mirror of
https://github.com/snailyp/gemini-balance.git
synced 2026-09-04 23:19:17 +08:00
refactor: 项目结构优化与FastAPI生命周期更新
重构项目目录结构，提高代码组织性和可维护性 将schemas目录重命名为domain，更好地表达领域模型概念 将services目录细分为service/chat、service/image等子目录 将api目录重命名为router，更符合FastAPI惯例 创建utils目录存放通用工具函数 更新FastAPI应用程序生命周期管理 替换已弃用的on_event方法为推荐的lifespan事件处理器 添加应用程序关闭时的日志记录 代码质量改进 抽取常量到constants.py，减少硬编码值 添加helpers.py提供通用工具函数 优化配置管理，使用环境变量和默认值 完善文档字符串，提高代码可读性
This commit is contained in:
snaily
@@ -0,0 +1,178 @@
|
||||
from fastapi import APIRouter, Depends, HTTPException
|
||||
from fastapi.responses import StreamingResponse, JSONResponse
|
||||
from copy import deepcopy
|
||||
from app.config.config import settings
|
||||
from app.logger.logger import get_gemini_logger
|
||||
from app.core.security import SecurityService
|
||||
from app.domain.gemini_models import GeminiContent, GeminiRequest
|
||||
from app.service.chat.gemini_chat_service import GeminiChatService
|
||||
from app.service.key.key_manager import KeyManager, get_key_manager_instance
|
||||
from app.service.model.model_service import ModelService
|
||||
from app.handler.retry_handler import RetryHandler
|
||||
from app.core.constants import API_VERSION
|
||||
|
||||
# 路由设置
|
||||
router = APIRouter(prefix=f"/gemini/{API_VERSION}")
|
||||
router_v1beta = APIRouter(prefix=f"/{API_VERSION}")
|
||||
logger = get_gemini_logger()
|
||||
|
||||
# 初始化服务
|
||||
security_service = SecurityService(settings.ALLOWED_TOKENS, settings.AUTH_TOKEN)
|
||||
model_service = ModelService(settings.SEARCH_MODELS, settings.IMAGE_MODELS)
|
||||
|
||||
|
||||
async def get_key_manager():
|
||||
"""获取密钥管理器实例"""
|
||||
return await get_key_manager_instance()
|
||||
|
||||
|
||||
async def get_next_working_key(key_manager: KeyManager = Depends(get_key_manager)):
|
||||
"""获取下一个可用的API密钥"""
|
||||
return await key_manager.get_next_working_key()
|
||||
|
||||
|
||||
@router.get("/models")
|
||||
@router_v1beta.get("/models")
|
||||
async def list_models(
|
||||
_=Depends(security_service.verify_key),
|
||||
key_manager: KeyManager = Depends(get_key_manager)
|
||||
):
|
||||
"""获取可用的Gemini模型列表"""
|
||||
logger.info("-" * 50 + "list_gemini_models" + "-" * 50)
|
||||
logger.info("Handling Gemini models list request")
|
||||
|
||||
api_key = await key_manager.get_next_working_key()
|
||||
logger.info(f"Using API key: {api_key}")
|
||||
|
||||
models_json = model_service.get_gemini_models(api_key)
|
||||
model_mapping = {x.get("name", "").split("/", maxsplit=1)[1]: x for x in models_json["models"]}
|
||||
|
||||
# 添加搜索模型
|
||||
if model_service.search_models:
|
||||
for name in model_service.search_models:
|
||||
model = model_mapping.get(name)
|
||||
if not model:
|
||||
continue
|
||||
|
||||
item = deepcopy(model)
|
||||
item["name"] = f"models/{name}-search"
|
||||
display_name = f'{item.get("displayName")} For Search'
|
||||
item["displayName"] = display_name
|
||||
item["description"] = display_name
|
||||
|
||||
models_json["models"].append(item)
|
||||
|
||||
# 添加图像生成模型
|
||||
if model_service.image_models:
|
||||
for name in model_service.image_models:
|
||||
model = model_mapping.get(name)
|
||||
if not model:
|
||||
continue
|
||||
|
||||
item = deepcopy(model)
|
||||
item["name"] = f"models/{name}-image"
|
||||
display_name = f'{item.get("displayName")} For Image'
|
||||
item["displayName"] = display_name
|
||||
item["description"] = display_name
|
||||
|
||||
models_json["models"].append(item)
|
||||
