mode according to query prefix (bypass is not LightRAG quer mode)
|
||||||
|
|||||||
@@ -2,11 +2,33 @@
|
|||||||
Utility functions for the LightRAG API.
|
Utility functions for the LightRAG API.
|
||||||
"""
|
"""
|
||||||
|
|
||||||
|
import os
|
||||||
|
import argparse
|
||||||
from typing import Optional
|
from typing import Optional
|
||||||
|
import sys
|
||||||
|
from ascii_colors import ASCIIColors
|
||||||
|
from lightrag.api import __api_version__
|
||||||
from fastapi import HTTPException, Security
|
from fastapi import HTTPException, Security
|
||||||
|
from dotenv import load_dotenv
|
||||||
from fastapi.security import APIKeyHeader
|
from fastapi.security import APIKeyHeader
|
||||||
from starlette.status import HTTP_403_FORBIDDEN
|
from starlette.status import HTTP_403_FORBIDDEN
|
||||||
|
|
||||||
|
# Load environment variables
|
||||||
|
load_dotenv(override=True)
|
||||||
|
|
||||||
|
|
||||||
|
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_api_key_dependency(api_key: Optional[str]):
|
def get_api_key_dependency(api_key: Optional[str]):
|
||||||
"""
|
"""
|
||||||
@@ -43,3 +65,490 @@ def get_api_key_dependency(api_key: Optional[str]):
|
|||||||
return api_key_header_value
|
return api_key_header_value
|
||||||
|
|
||||||
return api_key_auth
|
return api_key_auth
|
||||||
|
|
||||||
|
|
||||||
|
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
|
||||||
|
|
||||||
|
Returns:
|
||||||
|
argparse.Namespace: Parsed arguments
|
||||||
|
"""
|
||||||
|
|
||||||
|
parser = argparse.ArgumentParser(
|
||||||
|
description="LightRAG FastAPI Server with separate working and input directories"
|
||||||
|
)
|
||||||
|
|
||||||
|
parser.add_argument(
|
||||||
|
"--kv-storage",
|
||||||
|
default=get_env_value(
|
||||||
|
"LIGHTRAG_KV_STORAGE", DefaultRAGStorageConfig.KV_STORAGE
|
||||||
|
),
|
||||||
|
help=f"KV storage implementation (default: {DefaultRAGStorageConfig.KV_STORAGE})",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--doc-status-storage",
|
||||||
|
default=get_env_value(
|
||||||
|
"LIGHTRAG_DOC_STATUS_STORAGE", DefaultRAGStorageConfig.DOC_STATUS_STORAGE
|
||||||
|
),
|
||||||
|
help=f"Document status storage implementation (default: {DefaultRAGStorageConfig.DOC_STATUS_STORAGE})",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--graph-storage",
|
||||||
|
default=get_env_value(
|
||||||
|
"LIGHTRAG_GRAPH_STORAGE", DefaultRAGStorageConfig.GRAPH_STORAGE
|
||||||
|
),
|
||||||
|
help=f"Graph storage implementation (default: {DefaultRAGStorageConfig.GRAPH_STORAGE})",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--vector-storage",
|
||||||
|
default=get_env_value(
|
||||||
|
"LIGHTRAG_VECTOR_STORAGE", DefaultRAGStorageConfig.VECTOR_STORAGE
|
||||||
|
),
|
||||||
|
help=f"Vector storage implementation (default: {DefaultRAGStorageConfig.VECTOR_STORAGE})",
|
||||||
|
)
|
||||||
|
|
||||||
|
# Bindings configuration
|
||||||
|
parser.add_argument(
|
||||||
|
"--llm-binding",
|
||||||
|
default=get_env_value("LLM_BINDING", "ollama"),
|
||||||
|
help="LLM binding to be used. Supported: lollms, ollama, openai (default: from env or ollama)",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--embedding-binding",
|
||||||
|
default=get_env_value("EMBEDDING_BINDING", "ollama"),
|
||||||
|
help="Embedding binding to be used. Supported: lollms, ollama, openai (default: from env or ollama)",
|
||||||
|
)
|
||||||
|
|
||||||
|
# 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)",
|
||||||
|
)
|
||||||
|
|
||||||
|
# LLM Model configuration
|
||||||
|
parser.add_argument(
|
||||||
|
"--llm-binding-host",
|
||||||
|
default=get_env_value("LLM_BINDING_HOST", None),
|
||||||
|
help="LLM server host URL. If not provided, defaults based on llm-binding:\n"
|
||||||
|
+ "- ollama: http://localhost:11434\n"
|
||||||
|
+ "- lollms: http://localhost:9600\n"
|
||||||
|
+ "- openai: https://api.openai.com/v1",
|
||||||
|
)
|
