diff --git a/CLAUDE.md b/CLAUDE.md new file mode 100644 index 0000000..bbc02f8 --- /dev/null +++ b/CLAUDE.md @@ -0,0 +1,63 @@ +# CLAUDE.md + +This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository. + +## 项目概述 + +RTC AIGC Demo — 基于火山引擎 RTC SDK 的实时 AI 语音对话演示应用，前后端分离架构。前端 React + TypeScript，后端 Python FastAPI。 + +## 常用命令 + +### 前端 (frontend/) +```bash +cd frontend +npm install # 安装依赖 +npm run dev # 开发服务器 (localhost:3000) +npm run build # 生产构建 +npm run eslint # ESLint 检查并修复 +npm run stylelint # LESS 样式检查 +npm run prettier # 代码格式化 +npm run test # 运行测试 +``` + +### 后端 (backend/) +```bash +cd backend +cp .env.example .env # 首次需复制环境变量配置 +uv sync # 安装依赖（使用 uv 包管理器） +uv run uvicorn server:app --host 0.0.0.0 --port 3001 --reload # 启动开发服务器 +``` + +## 架构 + +### 前后端通信 +- 前端默认连接 `http://localhost:3001`（配置在 `frontend/src/config/index.ts` 的 `AIGC_PROXY_HOST`） +- 后端 FastAPI 入口：`backend/server.py` + +### 前端核心模块 +- **状态管理**: Redux Toolkit，两个 slice：`store/slices/room.ts`（房间状态）、`store/slices/device.ts`（设备状态） +- **RTC 封装**: `src/lib/RtcClient.ts` 封装 `@volcengine/rtc` SDK +- **API 层**: `src/app/api.ts` 定义 `getScenes`、`StartVoiceChat`、`StopVoiceChat` 接口 +- **页面结构**: `pages/MainPage/` 包含 Room（通话中）和 Antechamber（通话前）两个主要区域 +- **路径别名**: `@/` → `src/`（通过 craco + tsconfig paths 配置） +- **UI 组件库**: Arco Design +- **CSS**: LESS + +### 后端核心模块 +- **场景配置**: `config/custom_scene.py` — 从环境变量构建场景配置，自动生成 RoomId/UserId/Token +- **API 代理**: `/proxy` 端点转发请求到火山引擎 RTC OpenAPI（含请求签名） +- **LLM 集成**: `services/local_llm_service.py` — Ark SDK 对接，SSE 流式响应 +- **请求签名**: `security/signer.py` +- **Token 生成**: `security/rtc_token.py` + +### LLM 模式 +通过 `CUSTOM_LLM_MODE` 环境变量切换： +- `ArkV3`: 直接使用火山方舟 LLM +- `CustomLLM`: 自定义 LLM 回调（`/api/chat_callback` 端点） + +### 关键环境变量（backend/.env） +- `CUSTOM_ACCESS_KEY_ID` / `CUSTOM_SECRET_KEY`: 火山引擎凭证 +- `CUSTOM_RTC_APP_ID` / `CUSTOM_RTC_APP_KEY`: RTC 应用配置 +- `CUSTOM_LLM_MODE` + 对应 LLM 配置 +- `CUSTOM_ASR_APP_ID` / `CUSTOM_TTS_APP_ID`: 语音识别/合成配置 +- `CUSTOM_AVATAR_*`: 数字人配置（可选） diff --git a/README.md b/README.md index 2f66aba..ba4a3fc 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ # 交互式AIGC场景 AIGC Demo 此 Demo 为简化版本, 如您有 1.5.x 版本 UI 的诉求, 可切换至 1.5.1 分支。 -跑通阶段时, 无须关心代码实现，仅需按需完成 `backend/scenes/*.json` 的场景信息填充即可。 +跑通阶段时, 无须关心代码实现。当前推荐直接使用 `backend/.env` + `backend/config/custom_scene.py` 完成 `Custom` 场景配置。 ## 简介 - 在 AIGC 对话场景下，火山引擎 AIGC-RTC Server 云端服务，通过整合 RTC 音视频流处理，ASR 语音识别，大模型接口调用集成，以及 TTS 语音生成等能力，提供基于流式语音的端到端AIGC能力链路。 @@ -22,28 +22,66 @@ 开通 ASR、TTS、LLM、RTC 等服务，可参考 [开通服务](https://www.volcengine.com/docs/6348/1315561?s=g) 进行相关服务的授权与开通。 ### 3. 场景配置 -`backend/scenes/*.json` +当前真正生效的主配置入口是 `backend/.env` + `backend/config/custom_scene.py`。 您可以自定义具体场景, 并按需根据模版填充 `SceneConfig`、`AccountConfig`、`RTCConfig`、`VoiceChat` 中需要的参数。 -Demo 中以 `Custom` 场景为例，您可以自行新增场景。 +Demo 中以 `Custom` 场景为例，您也可以自行新增其他 JSON 场景。 + +`Custom` 场景建议先执行以下步骤： + +```shell +cp backend/.env.example backend/.env +``` 注意： - `SceneConfig`：场景的信息，例如名称、头像等。 -- `AccountConfig`：场景下的账号信息，https://console.volcengine.com/iam/keymanage/ 获取 AK/SK。 +- `AccountConfig`：`Custom` 场景默认从 `backend/.env` 读取 AK/SK，其他场景仍在 JSON 中配置。 - `RTCConfig`：场景下的 RTC 配置。 - AppId、AppKey 可从 https://console.volcengine.com/rtc/aigc/listRTC 中获取。 + - `Custom` 场景的 AppId、AppKey、RoomId、UserId、Token 可通过 `backend/.env` 注入。 - RoomId、UserId 可自定义也可不填，交由服务端生成。 - `VoiceChat`: 场景下的 AIGC 配置。 + - `Custom` 场景的 TaskId、Agent 用户信息、欢迎语、System Message 以及 LLM 模式参数均通过 `backend/.env` 注入。 + - 支持 `ArkV3` 与 `CustomLLM` 两种模式；`CustomLLM` 当前推荐“当前 backend 内置本地回调 + ngrok 暴露公网地址”这条接法。 - 可参考 https://www.volcengine.com/docs/6348/1558163 中参数描述，完整填写参数内容。 - - 可通过 [快速跑通 Demo](https://console.volcengine.com/rtc/aigc/run?s=g) 快速获取参数, 跑通后点击右上角 `接入 API` 按钮复制相关代码贴到 JSON 配置文件中即可。 + - `ASRConfig`、`TTSConfig`、`AvatarConfig` 等复杂结构由 `backend/config/custom_scene.py` 维护默认值，并从 `backend/.env` 读取关键运行参数。 + - 当前首版默认不启用 RAG 主链路，`backend/services/rag_service.py` 仅保留为后续扩展位。 + - 可通过 [快速跑通 Demo](https://console.volcengine.com/rtc/aigc/run?s=g) 快速获取参数，再分别填入 `backend/.env` 和 `backend/config/custom_scene.py` 的默认结构中。 + +### 第三方 CustomLLM 接入 + +如果你要把本地服务接成 `CustomLLM`，推荐直接让当前 `backend` 自己提供回调接口： + +```dotenv +CUSTOM_LLM_MODE=CustomLLM +CUSTOM_LLM_URL=http://127.0.0.1:3001/api/chat_callback +CUSTOM_LLM_MODEL_NAME=my-model +CUSTOM_LLM_API_KEY=your-callback-token +ARK_API_KEY=your-ark-api-key +ARK_ENDPOINT_ID=your-ark-endpoint-id +``` + +本地起好 `backend` 以后，用 `ngrok` 暴露 `3001` 端口，再把 `CUSTOM_LLM_URL` 改成公网地址： + +```dotenv +CUSTOM_LLM_URL=https://your-ngrok-domain.ngrok-free.app/api/chat_callback +``` + +说明： + +- `CUSTOM_LLM_URL` 是写进 `StartVoiceChat.LLMConfig.Url` 的地址 +- 默认可以先用本地地址启动服务，等 `ngrok` 跑起来后再改成公网 `https` 地址 +- 当前 backend 内置的固定回调路由是 `POST /api/chat_callback` +- `RTC_OPENAPI_VERSION` 默认使用 `2025-06-01` ## 快速开始 请注意，服务端和 Web 端都需要启动, 启动步骤如下: ### 后端服务（Python FastAPI） ```shell cd backend +cp .env.example .env uv sync -uv run uvicorn main:app --host 0.0.0.0 --port 3001 --reload +uv run uvicorn server:app --host 0.0.0.0 --port 3001 --reload ``` ### 前端页面 @@ -56,16 +94,16 @@ npm run dev ### 常见问题 | 问题 | 解决方案 | | :-- | :-- | -| 如何使用第三方模型、Coze Bot | 模型相关配置代码对应目录 `src/config/scenes/` 下json 文件，填写对应官方模型/ Coze/ 第三方模型的参数后，可点击页面上的 "修改 AI 人设" 进行切换。 | +| 如何使用第三方模型、Coze Bot | 当前主配置入口是 `backend/.env` + `backend/config/custom_scene.py`。如果接自己的模型，推荐使用当前 backend 内置的 `/api/chat_callback` 作为 `CustomLLM` 回调接口，再通过 `ngrok` 暴露公网地址，并把它填到 `CUSTOM_LLM_URL`。 | | **启动智能体之后, 对话无反馈，或者一直停留在 "AI 准备中, 请稍侯"；在启用数字人的情况下，一直停留在“数字人准备中，请稍候”** |
  • 可能因为控制台中相关权限没有正常授予，请参考[流程](https://www.volcengine.com/docs/6348/1315561?s=g)再次确认下是否完成相关操作。此问题的可能性较大，建议仔细对照是否已经将相应的权限开通。
  • 参数传递可能有问题, 例如参数大小写、类型等问题，请再次确认下这类型问题是否存在。
  • 相关资源可能未开通或者用量不足/欠费，请再次确认。
  • **请检查当前使用的模型 ID / 数字人 AppId / Token 等内容都是正确且可用的。**
  • 数字人服务有并发限制，当达到并发限制时，同样会表现为一直停留在“数字人准备中”状态
    • | | **浏览器报了 `Uncaught (in promise) r: token_error` 错误** | 请检查您填在项目中的 RTC Token 是否合法，检测用于生成 Token 的 UserId、RoomId 以及 Token 本身是否与项目中填写的一致；或者 Token 可能过期, 可尝试重新生成下。 | | **[StartVoiceChat]Failed(Reason: The task has been started. Please do not call the startup task interface repeatedly.)** 报错 | 如果设置的 RoomId、UserId 为固定值，重复调用 startAgent 会导致出错，只需先调用 stopAgent 后再重新 startAgent 即可。 | | 为什么麦克风、摄像头开启失败？浏览器报了`TypeError: Cannot read properties of undefined (reading 'getUserMedia')` | 检查当前页面是否为[安全上下文](https://developer.mozilla.org/zh-CN/docs/Web/Security/Secure_Contexts)（简单来说，检查当前页面是否为 `localhost` 或者 是否为 https 协议）。浏览器[限制](https://developer.mozilla.org/zh-CN/docs/Web/Security/Secure_Contexts/features_restricted_to_secure_contexts) `getUserMedia` 只能在安全上下文中使用。 | | 为什么我的麦克风正常、摄像头也正常，但是设备没有正常工作? | 可能是设备权限未授予，详情可参考 [Web 排查设备权限获取失败问题](https://www.volcengine.com/docs/6348/1356355?s=g)。 | -| 接口调用时, 返回 "Invalid 'Authorization' header, Pls check your authorization header" 错误 | `backend/scenes/*.json` 中的 AK/SK 不正确 | +| 接口调用时, 返回 "Invalid 'Authorization' header, Pls check your authorization header" 错误 | `Custom` 场景请检查 `backend/.env` 中的 `CUSTOM_ACCESS_KEY_ID` / `CUSTOM_SECRET_KEY`；其他场景请检查对应 `backend/scenes/*.json` 中的 AK/SK | | 什么是 RTC | **R**eal **T**ime **C**ommunication, RTC 的概念可参考[官网文档](https://www.volcengine.com/docs/6348/66812?s=g)。 | | 不清楚什么是主账号，什么是子账号 | 可以参考[官方概念](https://www.volcengine.com/docs/6257/64963?hyperlink_open_type=lark.open_in_browser&s=g) 。| -| 我有自己的服务端了, 我应该怎么让前端调用我的服务端呢 | 修改 `src/config/index.ts` 中的 `AIGC_PROXY_HOST` 请求域名和接口并在 `src/app/api.ts` 中修改接口参数配置 `APIS_CONFIG` | +| 我有自己的服务端了, 我应该怎么让前端调用我的服务端呢 | 修改 `frontend/src/config/index.ts` 中的 `AIGC_PROXY_HOST` 请求域名；如需同步调整接口路由，可再看 `frontend/src/app/api.ts` 里的 `BasicAPIs` / `AigcAPIs` | 如果有上述以外的问题，欢迎联系我们反馈。 @@ -97,4 +135,4 @@ npm run dev - 更新 UI 和参数配置方式 - 更新 Readme 文档 - 追加 Node 服务的参数检测能力 - - 追加 Node 服务的 Token 生成能力 \ No newline at end of file + - 追加 Node 服务的 Token 生成能力 diff --git a/backend/.env.example b/backend/.env.example new file mode 100644 index 0000000..4635521 --- /dev/null +++ b/backend/.env.example @@ -0,0 +1,84 @@ +# RTC OpenAPI 版本 +RTC_OPENAPI_VERSION=2025-06-01 + +# Custom 场景基础配置 +CUSTOM_ACCESS_KEY_ID=your-access-key-id +CUSTOM_SECRET_KEY=your-secret-key +CUSTOM_RTC_APP_ID=your-rtc-app-id +CUSTOM_RTC_APP_KEY= + +# 留空时由服务端自动生成 RoomId / UserId / Token +CUSTOM_RTC_ROOM_ID= +CUSTOM_RTC_USER_ID= +CUSTOM_RTC_TOKEN= + +# Custom 场景业务配置 +CUSTOM_TASK_ID=your-task-id +CUSTOM_AGENT_USER_ID=your-agent-user-id +CUSTOM_AGENT_TARGET_USER_ID= +CUSTOM_AGENT_WELCOME_MESSAGE=你好，我是小乖，有什么需要帮忙的吗？ +CUSTOM_SCENE_NAME=自定义助手 +CUSTOM_SCENE_ICON=https://lf3-rtc-demo.volccdn.com/obj/rtc-aigc-assets/DoubaoAvatar.png +CUSTOM_INTERRUPT_MODE=0 + +# LLM 公共配置 +CUSTOM_LLM_MODE=ArkV3 +CUSTOM_LLM_SYSTEM_MESSAGE=你是小乖，性格幽默又善解人意。你在表达时需简明扼要，有自己的观点。 +CUSTOM_LLM_VISION_ENABLE=false +CUSTOM_LLM_THINKING_TYPE=disabled + +# ArkV3 模式 +CUSTOM_LLM_ENDPOINT_ID=your-ark-endpoint-id + +# CustomLLM 模式 +# 本地调试时，可先保持默认本地回调地址。 +# 等 ngrok 跑起来后，再把 CUSTOM_LLM_URL 改成公网 https 地址，例如： +# https://your-ngrok-domain.ngrok-free.app/api/chat_callback +CUSTOM_LLM_URL=http://127.0.0.1:3001/api/chat_callback +# 火山调用当前 backend 的 /api/chat_callback 时使用的 Bearer Token，可留空 +CUSTOM_LLM_API_KEY= +CUSTOM_LLM_MODEL_NAME= +CUSTOM_LLM_HISTORY_LENGTH= +CUSTOM_LLM_PREFILL= +CUSTOM_LLM_CUSTOM= +CUSTOM_LLM_EXTRA_HEADER_JSON= +CUSTOM_LLM_ENABLE_PARALLEL_TOOL_CALLS= +CUSTOM_LLM_TEMPERATURE= +CUSTOM_LLM_TOP_P= +CUSTOM_LLM_MAX_TOKENS= + +# 当前 backend 内置的本地 Ark 回调配置 +# /api/chat_callback 会直接使用这组配置调用方舟 +ARK_API_KEY= +ARK_ENDPOINT_ID= +ARK_BASE_URL=https://ark.cn-beijing.volces.com/api/v3 +ARK_TIMEOUT_SECONDS=1800 +LOCAL_LLM_SYSTEM_PROMPT= "你是一个测试助手。如果别人问你是谁，你就说你是哈哈哈。" +LOCAL_LLM_TEMPERATURE=0.3 + +# 可选 RAG 占位配置 +# 当前首版默认未启用主链路 RAG，如需后续接入，可再填写这两个配置 +RAG_STATIC_CONTEXT= +RAG_CONTEXT_FILE= + +# ASR / TTS +CUSTOM_ASR_APP_ID=your-asr-app-id +CUSTOM_TTS_APP_ID=your-tts-app-id +CUSTOM_ASR_PROVIDER=volcano +CUSTOM_ASR_MODE=smallmodel +CUSTOM_ASR_CLUSTER=volcengine_streaming_common +CUSTOM_TTS_PROVIDER=volcano +CUSTOM_TTS_CLUSTER=volcano_tts +CUSTOM_TTS_VOICE_TYPE=BV001_streaming +CUSTOM_TTS_SPEED_RATIO=1 +CUSTOM_TTS_PITCH_RATIO=1 +CUSTOM_TTS_VOLUME_RATIO=1 + +# 数字人配置 +CUSTOM_AVATAR_ENABLED=false +CUSTOM_AVATAR_TYPE=3min +CUSTOM_AVATAR_ROLE=250623-zhibo-linyunzhi +CUSTOM_AVATAR_BACKGROUND_URL= +CUSTOM_AVATAR_VIDEO_BITRATE=2000 +CUSTOM_AVATAR_APP_ID= +CUSTOM_AVATAR_TOKEN= diff --git a/backend/README.md b/backend/README.md index aa7991d..fc1d380 100644 --- a/backend/README.md +++ b/backend/README.md @@ -1,6 +1,10 @@ -# AIGC Backend (Python FastAPI) +# AIGC Backend（Python FastAPI） -原 Node.js + Koa 服务的 Python 重写版本，使用 FastAPI 框架。 +这是当前 Demo 的后端服务，负责三件事： + +- 根据 `backend/.env` 与 `backend/config/custom_scene.py` 构建 `Custom` 场景配置 +- 代理调用火山 RTC OpenAPI +- 在同一个 FastAPI 进程里提供本地 `CustomLLM` 回调接口 `/api/chat_callback` ## 环境要求 @@ -12,38 +16,175 @@ uv sync ``` -## 场景配置 - -编辑 `scenes/*.json`，填写以下字段： - -| 字段 | 说明 | -|------|------| -| `AccountConfig.accessKeyId` | 火山引擎 AK，从 https://console.volcengine.com/iam/keymanage/ 获取 | -| `AccountConfig.secretKey` | 火山引擎 SK | -| `RTCConfig.AppId` | RTC 应用 ID | -| `RTCConfig.AppKey` | RTC 应用 Key（用于自动生成 Token） | -| `VoiceChat.*` | AIGC 相关配置，参考 https://www.volcengine.com/docs/6348/1558163 | - -## 启动服务 +## 启动方式 ```shell -uvicorn main:app --host 0.0.0.0 --port 3001 --reload +uv run uvicorn server:app --host 0.0.0.0 --port 3001 --reload ``` -服务启动后监听 `http://localhost:3001`。 +服务默认监听 `http://localhost:3001`。 + +## 配置方式 + +`Custom` 场景固定使用： + +- `backend/.env` +- `backend/config/custom_scene.py` + +不再依赖 `backend/scenes/Custom.json`。 + +先复制示例配置： + +```shell +cp .env.example .env +``` + +### 必填基础配置 + +| 变量名 | 说明 | +| --- | --- | +| `CUSTOM_ACCESS_KEY_ID` | 火山引擎 AK | +| `CUSTOM_SECRET_KEY` | 火山引擎 SK | +| `CUSTOM_RTC_APP_ID` | RTC 应用 ID，同时作为 `RTCConfig.AppId` 和 `VoiceChat.AppId` | +| `CUSTOM_TASK_ID` | AIGC 任务 ID | +| `CUSTOM_AGENT_USER_ID` | 智能体用户 ID | +| `CUSTOM_AGENT_WELCOME_MESSAGE` | 智能体欢迎语 | +| `CUSTOM_LLM_SYSTEM_MESSAGE` | System Message | +| `CUSTOM_ASR_APP_ID` | ASR 应用 ID | +| `CUSTOM_TTS_APP_ID` | TTS 应用 ID | + +### RTC 相关配置 + +| 变量名 | 说明 | +| --- | --- | +| `CUSTOM_RTC_APP_KEY` | 未提供 `CUSTOM_RTC_TOKEN` 时，用于自动生成 Token | +| `CUSTOM_RTC_ROOM_ID` | 房间 ID，留空时服务端自动生成 | +| `CUSTOM_RTC_USER_ID` | 用户 ID，留空时服务端自动生成 | +| `CUSTOM_RTC_TOKEN` | RTC Token；留空时服务端会自动生成 | +| `RTC_OPENAPI_VERSION` | `StartVoiceChat/StopVoiceChat` 使用的 OpenAPI 版本，默认 `2025-06-01` | + +### LLM 模式一：ArkV3 + +```dotenv +CUSTOM_LLM_MODE=ArkV3 +CUSTOM_LLM_ENDPOINT_ID=your-ark-endpoint-id +``` + +### LLM 模式二：CustomLLM 本地回调 + +这个模式不是再起一个额外代理服务，而是直接由当前 `backend` 自己对外提供回调接口： + +```dotenv +CUSTOM_LLM_MODE=CustomLLM +CUSTOM_LLM_URL=http://127.0.0.1:3001/api/chat_callback +CUSTOM_LLM_API_KEY=your-callback-token +CUSTOM_LLM_MODEL_NAME=my-model +``` + +推荐调试流程： + +1. 先启动当前 `backend` +2. 用 `ngrok` 暴露 `3001` 端口 +3. 把 `CUSTOM_LLM_URL` 改成公网地址，例如： + +```dotenv +CUSTOM_LLM_URL=https://your-ngrok-domain.ngrok-free.app/api/chat_callback +``` + +`CUSTOM_LLM_API_KEY` 是火山调用你这个本地回调接口时带上的 Bearer Token；如果你不需要这层鉴权，可以留空。 + +### 当前 backend 内置的 Ark 配置 + +`/api/chat_callback` 内部会直接调用方舟 SDK，因此还需要： + +```dotenv +ARK_API_KEY=your-ark-api-key +ARK_ENDPOINT_ID=your-ark-endpoint-id +ARK_BASE_URL=https://ark.cn-beijing.volces.com/api/v3 +ARK_TIMEOUT_SECONDS=1800 +LOCAL_LLM_SYSTEM_PROMPT= +LOCAL_LLM_TEMPERATURE=0.3 +``` + +如果 `LOCAL_LLM_SYSTEM_PROMPT` 留空，会回退使用 `CUSTOM_LLM_SYSTEM_MESSAGE`。 + +### 可选 RAG 占位配置 + +当前仓库内置了一个最小 RAG 占位实现，但首版默认不接入主链路，支持两种输入来源： + +```dotenv +RAG_STATIC_CONTEXT= +RAG_CONTEXT_FILE= +``` + +- `RAG_STATIC_CONTEXT`：直接写死一段知识文本 +- `RAG_CONTEXT_FILE`：从本地文件读取全文作为知识上下文 + +后续如果你要接真实向量检索，直接替换 `services/rag_service.py` 里的 `retrieve`，再把 `server.py` 主链路接回去即可。 + +### CustomLLM 可选参数 + +| 变量名 | 说明 | +| --- | --- | +| `CUSTOM_LLM_HISTORY_LENGTH` | 历史轮数 | +| `CUSTOM_LLM_PREFILL` | 是否开启 Prefill | +| `CUSTOM_LLM_CUSTOM` | 透传到请求体的 `custom` 字段 | +| `CUSTOM_LLM_EXTRA_HEADER_JSON` | 额外请求头，JSON 对象字符串 | +| `CUSTOM_LLM_ENABLE_PARALLEL_TOOL_CALLS` | 是否开启并行工具调用 | +| `CUSTOM_LLM_TEMPERATURE` | 透传温度参数 | +| `CUSTOM_LLM_TOP_P` | 透传 `top_p` | +| `CUSTOM_LLM_MAX_TOKENS` | 透传 `max_tokens` | + +其余 ASR、TTS、数字人相关可选字段，请直接参考 `backend/.env.example`。 ## 接口说明 -### POST /getScenes +### `POST /getScenes` -返回所有场景列表，自动生成 RoomId/UserId/Token（若未在 JSON 中配置）。 +返回场景列表，并自动补齐： -### POST /proxy?Action={Action}&Version={Version} +- `RoomId` +- `UserId` +- `Token` -代理转发至火山引擎 RTC OpenAPI。 +### `POST /proxy?Action={Action}&Version={Version}` -支持的 Action： -- `StartVoiceChat` — 启动语音对话 -- `StopVoiceChat` — 停止语音对话 +代理转发到火山 RTC OpenAPI。 -请求体需包含 `SceneID` 字段，对应 `scenes/` 目录下的 JSON 文件名（不含扩展名）。 +支持： + +- `StartVoiceChat` +- `StopVoiceChat` + +请求体必须包含 `SceneID`。 + +版本优先级如下： + +1. 查询参数里的 `Version` +2. 环境变量 `RTC_OPENAPI_VERSION` +3. 默认值 `2025-06-01` + +### `POST /api/chat_callback` + +这是当前 backend 内置的 `CustomLLM` 回调接口，也是你配置给火山 `LLMConfig.Url` 的目标地址。 + +行为说明： + +- 接收火山传入的 `messages` +- 可选校验 `Authorization: Bearer ` +- 内部调用 `services/local_llm_service.py` 里的 Ark SDK +- 按火山要求返回 `text/event-stream` +- 结束时一定补 `data: [DONE]` + +### `POST /debug/chat` + +本地调试 LLM 文本流，不经过 RTC。 + +### `GET /debug/rag?query=...` + +本地调试 RAG 返回结果。 + +## 说明 + +- 当前前端不会直接决定模型供应商，模型切换统一由后端环境变量控制。 +- 如果缺少关键 `CUSTOM_*` 或 `ARK_*` 配置，服务会在启动阶段直接报错，而不是进入半可用状态。 