|
||||
return models_json
|
||||
|
||||
|
||||
@router.post("/models/{model_name}:generateContent")
|
||||
@router_v1beta.post("/models/{model_name}:generateContent")
|
||||
@RetryHandler(max_retries=3, key_arg="api_key")
|
||||
async def generate_content(
|
||||
model_name: str,
|
||||
request: GeminiRequest,
|
||||
_=Depends(security_service.verify_goog_api_key),
|
||||
api_key: str = Depends(get_next_working_key),
|
||||
key_manager: KeyManager = Depends(get_key_manager)
|
||||
):
|
||||
"""非流式生成内容"""
|
||||
logger.info("-" * 50 + "gemini_generate_content" + "-" * 50)
|
||||
logger.info(f"Handling Gemini content generation request for model: {model_name}")
|
||||
logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
|
||||
logger.info(f"Using API key: {api_key}")
|
||||
|
||||
if not model_service.check_model_support(model_name):
|
||||
raise HTTPException(status_code=400, detail=f"Model {model_name} is not supported")
|
||||
|
||||
try:
|
||||
chat_service = GeminiChatService(settings.BASE_URL, key_manager)
|
||||
response = await chat_service.generate_content(
|
||||
model=model_name,
|
||||
request=request,
|
||||
api_key=api_key
|
||||
)
|
||||
return response
|
||||
except Exception as e:
|
||||
logger.error(f"Chat completion failed after retries: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail="Chat completion failed") from e
|
||||
|
||||
|
||||
@router.post("/models/{model_name}:streamGenerateContent")
|
||||
@router_v1beta.post("/models/{model_name}:streamGenerateContent")
|
||||
@RetryHandler(max_retries=3, key_arg="api_key")
|
||||
async def stream_generate_content(
|
||||
model_name: str,
|
||||
request: GeminiRequest,
|
||||
_=Depends(security_service.verify_goog_api_key),
|
||||
api_key: str = Depends(get_next_working_key),
|
||||
key_manager: KeyManager = Depends(get_key_manager)
|
||||
):
|
||||
"""流式生成内容"""
|
||||
logger.info("-" * 50 + "gemini_stream_generate_content" + "-" * 50)
|
||||
logger.info(f"Handling Gemini streaming content generation for model: {model_name}")
|
||||
logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
|
||||
logger.info(f"Using API key: {api_key}")
|
||||
|
||||
if not model_service.check_model_support(model_name):
|
||||
raise HTTPException(status_code=400, detail=f"Model {model_name} is not supported")
|
||||
|
||||
try:
|
||||
chat_service = GeminiChatService(settings.BASE_URL, key_manager)
|
||||
response_stream = chat_service.stream_generate_content(
|
||||
model=model_name,
|
||||
request=request,
|
||||
api_key=api_key
|
||||
)
|
||||
return StreamingResponse(response_stream, media_type="text/event-stream")
|
||||
except Exception as e:
|
||||
logger.error(f"Streaming request failed: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail="Streaming request failed") from e
|
||||
|
||||
|
||||
@router.post("/verify-key/{api_key}")
|
||||
async def verify_key(api_key: str):
|
||||
"""验证Gemini API密钥的有效性"""
|
||||
logger.info("-" * 50 + "verify_gemini_key" + "-" * 50)
|
||||
logger.info("Verifying API key validity")
|
||||
|
||||
try:
|
||||
key_manager = await get_key_manager()
|
||||
chat_service = GeminiChatService(settings.BASE_URL, key_manager)
|
||||
|
||||
# 使用generate_content接口测试key的有效性
|
||||
gemini_request = GeminiRequest(
|
||||
contents=[
|
||||
GeminiContent(
|
||||
role="user",
|
||||
parts=[{"text": "hi"}]
|
||||
)
|
||||
]
|
||||
)
|
||||
|
||||
response = await chat_service.generate_content(
|
||||
settings.TEST_MODEL,
|