||||||
|
|
||||||
|
default_llm_api_key = get_env_value("LLM_BINDING_API_KEY", None)
|
||||||
|
|
||||||
|
parser.add_argument(
|
||||||
|
"--llm-binding-api-key",
|
||||||
|
default=default_llm_api_key,
|
||||||
|
help="llm server API key (default: from env or empty string)",
|
||||||
|
)
|
||||||
|
|
||||||
|
parser.add_argument(
|
||||||
|
"--llm-model",
|
||||||
|
default=get_env_value("LLM_MODEL", "mistral-nemo:latest"),
|
||||||
|
help="LLM model name (default: from env or mistral-nemo:latest)",
|
||||||
|
)
|
||||||
|
|
||||||
|
# Embedding model configuration
|
||||||
|
parser.add_argument(
|
||||||
|
"--embedding-binding-host",
|
||||||
|
default=get_env_value("EMBEDDING_BINDING_HOST", None),
|
||||||
|
help="Embedding server host URL. If not provided, defaults based on embedding-binding:\n"
|
||||||
|
+ "- ollama: http://localhost:11434\n"
|
||||||
|
+ "- lollms: http://localhost:9600\n"
|
||||||
|
+ "- openai: https://api.openai.com/v1",
|
||||||
|
)
|
||||||
|
|
||||||
|
default_embedding_api_key = get_env_value("EMBEDDING_BINDING_API_KEY", "")
|
||||||
|
parser.add_argument(
|
||||||
|
"--embedding-binding-api-key",
|
||||||
|
default=default_embedding_api_key,
|
||||||
|
help="embedding server API key (default: from env or empty string)",
|
||||||
|
)
|
||||||
|
|
||||||
|
parser.add_argument(
|
||||||
|
"--embedding-model",
|
||||||
|
default=get_env_value("EMBEDDING_MODEL", "bge-m3:latest"),
|
||||||
|
help="Embedding model name (default: from env or bge-m3:latest)",
|
||||||
|
)
|
||||||
|
|
||||||
|
parser.add_argument(
|
||||||
|
"--chunk_size",
|
||||||
|
default=get_env_value("CHUNK_SIZE", 1200),
|
||||||
|
help="chunk chunk size default 1200",
|
||||||
|
)
|
||||||
|
|
||||||
|
parser.add_argument(
|
||||||
|
"--chunk_overlap_size",
|
||||||
|
default=get_env_value("CHUNK_OVERLAP_SIZE", 100),
|
||||||
|
help="chunk overlap size default 100",
|
||||||
|
)
|
||||||
|
|
||||||
|
def timeout_type(value):
|
||||||
|
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)",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--embedding-dim",
|
||||||
|
type=int,
|
||||||
|
default=get_env_value("EMBEDDING_DIM", 1024, int),
|
||||||
|
help="Embedding dimensions (default: from env or 1024)",
|
||||||
|
)
|
||||||
|
parser.add_argument(
|
||||||
|
"--max-embed-tokens",
|
||||||
|
type=int,
|
||||||
|
default=get_env_value("MAX_EMBED_TOKENS", 8192, int),
|
||||||
|
help="Maximum embedding token size (default: from env or 8192)",
|
||||||
|
)
|
||||||
|
|
||||||
|
# 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(
|
||||||
|
"--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(
|
||||||
|
"--auto-scan-at-startup",
|
||||||
|
action="store_true",
|
||||||
|
default=False,
|
||||||
|
help="Enable automatic scanning when the program starts",
|
||||||
|
)
|
||||||
|
|
||||||
|
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(
|
||||||
|
"--verbose",
|
||||||
|
type=bool,
|
||||||
|
default=get_env_value("VERBOSE", False, bool),
|
||||||
|
help="Verbose debug output(default: from env or false)",
|
||||||
|
)
|
||||||
|
|
||||||
|
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)
|
||||||
|
|
||||||
|
ollama_server_infos.LIGHTRAG_MODEL = args.simulated_model_name
|
||||||
|
|
||||||
|
return args
|
||||||
|
|
||||||
|
|
||||||
|
def display_splash_screen(args: argparse.Namespace) -> None:
|
||||||
|
"""
|
||||||
|
Display a colorful splash screen showing LightRAG server configuration
|
||||||
|
|
||||||
|
Args:
|
||||||
|
args: Parsed command line arguments
|
||||||
|
"""
|
||||||
|
# Banner
|
||||||
|
ASCIIColors.cyan(f"""
|
||||||
|
╔══════════════════════════════════════════════════════════════╗
|
||||||
|
║ 🚀 LightRAG Server v{__api_version__} ║
|
||||||
|
║ Fast, Lightweight RAG Server Implementation ║
|
||||||
|
╚══════════════════════════════════════════════════════════════╝
|
||||||
|
""")
|
||||||
|
|
||||||
|
