feat(vertex): 集成 Vertex AI Express API 支持

本次更新引入了对 Google Vertex AI Express API 的支持，允许用户配置和使用 Vertex AI 模型。主要变更包括：后端： - 新增 `VERTEX_API_KEYS` 和 `VERTEX_EXPRESS_BASE_URL` 至系统配置 ([`.env.example`](.env.example:13), [`app/config/config.py:62`](app/config/config.py:62), [`app/database/models.py`](app/database/models.py), [`app/database/services.py`](app/database/services.py))。 - 实现 `VertexExpressChatService` ([`app/service/chat/vertex_express_chat_service.py`](app/service/chat/vertex_express_chat_service.py)) 用于处理与 Vertex AI Express API 的交互。 - 添加 `vertex_express_routes` ([`app/router/vertex_express_routes.py`](app/router/vertex_express_routes.py)) 来暴露 Vertex AI 相关的 API 端点，并集成到主应用 ([`app/core/application.py:36`](app/core/application.py:36), [`app/router/routes.py:15`](app/router/routes.py:15))。 - 更新密钥管理器 ([`app/service/key/key_manager.py`](app/service/key/key_manager.py)) 以支持 Vertex API 密钥的获取、检查和轮换。前端 (配置编辑器): - 在配置页面 ([`app/templates/config_editor.html:463`](app/templates/config_editor.html:463)) 添加了 Vertex API 密钥列表和 Vertex Express API 基础 URL 的表单字段。 - 实现了批量添加和删除 Vertex API 密钥的功能，包括相应的模态框和操作逻辑 ([`app/static/js/config_editor.js:550`](app/static/js/config_editor.js:550), [`app/static/js/config_editor.js:1097`](app/static/js/config_editor.js:1097), [`app/templates/config_editor.html:1657`](app/templates/config_editor.html:1657))。 - 确保新的配置项在初始化 ([`app/static/js/config_editor.js:598`](app/static/js/config_editor.js:598)) 和表单填充 ([`app/static/js/config_editor.js:671`](app/static/js/config_editor.js:671)) 时得到正确处理。 - 更新了数组项添加逻辑以识别 `VERTEX_API_KEYS` 为敏感字段 ([`app/static/js/config_editor.js:1235`](app/static/js/config_editor.js:1235))。此功能扩展了应用支持的 AI 服务范围，为用户提供了更多模型选择。
2026-09-05 15:36:45 +08:00 · 2025-05-17 00:13:49 +08:00
parent e260ad02bf
commit 6aab140ec2
19 changed files with 1040 additions and 77 deletions
@@ -8,7 +8,7 @@ from fastapi.templating import Jinja2Templates

 from app.core.security import verify_auth_token
 from app.log.logger import get_routes_logger
-from app.router import error_log_routes, gemini_routes, openai_routes, config_routes, scheduler_routes, stats_routes, version_routes, openai_compatiable_routes
+from app.router import error_log_routes, gemini_routes, openai_routes, config_routes, scheduler_routes, stats_routes, version_routes, openai_compatiable_routes, vertex_express_routes
 from app.service.key.key_manager import get_key_manager_instance
 from app.service.stats.stats_service import StatsService

@@ -33,6 +33,7 @@ def setup_routers(app: FastAPI) -> None:
    app.include_router(stats_routes.router)
    app.include_router(version_routes.router)
    app.include_router(openai_compatiable_routes.router)
+    app.include_router(vertex_express_routes.router)

    setup_page_routes(app)