||||
gemini_request,
|
||||
api_key
|
||||
)
|
||||
|
||||
if response:
|
||||
return JSONResponse({"status": "valid"})
|
||||
return JSONResponse({"status": "invalid"})
|
||||
except Exception as e:
|
||||
logger.error(f"Key verification failed: {str(e)}")
|
||||
return JSONResponse({"status": "invalid", "error": str(e)})
|
||||
@@ -0,0 +1,145 @@
|
||||
from fastapi import HTTPException, APIRouter, Depends
|
||||
from fastapi.responses import StreamingResponse
|
||||
|
||||
from app.config.config import settings
|
||||
from app.logger.logger import get_openai_logger
|
||||
from app.core.security import SecurityService
|
||||
from app.domain.openai_models import ChatRequest, EmbeddingRequest, ImageGenerationRequest
|
||||
from app.handler.retry_handler import RetryHandler
|
||||
from app.service.embedding.embedding_service import EmbeddingService
|
||||
from app.service.image.image_create_service import ImageCreateService
|
||||
from app.service.key.key_manager import KeyManager, get_key_manager_instance
|
||||
from app.service.model.model_service import ModelService
|
||||
from app.service.chat.openai_chat_service import OpenAIChatService
|
||||
|
||||
router = APIRouter()
|
||||
logger = get_openai_logger()
|
||||
|
||||
# 初始化服务
|
||||
security_service = SecurityService(settings.ALLOWED_TOKENS, settings.AUTH_TOKEN)
|
||||
model_service = ModelService(settings.SEARCH_MODELS,settings.IMAGE_MODELS)
|
||||
embedding_service = EmbeddingService(settings.BASE_URL)
|
||||
image_create_service = ImageCreateService()
|
||||
|
||||
async def get_key_manager():
|
||||
return await get_key_manager_instance()
|
||||
|
||||
async def get_next_working_key_wrapper(key_manager: KeyManager = Depends(get_key_manager)):
|
||||
return await key_manager.get_next_working_key()
|
||||
|
||||
@router.get("/v1/models")
|
||||
@router.get("/hf/v1/models")
|
||||
async def list_models(
|
||||
_=Depends(security_service.verify_authorization),
|
||||
key_manager: KeyManager = Depends(get_key_manager)
|
||||
):
|
||||
logger.info("-" * 50 + "list_models" + "-" * 50)
|
||||
logger.info("Handling models list request")
|
||||
api_key = await key_manager.get_next_working_key()
|
||||
logger.info(f"Using API key: {api_key}")
|
||||
try:
|
||||
return model_service.get_gemini_openai_models(api_key)
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting models list: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail="Internal server error while fetching models list") from e
|
||||
|
||||
|
||||
@router.post("/v1/chat/completions")
|
||||
@router.post("/hf/v1/chat/completions")
|
||||
@RetryHandler(max_retries=3, key_arg="api_key")
|
||||
async def chat_completion(
|
||||
request: ChatRequest,
|
||||
_=Depends(security_service.verify_authorization),
|
||||
api_key: str = Depends(get_next_working_key_wrapper),
|
||||
key_manager: KeyManager = Depends(get_key_manager)
|
||||
):
|
||||
# 如果model是imagen3,使用paid_key
|
||||
if request.model == f"{settings.CREATE_IMAGE_MODEL}-chat":
|
||||
api_key = await key_manager.get_paid_key()
|
||||
chat_service = OpenAIChatService(settings.BASE_URL, key_manager)
|
||||
logger.info("-" * 50 + "chat_completion" + "-" * 50)
|
||||
logger.info(f"Handling chat completion request for model: {request.model}")
|
||||
logger.info(f"Request: \n{request.model_dump_json(indent=2)}")
|
||||
logger.info(f"Using API key: {api_key}")
|
||||
|
||||
if not model_service.check_model_support(request.model):
|
||||
