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

refactor(api): Code optimization based on review comments.

Browse Source 
- Removed authentication dependency for the health check endpoint in lightrag_server.py
- Removed the authentication dependency for the entire router in ollama_api.py
- Updated the parameter list and example usage in README.md, removing authentication-related parts
- Removed neo4j and tqdm dependencies from requirements.txt
- Deleted command-line argument parsing code related to authentication from utils_api.py
This commit is contained in:
Milin
2025-03-05 20:38:05 +08:00
parent 11502fc756
commit 59e3b2eec1
5 changed files with 29 additions and 69 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
lightrag/api/README.md
View File

@@ -295,32 +295,26 @@ You can not change storage implementation selection after you add documents to L
### LightRag API Server Comand Line Options
| Parameter | Default | Description |
|-------------------------|----------------|-----------------------------------------------------------------------------------------------------------------------------|
| --host | 0.0.0.0 | Server host |
| --port | 9621 | Server port |
| --working-dir | ./rag_storage | Working directory for RAG storage |
| --input-dir | ./inputs | Directory containing input documents |
| --max-async | 4 | Maximum async operations |
| --max-tokens | 32768 | Maximum token size |
| --timeout | 150 | Timeout in seconds. None for infinite timeout(not recommended) |
| --log-level | INFO | Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) |
| --verbose | - | Verbose debug output (True, Flase) |
| --key | None | API key for authentication. Protects lightrag server against unauthorized access |
| --ssl | False | Enable HTTPS |
| --ssl-certfile | None | Path to SSL certificate file (required if --ssl is enabled) |
| --ssl-keyfile | None | Path to SSL private key file (required if --ssl is enabled) |
| --top-k | 50 | Number of top-k items to retrieve; corresponds to entities in "local" mode and relationships in "global" mode. |
| --cosine-threshold | 0.4 | The cossine threshold for nodes and relations retrieval, works with top-k to control the retrieval of nodes and relations. |
| --llm-binding | ollama | LLM binding type (lollms, ollama, openai, openai-ollama, azure_openai) |
| --embedding-binding | ollama | Embedding binding type (lollms, ollama, openai, azure_openai) |
| --auto-scan-at-startup | - | Scan input directory for new files and start indexing |
| --auth-username | - | Enable jwt if not empty |
| --auth-password | - | Enable jwt if not empty |
| --token-secret | - | JWT key |
| --token-expire-hours | 4 | expire duration |
| --whitelist-paths | /login,/health | white list |
| Parameter | Default | Description |
|-----------|---------|-------------|
| --host | 0.0.0.0 | Server host |
| --port | 9621 | Server port |
| --working-dir | ./rag_storage | Working directory for RAG storage |
| --input-dir | ./inputs | Directory containing input documents |
| --max-async | 4 | Maximum async operations |
| --max-tokens | 32768 | Maximum token size |
| --timeout | 150 | Timeout in seconds. None for infinite timeout(not recommended) |
| --log-level | INFO | Logging level (DEBUG, INFO, WARNING, ERROR, CRITICAL) |
| --verbose | - | Verbose debug output (True, Flase) |
| --key | None | API key for authentication. Protects lightrag server against unauthorized access |
| --ssl | False | Enable HTTPS |
| --ssl-certfile | None | Path to SSL certificate file (required if --ssl is enabled) |
| --ssl-keyfile | None | Path to SSL private key file (required if --ssl is enabled) |
| --top-k | 50 | Number of top-k items to retrieve; corresponds to entities in "local" mode and relationships in "global" mode. |
| --cosine-threshold | 0.4 | The cossine threshold for nodes and relations retrieval, works with top-k to control the retrieval of nodes and relations. |
| --llm-binding | ollama | LLM binding type (lollms, ollama, openai, openai-ollama, azure_openai) |
| --embedding-binding | ollama | Embedding binding type (lollms, ollama, openai, azure_openai) |
| auto-scan-at-startup | - | Scan input directory for new files and start indexing |
### Example Usage
@@ -399,11 +393,11 @@ pip install lightrag-hku
LightRAG API Server implements JWT-based authentication using HS256 algorithm. To enable secure access control, the following environment variables are required:
```bash
# For jwt auth
AUTH_USERNAME=admin # login name --auth-username
AUTH_PASSWORD=admin123 # password --auth-password
TOKEN_SECRET=your-key # JWT key --token-secret
TOKEN_EXPIRE_HOURS=4 # expire duration --token-expire-hours
WHITELIST_PATHS=/login,/health # white list --whitelist-paths
AUTH_USERNAME=admin # login name
AUTH_PASSWORD=admin123 # password
TOKEN_SECRET=your-key # JWT key
TOKEN_EXPIRE_HOURS=4 # expire duration
WHITELIST_PATHS=/api1,/api2 # white list. /login,/health,/docs,/redoc,/openapi.json are whitelisted by default.
```
## API Endpoints