diff --git a/backend/config/__init__.py b/backend/config/__init__.py new file mode 100644 index 0000000..39c20fe --- /dev/null +++ b/backend/config/__init__.py @@ -0,0 +1 @@ +"""Backend config package.""" diff --git a/backend/config/custom_scene.py b/backend/config/custom_scene.py new file mode 100644 index 0000000..925c0ae --- /dev/null +++ b/backend/config/custom_scene.py @@ -0,0 +1,225 @@ +""" +Copyright 2025 Beijing Volcano Engine Technology Co., Ltd. All Rights Reserved. +SPDX-license-identifier: BSD-3-Clause +""" + +from typing import Any + +from utils.env import ( + env_bool, + env_int, + env_json_object, + env_list, + env_number, + env_optional_bool, + env_optional_int, + env_optional_number, + env_str, + require_env, + set_if_present, +) + +CUSTOM_SCENE_ID = "Custom" + +DEFAULT_SCENE_NAME = "自定义助手" +DEFAULT_SCENE_ICON = ( + "https://lf3-rtc-demo.volccdn.com/obj/rtc-aigc-assets/DoubaoAvatar.png" +) +DEFAULT_LLM_MODE = "ArkV3" +DEFAULT_LLM_THINKING_TYPE = "disabled" +DEFAULT_RTC_OPENAPI_VERSION = "2025-06-01" +DEFAULT_CUSTOM_LLM_CALLBACK_URL = "http://127.0.0.1:3001/api/chat_callback" +SUPPORTED_LLM_MODES = {"ArkV3", "CustomLLM"} +DEFAULT_ASR_PROVIDER = "volcano" +DEFAULT_ASR_MODE = "smallmodel" +DEFAULT_ASR_CLUSTER = "volcengine_streaming_common" +DEFAULT_TTS_PROVIDER = "volcano" +DEFAULT_TTS_CLUSTER = "volcano_tts" +DEFAULT_TTS_VOICE_TYPE = "BV001_streaming" +DEFAULT_AVATAR_TYPE = "3min" +DEFAULT_AVATAR_ROLE = "250623-zhibo-linyunzhi" +DEFAULT_AVATAR_VIDEO_BITRATE = 2000 + + +def get_rtc_openapi_version() -> str: + return env_str("RTC_OPENAPI_VERSION", DEFAULT_RTC_OPENAPI_VERSION) + + +def build_llm_settings_from_env(missing: list[str]) -> dict[str, Any]: + llm_mode = env_str("CUSTOM_LLM_MODE", DEFAULT_LLM_MODE) + if llm_mode not in SUPPORTED_LLM_MODES: + modes = ", ".join(sorted(SUPPORTED_LLM_MODES)) + raise ValueError(f"CUSTOM_LLM_MODE 仅支持以下取值: {modes}") + + settings = { + "mode": llm_mode, + "system_message": require_env("CUSTOM_LLM_SYSTEM_MESSAGE", missing), + "vision_enable": env_bool("CUSTOM_LLM_VISION_ENABLE", False), + "thinking_type": env_str( + "CUSTOM_LLM_THINKING_TYPE", DEFAULT_LLM_THINKING_TYPE + ), + "api_key": env_str("CUSTOM_LLM_API_KEY"), + "model_name": env_str("CUSTOM_LLM_MODEL_NAME"), + "history_length": env_optional_int("CUSTOM_LLM_HISTORY_LENGTH"), + "prefill": env_optional_bool("CUSTOM_LLM_PREFILL"), + "custom": env_str("CUSTOM_LLM_CUSTOM"), + "extra_header": env_json_object("CUSTOM_LLM_EXTRA_HEADER_JSON"), + "enable_parallel_tool_calls": env_optional_bool( + "CUSTOM_LLM_ENABLE_PARALLEL_TOOL_CALLS" + ), + "temperature": env_optional_number("CUSTOM_LLM_TEMPERATURE"), + "top_p": env_optional_number("CUSTOM_LLM_TOP_P"), + "max_tokens": env_optional_int("CUSTOM_LLM_MAX_TOKENS"), + } + + if llm_mode == "ArkV3": + settings["endpoint_id"] = require_env("CUSTOM_LLM_ENDPOINT_ID", missing) + return settings + + settings["url"] = env_str("CUSTOM_LLM_URL", DEFAULT_CUSTOM_LLM_CALLBACK_URL) + settings["endpoint_id"] = env_str("CUSTOM_LLM_ENDPOINT_ID") + require_env("ARK_API_KEY", missing) + require_env("ARK_ENDPOINT_ID", missing) + + return settings + + +def build_llm_config(llm_settings: dict[str, Any]) -> dict[str, Any]: + llm_config = { + "Mode": llm_settings["mode"], + "SystemMessages": [llm_settings["system_message"]], + "VisionConfig": { + "Enable": llm_settings["vision_enable"], + }, + } + + if llm_settings["mode"] == "ArkV3": + llm_config["EndPointId"] = llm_settings["endpoint_id"] + llm_config["ThinkingType"] = llm_settings["thinking_type"] + return llm_config + + llm_config["Url"] = llm_settings["url"] + + if llm_settings["api_key"]: + llm_config["APIKey"] = llm_settings["api_key"] + + optional_fields = { + "ModelName": llm_settings["model_name"], + "HistoryLength": llm_settings["history_length"], + "Prefill": llm_settings["prefill"], + "Custom": llm_settings["custom"], + "ExtraHeader": llm_settings["extra_header"], + "EnableParallelToolCalls": llm_settings["enable_parallel_tool_calls"], + "Temperature": llm_settings["temperature"], + "TopP": llm_settings["top_p"], + "MaxTokens": llm_settings["max_tokens"], + } + for key, value in optional_fields.items(): + set_if_present(llm_config, key, value) + + return llm_config + + +def build_custom_scene_from_env() -> dict[str, Any]: + missing: list[str] = [] + + access_key_id = require_env("CUSTOM_ACCESS_KEY_ID", missing) + secret_key = require_env("CUSTOM_SECRET_KEY", missing) + rtc_app_id = require_env("CUSTOM_RTC_APP_ID", missing) + task_id = require_env("CUSTOM_TASK_ID", missing) + agent_user_id = require_env("CUSTOM_AGENT_USER_ID", missing) + welcome_message = require_env("CUSTOM_AGENT_WELCOME_MESSAGE", missing) + asr_app_id = require_env("CUSTOM_ASR_APP_ID", missing) + tts_app_id = require_env("CUSTOM_TTS_APP_ID", missing) + llm_settings = build_llm_settings_from_env(missing) + + rtc_app_key = env_str("CUSTOM_RTC_APP_KEY") + rtc_room_id = env_str("CUSTOM_RTC_ROOM_ID") + rtc_user_id = env_str("CUSTOM_RTC_USER_ID") + rtc_token = env_str("CUSTOM_RTC_TOKEN") + + if not rtc_token and not rtc_app_key: + missing.append("CUSTOM_RTC_APP_KEY") + + if missing: + missing_str = ", ".join(dict.fromkeys(missing)) + raise ValueError(f"Custom 场景缺少以下环境变量: {missing_str}") + + interrupt_mode = env_int("CUSTOM_INTERRUPT_MODE", 0) + avatar_enabled = env_bool("CUSTOM_AVATAR_ENABLED", False) + + target_user_ids = env_list("CUSTOM_AGENT_TARGET_USER_ID") + if not target_user_ids: + target_user_ids = [rtc_user_id or ""] + + return { + "SceneConfig": { + "icon": env_str("CUSTOM_SCENE_ICON", DEFAULT_SCENE_ICON), + "name": env_str("CUSTOM_SCENE_NAME", DEFAULT_SCENE_NAME), + }, + "AccountConfig": { + "accessKeyId": access_key_id, + "secretKey": secret_key, + }, + "RTCConfig": { + "AppId": rtc_app_id, + "AppKey": rtc_app_key, + "RoomId": rtc_room_id, + "UserId": rtc_user_id, + "Token": rtc_token, + }, + "VoiceChat": { + "AppId": rtc_app_id, + "RoomId": rtc_room_id, + "TaskId": task_id, + "AgentConfig": { + "TargetUserId": target_user_ids, + "WelcomeMessage": welcome_message, + "UserId": agent_user_id, + "EnableConversationStateCallback": True, + }, + "Config": { + "ASRConfig": { + "Provider": env_str("CUSTOM_ASR_PROVIDER", DEFAULT_ASR_PROVIDER), + "ProviderParams": { + "Mode": env_str("CUSTOM_ASR_MODE", DEFAULT_ASR_MODE), + "AppId": asr_app_id, + "Cluster": env_str("CUSTOM_ASR_CLUSTER", DEFAULT_ASR_CLUSTER), + }, + }, + "TTSConfig": { + "Provider": env_str("CUSTOM_TTS_PROVIDER", DEFAULT_TTS_PROVIDER), + "ProviderParams": { + "app": { + "appid": tts_app_id, + "cluster": env_str( + "CUSTOM_TTS_CLUSTER", DEFAULT_TTS_CLUSTER + ), + }, + "audio": { + "voice_type": env_str( + "CUSTOM_TTS_VOICE_TYPE", DEFAULT_TTS_VOICE_TYPE + ), + "speed_ratio": env_number("CUSTOM_TTS_SPEED_RATIO", 1), + "pitch_ratio": env_number("CUSTOM_TTS_PITCH_RATIO", 1), + "volume_ratio": env_number("CUSTOM_TTS_VOLUME_RATIO", 1), + }, + }, + }, + "LLMConfig": build_llm_config(llm_settings), + "InterruptMode": interrupt_mode, + }, + "AvatarConfig": { + "Enabled": avatar_enabled, + "AvatarType": env_str("CUSTOM_AVATAR_TYPE", DEFAULT_AVATAR_TYPE), + "AvatarRole": env_str("CUSTOM_AVATAR_ROLE", DEFAULT_AVATAR_ROLE), + "BackgroundUrl": env_str("CUSTOM_AVATAR_BACKGROUND_URL"), + "VideoBitrate": env_int( + "CUSTOM_AVATAR_VIDEO_BITRATE", DEFAULT_AVATAR_VIDEO_BITRATE + ), + "AvatarAppID": env_str("CUSTOM_AVATAR_APP_ID"), + "AvatarToken": env_str("CUSTOM_AVATAR_TOKEN"), + }, + "InterruptMode": interrupt_mode, + }, + } diff --git a/backend/main.py b/backend/main.py index 0e817f2..2b0aac5 100644 --- a/backend/main.py +++ b/backend/main.py @@ -1,225 +1,14 @@ """ -Copyright 2025 Beijing Volcano Engine Technology Co., Ltd. All Rights Reserved. -SPDX-license-identifier: BSD-3-Clause +兼容入口。 -FastAPI backend — migrated from Server/app.js (Node.js + Koa) +推荐使用: + uv run uvicorn server:app --host 0.0.0.0 --port 3001 --reload """ -import json -import os -import time -import uuid -from pathlib import Path - -import httpx -from fastapi import FastAPI, Request -from fastapi.middleware.cors import CORSMiddleware -from fastapi.responses import JSONResponse - -from signer import Signer -from rtc_token import AccessToken, privileges - -app = FastAPI() - -app.add_middleware( - CORSMiddleware, - allow_origins=["*"], - allow_methods=["*"], - allow_headers=["*"], -) - -SCENES_DIR = Path(__file__).parent / "scenes" - - -def load_scenes() -> dict: - scenes = {} - for p in SCENES_DIR.glob("*.json"): - with open(p, encoding="utf-8") as f: - scenes[p.stem] = json.load(f) - return scenes - - -Scenes = load_scenes() - - -def assert_value(value, msg: str): - if not value or (isinstance(value, str) and " " in value): - raise ValueError(msg) - - -def error_response(action: str, message: str): - return JSONResponse( - { - "ResponseMetadata": { - "Action": action, - "Error": {"Code": -1, "Message": message}, - } - } - ) - - -@app.post("/proxy") -async def proxy(request: Request): - action = request.query_params.get("Action", "") - version = request.query_params.get("Version", "2024-12-01") - - try: - assert_value(action, "Action 不能为空") - assert_value(version, "Version 不能为空") - - body = await request.json() - scene_id = body.get("SceneID", "") - assert_value(scene_id, "SceneID 不能为空，SceneID 用于指定场景的 JSON") - - json_data = Scenes.get(scene_id) - if not json_data: - raise ValueError( - f"{scene_id} 不存在，请先在 backend/scenes 下定义该场景的 JSON." - ) - - voice_chat = json_data.get("VoiceChat", {}) - account_config = json_data.get("AccountConfig", {}) - assert_value( - account_config.get("accessKeyId"), "AccountConfig.accessKeyId 不能为空" - ) - assert_value( - account_config.get("secretKey"), "AccountConfig.secretKey 不能为空" - ) - - if action == "StartVoiceChat": - req_body = voice_chat - elif action == "StopVoiceChat": - app_id = voice_chat.get("AppId", "") - room_id = voice_chat.get("RoomId", "") - task_id = voice_chat.get("TaskId", "") - assert_value(app_id, "VoiceChat.AppId 不能为空") - assert_value(room_id, "VoiceChat.RoomId 不能为空") - assert_value(task_id, "VoiceChat.TaskId 不能为空") - req_body = {"AppId": app_id, "RoomId": room_id, "TaskId": task_id} - else: - req_body = {} - - request_data = { - "region": "cn-north-1", - "method": "POST", - "params": {"Action": action, "Version": version}, - "headers": { - "Host": "rtc.volcengineapi.com", - "Content-type": "application/json", - }, - "body": req_body, - } - signer = Signer(request_data, "rtc") - signer.add_authorization(account_config) - - async with httpx.AsyncClient() as client: - resp = await client.post( - f"https://rtc.volcengineapi.com?Action={action}&Version={version}", - headers=request_data["headers"], - json=req_body, - ) - return JSONResponse(resp.json()) - - except ValueError as e: - return error_response(action, str(e)) - except Exception as e: - return error_response(action, str(e)) - - -@app.post("/getScenes") -async def get_scenes(): - try: - scenes_list = [] - for scene_name, data in Scenes.items(): - scene_config = data.get("SceneConfig", {}) - rtc_config = data.get("RTCConfig", {}) - voice_chat = data.get("VoiceChat", {}) - - app_id = rtc_config.get("AppId", "") - assert_value(app_id, f"{scene_name} 场景的 RTCConfig.AppId 不能为空") - - token = rtc_config.get("Token", "") - user_id = rtc_config.get("UserId", "") - room_id = rtc_config.get("RoomId", "") - app_key = rtc_config.get("AppKey", "") - - if app_id and (not token or not user_id or not room_id): - rtc_config["RoomId"] = voice_chat["RoomId"] = room_id or str( - uuid.uuid4() - ) - rtc_config["UserId"] = user_id = user_id or str(uuid.uuid4()) - if voice_chat.get("AgentConfig") and voice_chat["AgentConfig"].get( - "TargetUserId" - ): - voice_chat["AgentConfig"]["TargetUserId"][0] = rtc_config["UserId"] - - assert_value( - app_key, f"自动生成 Token 时，{scene_name} 场景的 AppKey 不可为空" - ) - key = AccessToken( - app_id, app_key, rtc_config["RoomId"], rtc_config["UserId"] - ) - key.add_privilege(privileges["PrivSubscribeStream"], 0) - key.add_privilege(privileges["PrivPublishStream"], 0) - key.expire_time(int(time.time()) + 24 * 3600) - rtc_config["Token"] = key.serialize() - - scene_config["id"] = scene_name - scene_config["botName"] = voice_chat.get("AgentConfig", {}).get("UserId") - scene_config["isInterruptMode"] = ( - voice_chat.get("Config", {}).get("InterruptMode") == 0 - ) - scene_config["isVision"] = ( - voice_chat.get("Config", {}) - .get("LLMConfig", {}) - .get("VisionConfig", {}) - .get("Enable") - ) - scene_config["isScreenMode"] = ( - voice_chat.get("Config", {}) - .get("LLMConfig", {}) - .get("VisionConfig", {}) - .get("SnapshotConfig", {}) - .get("StreamType") - == 1 - ) - scene_config["isAvatarScene"] = ( - voice_chat.get("Config", {}).get("AvatarConfig", {}).get("Enabled") - ) - scene_config["avatarBgUrl"] = ( - voice_chat.get("Config", {}) - .get("AvatarConfig", {}) - .get("BackgroundUrl") - ) - - rtc_out = {k: v for k, v in rtc_config.items() if k != "AppKey"} - - scenes_list.append( - { - "scene": scene_config, - "rtc": rtc_out, - } - ) - - return JSONResponse( - { - "ResponseMetadata": {"Action": "getScenes"}, - "Result": {"scenes": scenes_list}, - } - ) - - except ValueError as e: - return JSONResponse( - { - "ResponseMetadata": { - "Action": "getScenes", - "Error": {"Code": -1, "Message": str(e)}, - } - } - ) +from server import app if __name__ == "__main__": import uvicorn - uvicorn.run("main:app", host="0.0.0.0", port=3001, reload=True) + uvicorn.run("server:app", host="0.0.0.0", port=3001, reload=True) diff --git a/backend/pyproject.toml b/backend/pyproject.toml index 1c7ed70..81637c6 100644 --- a/backend/pyproject.toml +++ b/backend/pyproject.toml @@ -7,7 +7,9 @@ dependencies = [ "fastapi>=0.110.0", "uvicorn[standard]>=0.29.0", "httpx>=0.27.0", + "python-dotenv>=1.2.2", "python-multipart>=0.0.9", + "volcengine-python-sdk[ark]>=4.0.6", ] [tool.uv] diff --git a/backend/routes/__init__.py b/backend/routes/__init__.py new file mode 100644 index 0000000..b414d7c --- /dev/null +++ b/backend/routes/__init__.py @@ -0,0 +1 @@ +"""路由模块""" diff --git a/backend/routes/chat_callback.py b/backend/routes/chat_callback.py new file mode 100644 index 0000000..cde9176 --- /dev/null +++ b/backend/routes/chat_callback.py @@ -0,0 +1,108 @@ +""" +POST /api/chat_callback — 自定义 LLM 回调（SSE 流式响应） +""" + +import json + +from fastapi import APIRouter, Request +from fastapi.responses import StreamingResponse + +from services.local_llm_service import local_llm_service +from services.scene_service import ensure_custom_llm_authorized, get_custom_llm_callback_settings +from utils.responses import custom_llm_error_response + +router = APIRouter() + + +@router.post("/api/chat_callback") +async def chat_callback(request: Request): + try: + settings = get_custom_llm_callback_settings() + ensure_custom_llm_authorized(request, settings["api_key"]) + payload = await request.json() + except PermissionError as exc: + return custom_llm_error_response( + str(exc), + code="AuthenticationError", + status_code=401, + ) + except json.JSONDecodeError: + return custom_llm_error_response( + "请求体必须是合法的 JSON", + code="BadRequest", + status_code=400, + ) + except ValueError as exc: + return custom_llm_error_response(str(exc)) + except Exception as exc: + return custom_llm_error_response( + f"解析请求失败: {exc}", + code="InternalError", + status_code=500, + ) + + messages = payload.get("messages") + if not isinstance(messages, list) or not messages: + return custom_llm_error_response( + "messages 不能为空", + code="BadRequest", + status_code=400, + ) + + last_message = messages[-1] + if last_message.get("role") != "user": + return custom_llm_error_response( + "最后一条消息必须是用户消息", + code="BadRequest", + status_code=400, + ) + + try: + stream_iterator = local_llm_service.chat_stream( + history_messages=messages, + request_options={ + "temperature": payload.get("temperature"), + "max_tokens": payload.get("max_tokens"), + "top_p": payload.get("top_p"), + }, + ) + except Exception as exc: + return custom_llm_error_response( + f"初始化本地 LLM 流式调用失败: {exc}", + code="InternalError", + status_code=500, + ) + + def generate_sse(): + has_error = False + try: + for chunk in stream_iterator: + if chunk is None: + continue + + if hasattr(chunk, "model_dump_json"): + chunk_json = chunk.model_dump_json() + else: + chunk_json = json.dumps(chunk, ensure_ascii=False) + yield f"data: {chunk_json}\n\n" + except GeneratorExit: + raise + except Exception as exc: + has_error = True + print(f"❌ /api/chat_callback 流式输出失败: {exc}") + + if has_error: + print("⚠️ 已提前结束当前 SSE 流") + + yield "data: [DONE]\n\n" + + return StreamingResponse( + generate_sse(), + status_code=200, + media_type="text/event-stream", + headers={ + "Cache-Control": "no-cache", + "Connection": "keep-alive", + "Access-Control-Allow-Origin": "*", + }, + ) diff --git a/backend/routes/debug.py b/backend/routes/debug.py new file mode 100644 index 0000000..8344cf2 --- /dev/null +++ b/backend/routes/debug.py @@ -0,0 +1,85 @@ +""" +调试端点：POST /debug/chat, GET /debug/rag +""" + +import json +import time + +from fastapi import APIRouter +from fastapi.responses import StreamingResponse + +from schemas.chat import DebugChatRequest +from services.local_llm_service import local_llm_service +from services.rag_service import rag_service + +router = APIRouter(prefix="/debug") + + +@router.post("/chat") +async def debug_chat(request: DebugChatRequest): + current_messages = [ + {"role": message.role, "content": message.content} for message in request.history + ] + current_messages.append({"role": "user", "content": request.question}) + + start_time = time.time() + stream_iterator = local_llm_service.chat_stream( + history_messages=current_messages, + ) + + def generate_text(): + full_ai_response = "" + total_usage = None + + for chunk in stream_iterator: + if chunk is None: + continue + + choices = getattr(chunk, "choices", None) or [] + if choices: + delta = getattr(choices[0], "delta", None) + content = getattr(delta, "content", None) + if content: + full_ai_response += content + yield content + + usage = getattr(chunk, "usage", None) + if usage: + total_usage = usage + + print(f"DEBUG: LLM 调用耗时: {time.time() - start_time:.2f}s") + if total_usage: + print( + "🎫 Token 统计: " + f"Total={total_usage.total_tokens} " + f"(P:{total_usage.prompt_tokens}, C:{total_usage.completion_tokens})" + ) + + new_history = [ + {"role": message.role, "content": message.content} + for message in request.history + ] + new_history.append({"role": "user", "content": request.question}) + new_history.append({"role": "assistant", "content": full_ai_response}) + + print("\n" + "=" * 50) + print("🐞 调试完成！以下是可用于下次请求的 history 结构：") + print(json.dumps({"history": new_history}, ensure_ascii=False, indent=2)) + print("=" * 50 + "\n") + + return StreamingResponse(generate_text(), media_type="text/plain") + + +@router.get("/rag") +async def debug_rag(query: str): + if not query: + return {"error": "请提供 query 参数"} + + print(f"🔍 [Debug] 正在检索知识库: {query}") + context = await rag_service.retrieve(query) + return { + "query": query, + "retrieved_context": context, + "length": len(context) if context else 0, + "status": "success" if context else "no_results_or_error", + } diff --git a/backend/routes/proxy.py b/backend/routes/proxy.py new file mode 100644 index 0000000..b5c3c87 --- /dev/null +++ b/backend/routes/proxy.py @@ -0,0 +1,81 @@ +""" +POST /proxy — RTC OpenAPI 代理（含请求签名） +""" + +import httpx +from fastapi import APIRouter, Request +from fastapi.responses import JSONResponse + +from config.custom_scene import get_rtc_openapi_version +from security.signer import Signer +from services.scene_service import Scenes, prepare_scene_runtime +from utils.responses import error_response +from utils.validation import assert_scene_value, assert_value + +router = APIRouter() + + +@router.post("/proxy") +async def proxy(request: Request): + action = request.query_params.get("Action", "") + version = request.query_params.get("Version") or get_rtc_openapi_version() + + try: + assert_value(action, "Action 不能为空") + assert_value(version, "Version 不能为空") + + body = await request.json() + scene_id = body.get("SceneID", "") + assert_value(scene_id, "SceneID 不能为空，SceneID 用于指定场景配置") + + json_data = Scenes.get(scene_id) + if not json_data: + raise ValueError(f"{scene_id} 不存在，请先配置对应场景。") + + _, _, voice_chat = prepare_scene_runtime(scene_id, json_data) + account_config = json_data.get("AccountConfig", {}) + assert_scene_value( + scene_id, "AccountConfig.accessKeyId", account_config.get("accessKeyId") + ) + assert_scene_value( + scene_id, "AccountConfig.secretKey", account_config.get("secretKey") + ) + + if action == "StartVoiceChat": + req_body = voice_chat + elif action == "StopVoiceChat": + app_id = voice_chat.get("AppId", "") + room_id = voice_chat.get("RoomId", "") + task_id = voice_chat.get("TaskId", "") + assert_scene_value(scene_id, "VoiceChat.AppId", app_id) + assert_scene_value(scene_id, "VoiceChat.RoomId", room_id) + assert_scene_value(scene_id, "VoiceChat.TaskId", task_id) + req_body = {"AppId": app_id, "RoomId": room_id, "TaskId": task_id} + else: + req_body = {} + + request_data = { + "region": "cn-north-1", + "method": "POST", + "params": {"Action": action, "Version": version}, + "headers": { + "Host": "rtc.volcengineapi.com", + "Content-type": "application/json", + }, + "body": req_body, + } + signer = Signer(request_data, "rtc") + signer.add_authorization(account_config) + + async with httpx.AsyncClient() as client: + resp = await client.post( + f"https://rtc.volcengineapi.com?Action={action}&Version={version}", + headers=request_data["headers"], + json=req_body, + ) + return JSONResponse(resp.json()) + + except ValueError as e: + return error_response(action, str(e)) + except Exception as e: + return error_response(action, str(e)) diff --git a/backend/routes/scenes.py b/backend/routes/scenes.py new file mode 100644 index 0000000..e4a119a --- /dev/null +++ b/backend/routes/scenes.py @@ -0,0 +1,74 @@ +""" +POST /getScenes — 场景列表 +""" + +from fastapi import APIRouter +from fastapi.responses import JSONResponse + +from services.scene_service import Scenes, prepare_scene_runtime + +router = APIRouter() + + +@router.post("/getScenes") +async def get_scenes(): + try: + scenes_list = [] + for scene_name, data in Scenes.items(): + scene_config, rtc_config, voice_chat = prepare_scene_runtime( + scene_name, data + ) + + scene_config["id"] = scene_name + scene_config["botName"] = voice_chat.get("AgentConfig", {}).get("UserId") + scene_config["isInterruptMode"] = ( + voice_chat.get("Config", {}).get("InterruptMode") == 0 + ) + scene_config["isVision"] = ( + voice_chat.get("Config", {}) + .get("LLMConfig", {}) + .get("VisionConfig", {}) + .get("Enable") + ) + scene_config["isScreenMode"] = ( + voice_chat.get("Config", {}) + .get("LLMConfig", {}) + .get("VisionConfig", {}) + .get("SnapshotConfig", {}) + .get("StreamType") + == 1 + ) + scene_config["isAvatarScene"] = ( + voice_chat.get("Config", {}).get("AvatarConfig", {}).get("Enabled") + ) + scene_config["avatarBgUrl"] = ( + voice_chat.get("Config", {}) + .get("AvatarConfig", {}) + .get("BackgroundUrl") + ) + + rtc_out = {k: v for k, v in rtc_config.items() if k != "AppKey"} + + scenes_list.append( + { + "scene": scene_config, + "rtc": rtc_out, + } + ) + + return JSONResponse( + { + "ResponseMetadata": {"Action": "getScenes"}, + "Result": {"scenes": scenes_list}, + } + ) + + except ValueError as e: + return JSONResponse( + { + "ResponseMetadata": { + "Action": "getScenes", + "Error": {"Code": -1, "Message": str(e)}, + } + } + ) diff --git a/backend/scenes/Custom.json b/backend/scenes/Custom.json deleted file mode 100644 index 7afbc1e..0000000 --- a/backend/scenes/Custom.json +++ /dev/null @@ -1,75 +0,0 @@ -{ - "SceneConfig": { - "icon": "https://lf3-rtc-demo.volccdn.com/obj/rtc-aigc-assets/DoubaoAvatar.png", - "name": "自定义助手" - }, - "AccountConfig": { - "accessKeyId": "AKLTZWQ0NDljZTZhNjJhNDM4N2I5MjFiZWFkNDg5YWQ4YzI", - "secretKey": "Wm1WbU1EZzNaREl4WlRJNE5HRXhZV0V4TmpRMU1UQmpNamt4WXpJM04yWQ==" - }, - "RTCConfig": { - "AppId": "67d9266375d80e01b76f4108", - "AppKey": "", - "RoomId": "ChatRoom01", - "UserId": "Huoshan02", - "Token": "00167d9266375d80e01b76f4108SQCOTuMBk6DHaRPb0GkKAENoYXRSb29tMDEJAEh1b3NoYW4wMgYAAAAT29BpAQAT29BpAgAT29BpAwAT29BpBAAT29BpBQAT29BpIADq+UCvnjGv8j0Ay2eaLCUiSBG7oXmpGc6MdcdBYJA6CA==" - }, - "VoiceChat": { - "AppId": "67d9266375d80e01b76f4108", - "RoomId": "ChatRoom01", - "TaskId": "ChatTask01", - "AgentConfig": { - "TargetUserId": ["Huoshan02"], - "WelcomeMessage": "你好，我是小乖，有什么需要帮忙的吗？", - "UserId": "Huoshan0", - "EnableConversationStateCallback": true - }, - "Config": { - "ASRConfig": { - "Provider": "volcano", - "ProviderParams": { - "Mode": "smallmodel", - "AppId": "3340034205", - "Cluster": "volcengine_streaming_common" - } - }, - "TTSConfig": { - "Provider": "volcano", - "ProviderParams": { - "app": { - "appid": "3340034205", - "cluster": "volcano_tts" - }, - "audio": { - "voice_type": "BV001_streaming", - "speed_ratio": 1, - "pitch_ratio": 1, - "volume_ratio": 1 - } - } - }, - "LLMConfig": { - "Mode": "ArkV3", - "EndPointId": "ep-20250612105810-m6jh8", - "SystemMessages": [ - "你是小乖，性格幽默又善解人意。