raise HTTPException(status_code=400, detail=f"Model {request.model} is not supported")
|
||||
|
||||
try:
|
||||
# 如果model是imagen3,使用paid_key
|
||||
if request.model == f"{settings.CREATE_IMAGE_MODEL}-chat":
|
||||
response = await chat_service.create_image_chat_completion(request=request)
|
||||
else:
|
||||
response = await chat_service.create_chat_completion(request, api_key)
|
||||
# 处理流式响应
|
||||
if request.stream:
|
||||
return StreamingResponse(response, media_type="text/event-stream")
|
||||
logger.info("Chat completion request successful")
|
||||
return response
|
||||
except Exception as e:
|
||||
logger.error(f"Chat completion failed after retries: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail="Chat completion failed") from e
|
||||
|
||||
@router.post("/v1/images/generations")
|
||||
@router.post("/hf/v1/images/generations")
|
||||
async def generate_image(
|
||||
request: ImageGenerationRequest,
|
||||
_=Depends(security_service.verify_authorization),
|
||||
):
|
||||
logger.info("-" * 50 + "generate_image" + "-" * 50)
|
||||
logger.info(f"Handling image generation request for prompt: {request.prompt}")
|
||||
|
||||
try:
|
||||
response = image_create_service.generate_images(request)
|
||||
logger.info("Image generation request successful")
|
||||
return response
|
||||
except Exception as e:
|
||||
logger.error(f"Image generation request failed: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail="Image generation request failed") from e
|
||||
|
||||
@router.post("/v1/embeddings")
|
||||
@router.post("/hf/v1/embeddings")
|
||||
async def embedding(
|
||||
request: EmbeddingRequest,
|
||||
_=Depends(security_service.verify_authorization),
|
||||
key_manager: KeyManager = Depends(get_key_manager)
|
||||
):
|
||||
logger.info("-" * 50 + "embedding" + "-" * 50)
|
||||
logger.info(f"Handling embedding request for model: {request.model}")
|
||||
api_key = await key_manager.get_next_working_key()
|
||||
logger.info(f"Using API key: {api_key}")
|
||||
try:
|
||||
response = await embedding_service.create_embedding(
|
||||
input_text=request.input, model=request.model, api_key=api_key
|
||||
)
|
||||
logger.info("Embedding request successful")
|
||||
return response
|
||||
except Exception as e:
|
||||
logger.error(f"Embedding request failed: {str(e)}")
|
||||
raise HTTPException(status_code=500, detail="Embedding request failed") from e
|
||||
|
||||
@router.get("/v1/keys/list")
|
||||
@router.get("/hf/v1/keys/list")
|
||||
async def get_keys_list(
|
||||
_=Depends(security_service.verify_auth_token),
|
||||
key_manager: KeyManager = Depends(get_key_manager)
|
||||
):
|
||||
"""获取有效和无效的API key列表"""
|
||||
logger.info("-" * 50 + "get_keys_list" + "-" * 50)
|
||||
logger.info("Handling keys list request")
|
||||
try:
|
||||
keys_status = await key_manager.get_keys_by_status()
|
||||
return {
|
||||
"status": "success",
|
||||
"data": {
|
||||
"valid_keys": keys_status["valid_keys"],
|
||||
"invalid_keys": keys_status["invalid_keys"]
|
||||
},
|
||||
"total": len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"])
|
||||
}
|
||||
except Exception as e:
|
||||
logger.error(f"Error getting keys list: {str(e)}")
|
||||
raise HTTPException(
|
||||
status_code=500,
|
||||
detail="Internal server error while fetching keys list"
|
||||
) from e
|
||||
@@ -0,0 +1,103 @@
|
||||
"""
|
||||
路由配置模块，负责设置和配置应用程序的路由
|
||||
"""
|
||||
from fastapi import FastAPI, Request
|
||||