# Server Configuration
|
||||||
|
ASCIIColors.magenta("\n📡 Server Configuration:")
|
||||||
|
ASCIIColors.white(" ├─ Host: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.host}")
|
||||||
|
ASCIIColors.white(" ├─ Port: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.port}")
|
||||||
|
ASCIIColors.white(" ├─ CORS Origins: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{os.getenv('CORS_ORIGINS', '*')}")
|
||||||
|
ASCIIColors.white(" ├─ SSL Enabled: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.ssl}")
|
||||||
|
ASCIIColors.white(" └─ API Key: ", end="")
|
||||||
|
ASCIIColors.yellow("Set" if args.key else "Not Set")
|
||||||
|
if args.ssl:
|
||||||
|
ASCIIColors.white(" ├─ SSL Cert: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.ssl_certfile}")
|
||||||
|
ASCIIColors.white(" └─ SSL Key: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.ssl_keyfile}")
|
||||||
|
|
||||||
|
# Directory Configuration
|
||||||
|
ASCIIColors.magenta("\n📂 Directory Configuration:")
|
||||||
|
ASCIIColors.white(" ├─ Working Directory: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.working_dir}")
|
||||||
|
ASCIIColors.white(" └─ Input Directory: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.input_dir}")
|
||||||
|
|
||||||
|
# LLM Configuration
|
||||||
|
ASCIIColors.magenta("\n🤖 LLM Configuration:")
|
||||||
|
ASCIIColors.white(" ├─ Binding: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.llm_binding}")
|
||||||
|
ASCIIColors.white(" ├─ Host: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.llm_binding_host}")
|
||||||
|
ASCIIColors.white(" └─ Model: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.llm_model}")
|
||||||
|
|
||||||
|
# Embedding Configuration
|
||||||
|
ASCIIColors.magenta("\n📊 Embedding Configuration:")
|
||||||
|
ASCIIColors.white(" ├─ Binding: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.embedding_binding}")
|
||||||
|
ASCIIColors.white(" ├─ Host: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.embedding_binding_host}")
|
||||||
|
ASCIIColors.white(" ├─ Model: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.embedding_model}")
|
||||||
|
ASCIIColors.white(" └─ Dimensions: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.embedding_dim}")
|
||||||
|
|
||||||
|
# RAG Configuration
|
||||||
|
ASCIIColors.magenta("\n⚙️ RAG Configuration:")
|
||||||
|
ASCIIColors.white(" ├─ Max Async Operations: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.max_async}")
|
||||||
|
ASCIIColors.white(" ├─ Max Tokens: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.max_tokens}")
|
||||||
|
ASCIIColors.white(" ├─ Max Embed Tokens: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.max_embed_tokens}")
|
||||||
|
ASCIIColors.white(" ├─ Chunk Size: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.chunk_size}")
|
||||||
|
ASCIIColors.white(" ├─ Chunk Overlap Size: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.chunk_overlap_size}")
|
||||||
|
ASCIIColors.white(" ├─ History Turns: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.history_turns}")
|
||||||
|
ASCIIColors.white(" ├─ Cosine Threshold: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.cosine_threshold}")
|
||||||
|
ASCIIColors.white(" └─ Top-K: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.top_k}")
|
||||||
|
|
||||||
|
# System Configuration
|
||||||
|
ASCIIColors.magenta("\n💾 Storage Configuration:")
|
||||||
|
ASCIIColors.white(" ├─ KV Storage: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.kv_storage}")
|
||||||
|
ASCIIColors.white(" ├─ Vector Storage: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.vector_storage}")
|
||||||
|
ASCIIColors.white(" ├─ Graph Storage: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.graph_storage}")
|
||||||
|
ASCIIColors.white(" └─ Document Status Storage: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.doc_status_storage}")
|
||||||
|
|
||||||
|