2
lightrag/api/lightrag_server.py
View File

@@ -400,7 +400,7 @@ def create_app(args):
"token_type": "bearer"
}
@app.get("/health", dependencies=[Depends(optional_api_key), Depends(get_auth_dependency())])
@app.get("/health", dependencies=[Depends(optional_api_key)])
async def get_status():
"""Get current system status"""
# Get update flags status for all namespaces

2
lightrag/api/requirements.txt
View File

@@ -8,14 +8,12 @@ python-multipart
tenacity
tiktoken
uvicorn
tqdm
jiter
httpcore
distro
httpx
openai
asyncpg
neo4j
pytz
python-jose[cryptography]
passlib[bcrypt]

6
lightrag/api/routers/ollama_api.py
View File

@@ -1,4 +1,4 @@
from fastapi import APIRouter, HTTPException, Request, Depends
from fastapi import APIRouter, HTTPException, Request
from pydantic import BaseModel
from typing import List, Dict, Any, Optional
import logging
@@ -11,7 +11,7 @@ import asyncio
from ascii_colors import trace_exception
from lightrag import LightRAG, QueryParam
from lightrag.utils import encode_string_by_tiktoken
from ..utils_api import ollama_server_infos, get_auth_dependency
from ..utils_api import ollama_server_infos
# query mode according to query prefix (bypass is not LightRAG quer mode)
@@ -126,7 +126,7 @@ class OllamaAPI:
self.rag = rag
self.ollama_server_infos = ollama_server_infos
self.top_k = top_k
self.router = APIRouter(tags=["ollama"], dependencies=[Depends(get_auth_dependency())])
self.router = APIRouter(tags=["ollama"])
self.setup_routes()
def setup_routes(self):

32
lightrag/api/utils_api.py
View File

@@ -312,38 +312,6 @@ def parse_args(is_uvicorn_mode: bool = False) -> argparse.Namespace:
help="Embedding binding type (default: from env or ollama)",
)
# Authentication configuration
parser.add_argument(
"--auth-username",
type=str,
default=get_env_value("AUTH_USERNAME", ""),
help="Login username (default: from env or empty)"
)
parser.add_argument(
"--auth-password",
type=str,
default=get_env_value("AUTH_PASSWORD", ""),
help="Login password (default: from env or empty)"
)
parser.add_argument(
"--token-secret",
type=str,
default=get_env_value("TOKEN_SECRET", ""),
help="JWT signing secret (default: from env or empty)"
)
parser.add_argument(
"--token-expire-hours",
type=int,
default=get_env_value("TOKEN_EXPIRE_HOURS", 4, int),
help="Token validity in hours (default: from env or 4)"
)
parser.add_argument(
"--whitelist-paths",
type=str,
default=get_env_value("WHITELIST_PATHS", "/login,/health"),
help="Comma-separated auth-exempt paths (default: from env or /login,/health)"
)
args = parser.parse_args()
# If in uvicorn mode and workers > 1, force it to 1 and log warning