from fastapi.responses import HTMLResponse, RedirectResponse
|
||||
from fastapi.templating import Jinja2Templates
|
||||
|
||||
from app.logger.logger import get_main_logger
|
||||
from app.core.security import verify_auth_token
|
||||
from app.router import gemini_routes, openai_routes
|
||||
from app.service.key.key_manager import get_key_manager_instance
|
||||
|
||||
logger = get_main_logger()
|
||||
|
||||
# 配置Jinja2模板
|
||||
templates = Jinja2Templates(directory="app/templates")
|
||||
|
||||
def setup_routers(app: FastAPI) -> None:
|
||||
"""
|
||||
设置应用程序的路由
|
||||
|
||||
Args:
|
||||
app: FastAPI应用程序实例
|
||||
"""
|
||||
# 包含API路由
|
||||
app.include_router(openai_routes.router)
|
||||
app.include_router(gemini_routes.router)
|
||||
app.include_router(gemini_routes.router_v1beta)
|
||||
|
||||
# 添加页面路由
|
||||
setup_page_routes(app)
|
||||
|
||||
# 添加健康检查路由
|
||||
setup_health_routes(app)
|
||||
|
||||
def setup_page_routes(app: FastAPI) -> None:
|
||||
"""
|
||||
设置页面相关的路由
|
||||
|
||||
Args:
|
||||
app: FastAPI应用程序实例
|
||||
"""
|
||||
@app.get("/", response_class=HTMLResponse)
|
||||
async def auth_page(request: Request):
|
||||
"""认证页面"""
|
||||
return templates.TemplateResponse("auth.html", {"request": request})
|
||||
|
||||
@app.post("/auth")
|
||||
async def authenticate(request: Request):
|
||||
"""处理认证请求"""
|
||||
try:
|
||||
form = await request.form()
|
||||
auth_token = form.get("auth_token")
|
||||
if not auth_token:
|
||||
logger.warning("Authentication attempt with empty token")
|
||||
return RedirectResponse(url="/", status_code=302)
|
||||
|
||||
if verify_auth_token(auth_token):
|
||||
logger.info("Successful authentication")
|
||||
response = RedirectResponse(url="/keys", status_code=302)
|
||||
response.set_cookie(key="auth_token", value=auth_token, httponly=True, max_age=3600)
|
||||
return response
|
||||
logger.warning("Failed authentication attempt with invalid token")
|
||||
return RedirectResponse(url="/", status_code=302)
|
||||
except Exception as e:
|
||||
logger.error(f"Authentication error: {str(e)}")
|
||||
return RedirectResponse(url="/", status_code=302)
|
||||
|
||||
@app.get("/keys", response_class=HTMLResponse)
|
||||
async def keys_page(request: Request):
|
||||
"""密钥管理页面"""
|
||||
try:
|
||||
auth_token = request.cookies.get("auth_token")
|
||||
if not auth_token or not verify_auth_token(auth_token):
|
||||
logger.warning("Unauthorized access attempt to keys page")
|
||||
return RedirectResponse(url="/", status_code=302)
|
||||
|
||||
key_manager = await get_key_manager_instance()
|
||||
keys_status = await key_manager.get_keys_by_status()
|
||||
total = len(keys_status["valid_keys"]) + len(keys_status["invalid_keys"])
|
||||
logger.info(f"Keys status retrieved successfully. Total keys: {total}")
|
||||
return templates.TemplateResponse("keys_status.html", {
|
||||
"request": request,
|
||||
"valid_keys": keys_status["valid_keys"],
|
||||
"invalid_keys": keys_status["invalid_keys"],
|
||||
"total": total
|
||||
})
|
||||
except Exception as e:
|
||||
logger.error(f"Error retrieving keys status: {str(e)}")
|
||||
raise
|
||||
|
||||
def setup_health_routes(app: FastAPI) -> None:
|
||||
"""
|
||||
设置健康检查相关的路由
|
||||
|
||||
Args:
|
||||
app: FastAPI应用程序实例
|
||||
"""
|
||||
@app.get("/health")
|
||||
async def health_check(request: Request):
|
||||
"""健康检查端点"""
|
||||
logger.info("Health check endpoint called")
|
||||
return {"status": "healthy"}
|
||||
Reference in New Issue
Block a user