ASCIIColors.magenta("\n🛠️ System Configuration:")
|
||||||
|
ASCIIColors.white(" ├─ Ollama Emulating Model: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{ollama_server_infos.LIGHTRAG_MODEL}")
|
||||||
|
ASCIIColors.white(" ├─ Log Level: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.log_level}")
|
||||||
|
ASCIIColors.white(" ├─ Verbose Debug: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.verbose}")
|
||||||
|
ASCIIColors.white(" └─ Timeout: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{args.timeout if args.timeout else 'None (infinite)'}")
|
||||||
|
|
||||||
|
# Server Status
|
||||||
|
ASCIIColors.green("\n✨ Server starting up...\n")
|
||||||
|
|
||||||
|
# Server Access Information
|
||||||
|
protocol = "https" if args.ssl else "http"
|
||||||
|
if args.host == "0.0.0.0":
|
||||||
|
ASCIIColors.magenta("\n🌐 Server Access Information:")
|
||||||
|
ASCIIColors.white(" ├─ Local Access: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}")
|
||||||
|
ASCIIColors.white(" ├─ Remote Access: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{protocol}://<your-ip-address>:{args.port}")
|
||||||
|
ASCIIColors.white(" ├─ API Documentation (local): ", end="")
|
||||||
|
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/docs")
|
||||||
|
ASCIIColors.white(" ├─ Alternative Documentation (local): ", end="")
|
||||||
|
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/redoc")
|
||||||
|
ASCIIColors.white(" └─ WebUI (local): ", end="")
|
||||||
|
ASCIIColors.yellow(f"{protocol}://localhost:{args.port}/webui")
|
||||||
|
|
||||||
|
ASCIIColors.yellow("\n📝 Note:")
|
||||||
|
ASCIIColors.white(""" Since the server is running on 0.0.0.0:
|
||||||
|
- Use 'localhost' or '127.0.0.1' for local access
|
||||||
|
- Use your machine's IP address for remote access
|
||||||
|
- To find your IP address:
|
||||||
|
• Windows: Run 'ipconfig' in terminal
|
||||||
|
• Linux/Mac: Run 'ifconfig' or 'ip addr' in terminal
|
||||||
|
""")
|
||||||
|
else:
|
||||||
|
base_url = f"{protocol}://{args.host}:{args.port}"
|
||||||
|
ASCIIColors.magenta("\n🌐 Server Access Information:")
|
||||||
|
ASCIIColors.white(" ├─ Base URL: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{base_url}")
|
||||||
|
ASCIIColors.white(" ├─ API Documentation: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{base_url}/docs")
|
||||||
|
ASCIIColors.white(" └─ Alternative Documentation: ", end="")
|
||||||
|
ASCIIColors.yellow(f"{base_url}/redoc")
|
||||||
|
|
||||||
|
# Usage Examples
|
||||||
|
ASCIIColors.magenta("\n📚 Quick Start Guide:")
|
||||||
|
ASCIIColors.cyan("""
|
||||||
|
1. Access the Swagger UI:
|
||||||
|
Open your browser and navigate to the API documentation URL above
|
||||||
|
|
||||||
|
2. API Authentication:""")
|
||||||
|
if args.key:
|
||||||
|
ASCIIColors.cyan(""" Add the following header to your requests:
|
||||||
|
X-API-Key: <your-api-key>
|
||||||
|
""")
|
||||||
|
else:
|
||||||
|
ASCIIColors.cyan(" No authentication required\n")
|
||||||
|
|
||||||
|
ASCIIColors.cyan(""" 3. Basic Operations:
|
||||||
|
- POST /upload_document: Upload new documents to RAG
|
||||||
|
- POST /query: Query your document collection
|
||||||
|
- GET /collections: List available collections
|
||||||
|
|
||||||
|
4. Monitor the server:
|
||||||
|
- Check server logs for detailed operation information
|
||||||
|
- Use healthcheck endpoint: GET /health
|
||||||
|
""")
|
||||||
|
|
||||||
|
# Security Notice
|
||||||
|
if args.key:
|
||||||
|
ASCIIColors.yellow("\n⚠️ Security Notice:")
|
||||||
|
ASCIIColors.white(""" API Key authentication is enabled.
|
||||||
|
Make sure to include the X-API-Key header in all your requests.
|
||||||
|
""")
|
||||||
|
|
||||||
|
ASCIIColors.green("Server is ready to accept connections! 🚀\n")
|
||||||
|
|
||||||
|
# Ensure splash output flush to system log
|
||||||
|
sys.stdout.flush()
|
||||||
|
|||||||
Reference in New Issue
Block a user