@@ -0,0 +1,146 @@
+from fastapi import APIRouter, Depends, HTTPException
+from fastapi.responses import StreamingResponse
+from copy import deepcopy
+from app.config.config import settings
+from app.log.logger import get_vertex_express_logger
+from app.core.security import SecurityService
+from app.domain.gemini_models import GeminiRequest
+from app.service.chat.vertex_express_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.handler.error_handler import handle_route_errors
+from app.core.constants import API_VERSION
+
+router = APIRouter(prefix=f"/vertex-express/{API_VERSION}")
+logger = get_vertex_express_logger()
+
+security_service = SecurityService()
+model_service = ModelService()
+
+
+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_vertex_key()
+
+
+async def get_chat_service(key_manager: KeyManager = Depends(get_key_manager)):
+    """获取Gemini聊天服务实例"""
+    return GeminiChatService(settings.VERTEX_EXPRESS_BASE_URL, key_manager)
+
+
+@router.get("/models")
+async def list_models(
+    _=Depends(security_service.verify_key_or_goog_api_key),
+    key_manager: KeyManager = Depends(get_key_manager)
+):
+    """获取可用的 Gemini 模型列表，并根据配置添加衍生模型（搜索、图像、非思考）。"""
+    operation_name = "list_gemini_models"
+    logger.info("-" * 50 + operation_name + "-" * 50)
+    logger.info("Handling Gemini models list request")
+
+    try:
+        api_key = await key_manager.get_first_valid_key()
+        if not api_key:
+            raise HTTPException(status_code=503, detail="No valid API keys available to fetch models.")
+        logger.info(f"Using API key: {api_key}")
+
+        models_data = await model_service.get_gemini_models(api_key)
+        if not models_data or "models" not in models_data:
+            raise HTTPException(status_code=500, detail="Failed to fetch base models list.")
+
+        models_json = deepcopy(models_data)
+        model_mapping = {x.get("name", "").split("/", maxsplit=1)[-1]: x for x in models_json.get("models", [])}
+
+        def add_derived_model(base_name, suffix, display_suffix):
+            model = model_mapping.get(base_name)
+            if not model:
+                logger.warning(f"Base model '{base_name}' not found for derived model '{suffix}'.")
+                return
+            item = deepcopy(model)
+            item["name"] = f"models/{base_name}{suffix}"
+            display_name = f'{item.get("displayName", base_name)}{display_suffix}'
+            item["displayName"] = display_name
+            item["description"] = display_name
+            models_json["models"].append(item)
+
+        if settings.SEARCH_MODELS:
+            for name in settings.SEARCH_MODELS:
+                add_derived_model(name, "-search", " For Search")
+        if settings.IMAGE_MODELS:
+            for name in settings.IMAGE_MODELS:
+                 add_derived_model(name, "-image", " For Image")
+        if settings.THINKING_MODELS:
+            for name in settings.THINKING_MODELS:
+                add_derived_model(name, "-non-thinking", " Non Thinking")
+
+        logger.info("Gemini models list request successful")
+        return models_json
+    except HTTPException as http_exc:
+        raise http_exc
+    except Exception as e:
+        logger.error(f"Error getting Gemini models list: {str(e)}")
+        raise HTTPException(
+            status_code=500, detail="Internal server error while fetching Gemini models list"
+        ) from e
+
+
+@router.post("/models/{model_name}:generateContent")
+@RetryHandler(key_arg="api_key")
+async def generate_content(
+    model_name: str,
+    request: GeminiRequest,
+    _=Depends(security_service.verify_key_or_goog_api_key),
+    api_key: str = Depends(get_next_working_key),
+    key_manager: KeyManager = Depends(get_key_manager),
+    chat_service: GeminiChatService = Depends(get_chat_service)
+):
+    """处理 Gemini 非流式内容生成请求。"""
+    operation_name = "gemini_generate_content"
+    async with handle_route_errors(logger, operation_name, failure_message="Content generation failed"):
+        logger.info(f"Handling Gemini content generation request for model: {model_name}")
+        logger.debug(f"Request: \n{request.model_dump_json(indent=2)}")
+        logger.info(f"Using API key: {api_key}")
+
+        if not await model_service.check_model_support(model_name):
+            raise HTTPException(status_code=400, detail=f"Model {model_name} is not supported")
+
+        response = await chat_service.generate_content(
+            model=model_name,
+            request=request,
+            api_key=api_key
+        )
+        return response
+
+
+@router.post("/models/{model_name}:streamGenerateContent")
+@RetryHandler(key_arg="api_key")
+async def stream_generate_content(
+    model_name: str,
+    request: GeminiRequest,
+    _=Depends(security_service.verify_key_or_goog_api_key),
+    api_key: str = Depends(get_next_working_key),
+    key_manager: KeyManager = Depends(get_key_manager),
+    chat_service: GeminiChatService = Depends(get_chat_service)
+):
+    """处理 Gemini 流式内容生成请求。"""
+    operation_name = "gemini_stream_generate_content"
+    async with handle_route_errors(logger, operation_name, failure_message="Streaming request initiation failed"):
+        logger.info(f"Handling Gemini streaming content generation for model: {model_name}")
+        logger.debug(f"Request: \n{request.model_dump_json(indent=2)}")
+        logger.info(f"Using API key: {api_key}")
+
+        if not await model_service.check_model_support(model_name):
+            raise HTTPException(status_code=400, detail=f"Model {model_name} is not supported")
+
+        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")