你在表达时需简明扼要，有自己的观点。" - ], - "VisionConfig": { - "Enable": false - }, - "ThinkingType": "disabled" - }, - "InterruptMode": 0 - }, - "AvatarConfig": { - "Enabled": false, - "AvatarType": "3min", - "AvatarRole": "250623-zhibo-linyunzhi", - "BackgroundUrl": "", - "VideoBitrate": 2000, - "AvatarAppID": "", - "AvatarToken": "" - }, - "InterruptMode": 0 - } -} diff --git a/backend/schemas/__init__.py b/backend/schemas/__init__.py new file mode 100644 index 0000000..86255e1 --- /dev/null +++ b/backend/schemas/__init__.py @@ -0,0 +1 @@ +"""Pydantic 请求/响应模型""" diff --git a/backend/schemas/chat.py b/backend/schemas/chat.py new file mode 100644 index 0000000..7775214 --- /dev/null +++ b/backend/schemas/chat.py @@ -0,0 +1,15 @@ +""" +聊天相关的请求模型 +""" + +from pydantic import BaseModel, Field + + +class ChatMessage(BaseModel): + role: str + content: str + + +class DebugChatRequest(BaseModel): + history: list[ChatMessage] = Field(default_factory=list) + question: str diff --git a/backend/security/__init__.py b/backend/security/__init__.py new file mode 100644 index 0000000..2fca39b --- /dev/null +++ b/backend/security/__init__.py @@ -0,0 +1 @@ +"""Backend security package.""" diff --git a/backend/rtc_token.py b/backend/security/rtc_token.py similarity index 92% rename from backend/rtc_token.py rename to backend/security/rtc_token.py index 54ad345..383ec4b 100644 --- a/backend/rtc_token.py +++ b/backend/security/rtc_token.py @@ -4,19 +4,18 @@ SPDX-license-identifier: BSD-3-Clause Migrated from Server/token.js """ + +import base64 import hashlib import hmac import random import struct import time -import base64 VERSION = "001" VERSION_LENGTH = 3 APP_ID_LENGTH = 24 -_random_nonce = random.randint(0, 0xFFFFFFFF) - privileges = { "PrivPublishStream": 0, "privPublishAudioStream": 1, @@ -50,8 +49,9 @@ class ByteBuf: if not m: self.put_uint16(0) return self - self.put_uint16(len(m)) - for key, value in m.items(): + sorted_items = sorted(m.items(), key=lambda x: int(x[0])) + self.put_uint16(len(sorted_items)) + for key, value in sorted_items: self.put_uint16(int(key)) self.put_uint32(int(value)) return self @@ -71,7 +71,8 @@ class AccessToken: self.room_id = room_id self.user_id = user_id self.issued_at = int(time.time()) - self.nonce = _random_nonce + random.seed(time.time()) + self.nonce = random.randint(1, 99999999) self.expire_at = 0 self._privileges: dict = {} diff --git a/backend/signer.py b/backend/security/signer.py similarity index 75% rename from backend/signer.py rename to backend/security/signer.py index c105b05..be1d68e 100644 --- a/backend/signer.py +++ b/backend/security/signer.py @@ -5,6 +5,7 @@ SPDX-license-identifier: BSD-3-Clause Migrated from @volcengine/openapi Signer (AWS SigV4 compatible) Reference: https://www.volcengine.com/docs/6348/69828 """ + import hashlib import hmac import json @@ -21,7 +22,7 @@ def _hmac_sha256(key: bytes, data: str) -> bytes: def _get_signing_key(secret_key: str, date_str: str, region: str, service: str) -> bytes: - k_date = _hmac_sha256(("HMAC-SHA256" + secret_key).encode("utf-8"), date_str) + k_date = _hmac_sha256(secret_key.encode("utf-8"), date_str) k_region = _hmac_sha256(k_date, region) k_service = _hmac_sha256(k_region, service) k_signing = _hmac_sha256(k_service, "request") @@ -38,7 +39,7 @@ class Signer: request_data: { region: str, method: str, - params: dict, # query params (Action, Version, ...) + params: dict, headers: dict, body: dict, } @@ -52,10 +53,6 @@ class Signer: self.service = service def add_authorization(self, account_config: dict): - """ - Computes and injects Authorization + X-Date headers into self.headers. - account_config: { accessKeyId: str, secretKey: str } - """ access_key = account_config["accessKeyId"] secret_key = account_config["secretKey"] @@ -65,10 +62,11 @@ class Signer: self.headers["X-Date"] = datetime_str self.headers["X-Content-Sha256"] = _sha256_hex( - json.dumps(self.body, separators=(",", ":"), ensure_ascii=False).encode("utf-8") + json.dumps(self.body, separators=(",", ":"), ensure_ascii=False).encode( + "utf-8" + ) ) - # Canonical headers: sorted lowercase header names signed_header_names = sorted(k.lower() for k in self.headers) canonical_headers = "".join( f"{k}:{self.headers[next(h for h in self.headers if h.lower() == k)]}\n" @@ -76,34 +74,38 @@ class Signer: ) signed_headers_str = ";".join(signed_header_names) - # Canonical query string sorted_params = sorted(self.params.items()) canonical_qs = "&".join( f"{quote(str(k), safe='')}={quote(str(v), safe='')}" for k, v in sorted_params ) - # Canonical request body_hash = self.headers["X-Content-Sha256"] - canonical_request = "\n".join([ - self.method, - "/", - canonical_qs, - canonical_headers, - signed_headers_str, - body_hash, - ]) + canonical_request = "\n".join( + [ + self.method, + "/", + canonical_qs, + canonical_headers, + signed_headers_str, + body_hash, + ] + ) credential_scope = f"{date_str}/{self.region}/{self.service}/request" - string_to_sign = "\n".join([ - "HMAC-SHA256", - datetime_str, - credential_scope, - _sha256_hex(canonical_request.encode("utf-8")), - ]) + string_to_sign = "\n".join( + [ + "HMAC-SHA256", + datetime_str, + credential_scope, + _sha256_hex(canonical_request.encode("utf-8")), + ] + ) signing_key = _get_signing_key(secret_key, date_str, self.region, self.service) - signature = hmac.new(signing_key, string_to_sign.encode("utf-8"), hashlib.sha256).hexdigest() + signature = hmac.new( + signing_key, string_to_sign.encode("utf-8"), hashlib.sha256 + ).hexdigest() self.headers["Authorization"] = ( f"HMAC-SHA256 Credential={access_key}/{credential_scope}, " diff --git a/backend/server.py b/backend/server.py new file mode 100644 index 0000000..525ac3c --- /dev/null +++ b/backend/server.py @@ -0,0 +1,34 @@ +from pathlib import Path + +from dotenv import load_dotenv + +BASE_DIR = Path(__file__).parent +load_dotenv(BASE_DIR / ".env", override=False) + +# 路由必须在 load_dotenv 之后导入，因为模块级代码会读取环境变量 +from routes.chat_callback import router as chat_callback_router # noqa: E402 +from routes.debug import router as debug_router # noqa: E402 +from routes.proxy import router as proxy_router # noqa: E402 +from routes.scenes import router as scenes_router # noqa: E402 + +from fastapi import FastAPI # noqa: E402 +from fastapi.middleware.cors import CORSMiddleware # noqa: E402 + +app = FastAPI() + +app.add_middleware( + CORSMiddleware, + allow_origins=["*"], + allow_methods=["*"], + allow_headers=["*"], +) + +app.include_router(proxy_router) +app.include_router(scenes_router) +app.include_router(chat_callback_router) +app.include_router(debug_router) + +if __name__ == "__main__": + import uvicorn + + uvicorn.run("server:app", host="0.0.0.0", port=3001, reload=True) diff --git a/backend/services/__init__.py b/backend/services/__init__.py new file mode 100644 index 0000000..151bfda --- /dev/null +++ b/backend/services/__init__.py @@ -0,0 +1 @@ +"""本地 LLM 与知识检索服务。""" diff --git a/backend/services/local_llm_service.py b/backend/services/local_llm_service.py new file mode 100644 index 0000000..e793511 --- /dev/null +++ b/backend/services/local_llm_service.py @@ -0,0 +1,139 @@ +""" +本地 CustomLLM 服务。 + +当前实现直接在同一个 FastAPI 进程内调用方舟 SDK， +并由 /api/chat_callback 对外提供火山要求的 SSE 回调接口。 +""" + +from __future__ import annotations + +from dataclasses import dataclass +from typing import Any, Iterator + +from utils.env import env_float, env_int, env_str + +DEFAULT_ARK_BASE_URL = "https://ark.cn-beijing.volces.com/api/v3" +DEFAULT_ARK_TIMEOUT_SECONDS = 1800 +DEFAULT_ARK_TEMPERATURE = 0 + + +def _coalesce(*values): + for value in values: + if value is not None: + return value + return None + + +@dataclass(frozen=True) +class LocalLLMSettings: + api_key: str + endpoint_id: str + base_url: str + timeout_seconds: int + system_prompt: str + default_temperature: float + + +def _load_settings() -> LocalLLMSettings: + api_key = env_str("ARK_API_KEY") + endpoint_id = env_str("ARK_ENDPOINT_ID") + + if not api_key: + raise ValueError("ARK_API_KEY 不能为空") + if not endpoint_id: + raise ValueError("ARK_ENDPOINT_ID 不能为空") + + return LocalLLMSettings( + api_key=api_key, + endpoint_id=endpoint_id, + base_url=env_str("ARK_BASE_URL", DEFAULT_ARK_BASE_URL), + timeout_seconds=env_int("ARK_TIMEOUT_SECONDS", DEFAULT_ARK_TIMEOUT_SECONDS), + system_prompt=env_str( + "LOCAL_LLM_SYSTEM_PROMPT", + env_str("CUSTOM_LLM_SYSTEM_MESSAGE"), + ), + default_temperature=env_float( + "LOCAL_LLM_TEMPERATURE", DEFAULT_ARK_TEMPERATURE + ), + ) + + +class LocalLLMService: + def __init__(self): + self._client = None + self._settings: LocalLLMSettings | None = None + + @property + def settings(self) -> LocalLLMSettings: + if self._settings is None: + self._settings = _load_settings() + return self._settings + + def _get_client(self): + if self._client is not None: + return self._client + + try: + from volcenginesdkarkruntime import Ark + except ImportError as exc: + raise RuntimeError( + "未安装 volcenginesdkarkruntime，请先执行 uv sync 安装依赖" + ) from exc + + s = self.settings + self._client = Ark( + base_url=s.base_url, + api_key=s.api_key, + timeout=s.timeout_seconds, + ) + return self._client + + def chat_stream( + self, + history_messages: list[dict[str, Any]], + rag_context: str = "", + request_options: dict[str, Any] | None = None, + ) -> Iterator[Any]: + settings = self.settings + client = self._get_client() + request_options = request_options or {} + + system_blocks = [settings.system_prompt] + if rag_context: + system_blocks.append(f"### 参考知识库（绝对准则）\n{rag_context.strip()}") + + messages = [ + { + "role": "system", + "content": "\n\n".join(block for block in system_blocks if block), + } + ] + messages.extend(history_messages) + + payload: dict[str, Any] = { + "model": settings.endpoint_id, + "messages": messages, + "temperature": _coalesce( + request_options.get("temperature"), + settings.default_temperature, + ), + "stream": True, + "stream_options": {"include_usage": True}, + } + + if request_options.get("max_tokens") is not None: + payload["max_tokens"] = request_options["max_tokens"] + if request_options.get("top_p") is not None: + payload["top_p"] = request_options["top_p"] + + print(f"🚀 发起流式调用 (Endpoint: {settings.endpoint_id})") + try: + stream = client.chat.completions.create(**payload) + for chunk in stream: + yield chunk + except Exception as exc: + print(f"❌ LLM 调用失败: {exc}") + raise + + +local_llm_service = LocalLLMService() diff --git a/backend/services/rag_service.py b/backend/services/rag_service.py new file mode 100644 index 0000000..65e589d --- /dev/null +++ b/backend/services/rag_service.py @@ -0,0 +1,30 @@ +""" +最小可用的 RAG 服务占位实现。 + +当前版本支持两种简单来源： +- RAG_STATIC_CONTEXT：直接写在环境变量中的固定知识 +- RAG_CONTEXT_FILE：读取本地文件全文作为知识上下文 + +后续如果要接真正的向量检索，可以直接替换 retrieve 方法实现。 +""" + +from __future__ import annotations + +from pathlib import Path + +from utils.env import env_str + + +class RagService: + async def retrieve(self, query: str) -> str: + _ = query + context_file = env_str("RAG_CONTEXT_FILE") + if context_file: + path = Path(context_file).expanduser() + if path.exists() and path.is_file(): + return path.read_text(encoding="utf-8") + + return env_str("RAG_STATIC_CONTEXT") + + +rag_service = RagService() diff --git a/backend/services/scene_service.py b/backend/services/scene_service.py new file mode 100644 index 0000000..bbcb985 --- /dev/null +++ b/backend/services/scene_service.py @@ -0,0 +1,99 @@ +""" +场景配置加载与运行时准备 +""" + +import copy +import json +import time +import uuid +from pathlib import Path +from typing import Any + +from fastapi import Request + +from config.custom_scene import ( + CUSTOM_SCENE_ID, + build_custom_scene_from_env, + build_llm_settings_from_env, +) +from security.rtc_token import AccessToken, privileges +from utils.validation import assert_scene_value, assert_token_generation_ready + +BASE_DIR = Path(__file__).resolve().parent.parent +SCENES_DIR = BASE_DIR / "scenes" + + +def load_scenes() -> dict: + scenes = { + CUSTOM_SCENE_ID: build_custom_scene_from_env(), + } + for p in sorted(SCENES_DIR.glob("*.json")): + if p.stem == CUSTOM_SCENE_ID: + continue + with open(p, encoding="utf-8") as f: + scenes[p.stem] = json.load(f) + return scenes + + +def prepare_scene_runtime(scene_name: str, data: dict[str, Any]): + data = copy.deepcopy(data) + scene_config = data.get("SceneConfig", {}) + rtc_config = data.get("RTCConfig", {}) + voice_chat = data.get("VoiceChat", {}) + + app_id = rtc_config.get("AppId", "") + assert_scene_value(scene_name, "RTCConfig.AppId", app_id) + + token = rtc_config.get("Token", "") + user_id = rtc_config.get("UserId", "") + room_id = rtc_config.get("RoomId", "") + app_key = rtc_config.get("AppKey", "") + + if app_id and (not token or not user_id or not room_id): + rtc_config["RoomId"] = voice_chat["RoomId"] = room_id or str(uuid.uuid4()) + rtc_config["UserId"] = user_id = user_id or str(uuid.uuid4()) + + agent_config = voice_chat.get("AgentConfig", {}) + target_user_ids = agent_config.get("TargetUserId") + if target_user_ids: + target_user_ids[0] = rtc_config["UserId"] + + assert_token_generation_ready(scene_name, app_key) + key = AccessToken(app_id, app_key, rtc_config["RoomId"], rtc_config["UserId"]) + key.add_privilege(privileges["PrivSubscribeStream"], 0) + key.add_privilege(privileges["PrivPublishStream"], 0) + key.expire_time(int(time.time()) + 24 * 3600) + rtc_config["Token"] = key.serialize() + + return scene_config, rtc_config, voice_chat + + +def get_custom_llm_callback_settings() -> dict[str, Any]: + missing: list[str] = [] + settings = build_llm_settings_from_env(missing) + if missing: + missing_str = ", ".join(dict.fromkeys(missing)) + raise ValueError(f"Custom 场景缺少以下环境变量: {missing_str}") + + if settings["mode"] != "CustomLLM": + raise ValueError("当前 CUSTOM_LLM_MODE 不是 CustomLLM，无法使用本地回调接口") + + return settings + + +def ensure_custom_llm_authorized(request: Request, api_key: str): + if not api_key: + return + + authorization = request.headers.get("authorization", "") + expected_value = f"Bearer {api_key}" + if authorization == expected_value: + return + + raise PermissionError("自定义 LLM 回调鉴权失败，请检查 CUSTOM_LLM_API_KEY") + + +try: + Scenes = load_scenes() +except ValueError as exc: + raise RuntimeError(f"Custom 场景配置错误：{exc}") from exc diff --git a/backend/utils/__init__.py b/backend/utils/__init__.py new file mode 100644 index 0000000..e69de29 diff --git a/backend/utils/env.py b/backend/utils/env.py new file mode 100644 index 0000000..9f52e3f --- /dev/null +++ b/backend/utils/env.py @@ -0,0 +1,134 @@ +""" +环境变量读取工具函数。 +""" + +import json +import os +from typing import Any + +TRUTHY_VALUES = {"1", "true", "yes", "on"} +FALSY_VALUES = {"0", "false", "no", "off"} + + +def env_str(name: str, default: str = "") -> str: + value = os.getenv(name) + if value is None: + return default + value = value.strip() + return value if value else default + + +def require_env(name: str, missing: list[str]) -> str: + value = env_str(name) + if not value: + missing.append(name) + return value + + +def env_bool(name: str, default: bool) -> bool: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return default + + value = raw_value.strip().lower() + if value in TRUTHY_VALUES: + return True + if value in FALSY_VALUES: + return False + + raise ValueError(f"{name} 必须是布尔值，可选 true/false/1/0") + + +def env_optional_bool(name: str) -> bool | None: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return None + return env_bool(name, False) + + +def env_int(name: str, default: int) -> int: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return default + + try: + return int(raw_value.strip()) + except ValueError as exc: + raise ValueError(f"{name} 必须是整数") from exc + + +def env_optional_int(name: str) -> int | None: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return None + return env_int(name, 0) + + +def env_float(name: str, default: float) -> float: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return default + + try: + return float(raw_value.strip()) + except ValueError as exc: + raise ValueError(f"{name} 必须是浮点数") from exc + + +def env_number(name: str, default: int | float) -> int | float: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return default + + try: + value = float(raw_value.strip()) + except ValueError as exc: + raise ValueError(f"{name} 必须是数字") from exc + + if value.is_integer(): + return int(value) + return value + + +def env_optional_number(name: str) -> int | float | None: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return None + return env_number(name, 0) + + +def env_json_object(name: str) -> dict[str, str]: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return {} + + try: + value = json.loads(raw_value) + except json.JSONDecodeError as exc: + raise ValueError(f"{name} 必须是合法的 JSON 对象字符串") from exc + + if not isinstance(value, dict): + raise ValueError(f"{name} 必须是 JSON 对象") + + invalid_keys = [key for key in value.keys() if not isinstance(key, str)] + if invalid_keys: + raise ValueError(f"{name} 的所有键必须是字符串") + + return {key: str(val) for key, val in value.items()} + + +def env_list(name: str) -> list[str]: + raw_value = os.getenv(name) + if raw_value is None or not raw_value.strip(): + return [] + return [item.strip() for item in raw_value.split(",") if item.strip()] + + +def set_if_present(target: dict[str, Any], key: str, value: Any): + if value is None: + return + if isinstance(value, str) and not value: + return + if isinstance(value, dict) and not value: + return + target[key] = value diff --git a/backend/utils/responses.py b/backend/utils/responses.py new file mode 100644 index 0000000..0c4b0a6 --- /dev/null +++ b/backend/utils/responses.py @@ -0,0 +1,33 @@ +""" +统一错误响应格式 +""" + +from fastapi.responses import JSONResponse + + +def error_response(action: str, message: str): + return JSONResponse( + { + "ResponseMetadata": { + "Action": action, + "Error": {"Code": -1, "Message": message}, + } + } + ) + + +def custom_llm_error_response( + message: str, + *, + code: str = "InvalidConfiguration", + status_code: int = 400, +): + return JSONResponse( + { + "Error": { + "Code": code, + "Message": message, + } + }, + status_code=status_code, + ) diff --git a/backend/utils/validation.py b/backend/utils/validation.py new file mode 100644 index 0000000..f999cd0 --- /dev/null +++ b/backend/utils/validation.py @@ -0,0 +1,31 @@ +""" +校验工具函数 +""" + +from typing import Any + +from config.custom_scene import CUSTOM_SCENE_ID + + +def assert_value(value, msg: str): + if not value: + raise ValueError(msg) + + +def assert_scene_value(scene_name: str, field_name: str, value: Any): + if value: + return + + raise ValueError(f"{scene_name} 场景的 {field_name} 不能为空") + + +def assert_token_generation_ready(scene_name: str, app_key: str): + if app_key: + return + + if scene_name == CUSTOM_SCENE_ID: + raise ValueError( + "Custom 场景未提供 CUSTOM_RTC_TOKEN 时，必须配置 CUSTOM_RTC_APP_KEY 用于自动生成 Token" + ) + + raise ValueError(f"自动生成 Token 时，{scene_name} 场景的 RTCConfig.AppKey 不可为空") diff --git a/backend/uv.lock b/backend/uv.lock index aadc592..6d0661f 100644 --- a/backend/uv.lock +++ b/backend/uv.lock @@ -9,16 +9,20 @@ source = { virtual = "." } dependencies = [ { name = "fastapi" }, { name = "httpx" }, + { name = "python-dotenv" }, { name = "python-multipart" }, { name = "uvicorn", extra = ["standard"] }, + { name = "volcengine-python-sdk", extra = ["ark"] }, ] [package.metadata] requires-dist = [ { name = "fastapi", specifier = ">=0.110.0" }, { name = "httpx", specifier = ">=0.27.0" }, + { name = "python-dotenv", specifier = ">=1.2.2" }, { name = "python-multipart", specifier = ">=0.0.9" }, { name = "uvicorn", extras = ["standard"], specifier = ">=0.29.0" }, + { name = "volcengine-python-sdk", extras = ["ark"], specifier = ">=4.0.6" }, ] [package.metadata.requires-dev] @@ -63,6 +67,51 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/9a/3c/c17fb3ca2d9c3acff52e30b309f538586f9f5b9c9cf454f3845fc9af4881/certifi-2026.2.25-py3-none-any.whl", hash = "sha256:027692e4402ad994f1c42e52a4997a9763c646b73e4096e4d5d6db8af1d6f0fa", size = 153684 }, ] +[[package]] +name = "cffi" +version = "2.0.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "pycparser", marker = "implementation_name != 'PyPy'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/eb/56/b1ba7935a17738ae8453301356628e8147c79dbb825bcbc73dc7401f9846/cffi-2.0.0.tar.gz", hash = "sha256:44d1b5909021139fe36001ae048dbdde8214afa20200eda0f64c068cac5d5529", size = 523588 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/4b/8d/a0a47a0c9e413a658623d014e91e74a50cdd2c423f7ccfd44086ef767f90/cffi-2.0.0-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:00bdf7acc5f795150faa6957054fbbca2439db2f775ce831222b66f192f03beb", size = 185230 }, + { url = "https://files.pythonhosted.org/packages/4a/d2/a6c0296814556c68ee32009d9c2ad4f85f2707cdecfd7727951ec228005d/cffi-2.0.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:45d5e886156860dc35862657e1494b9bae8dfa63bf56796f2fb56e1679fc0bca", size = 181043 }, + { url = "https://files.pythonhosted.org/packages/b0/1e/d22cc63332bd59b06481ceaac49d6c507598642e2230f201649058a7e704/cffi-2.0.0-cp313-cp313-manylinux1_i686.manylinux2014_i686.manylinux_2_17_i686.manylinux_2_5_i686.whl", hash = "sha256:07b271772c100085dd28b74fa0cd81c8fb1a3ba18b21e03d7c27f3436a10606b", size = 212446 }, + { url = "https://files.pythonhosted.org/packages/a9/f5/a2c23eb03b61a0b8747f211eb716446c826ad66818ddc7810cc2cc19b3f2/cffi-2.0.0-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:d48a880098c96020b02d5a1f7d9251308510ce8858940e6fa99ece33f610838b", size = 220101 }, + { url = "https://files.pythonhosted.org/packages/f2/7f/e6647792fc5850d634695bc0e6ab4111ae88e89981d35ac269956605feba/cffi-2.0.0-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:f93fd8e5c8c0a4aa1f424d6173f14a892044054871c771f8566e4008eaa359d2", size = 207948 }, + { url = "https://files.pythonhosted.org/packages/cb/1e/a5a1bd6f1fb30f22573f76533de12a00bf274abcdc55c8edab639078abb6/cffi-2.0.0-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:dd4f05f54a52fb558f1ba9f528228066954fee3ebe629fc1660d874d040ae5a3", size = 206422 }, + { url = "https://files.pythonhosted.org/packages/98/df/0a1755e750013a2081e863e7cd37e0cdd02664372c754e5560099eb7aa44/cffi-2.0.0-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:c8d3b5532fc71b7a77c09192b4a5a200ea992702734a2e9279a37f2478236f26", size = 219499 }, + { url = "https://files.pythonhosted.org/packages/50/e1/a969e687fcf9ea58e6e2a928ad5e2dd88cc12f6f0ab477e9971f2309b57c/cffi-2.0.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:d9b29c1f0ae438d5ee9acb31cadee00a58c46cc9c0b2f9038c6b0b3470877a8c", size = 222928 }, + { url = "https://files.pythonhosted.org/packages/36/54/0362578dd2c9e557a28ac77698ed67323ed5b9775ca9d3fe73fe191bb5d8/cffi-2.0.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:6d50360be4546678fc1b79ffe7a66265e28667840010348dd69a314145807a1b", size = 221302 }, + { url = "https://files.pythonhosted.org/packages/eb/6d/bf9bda840d5f1dfdbf0feca87fbdb64a918a69bca42cfa0ba7b137c48cb8/cffi-2.0.0-cp313-cp313-win32.whl", hash = "sha256:74a03b9698e198d47562765773b4a8309919089150a0bb17d829ad7b44b60d27", size = 172909 }, + { url = "https://files.pythonhosted.org/packages/37/18/6519e1ee6f5a1e579e04b9ddb6f1676c17368a7aba48299c3759bbc3c8b3/cffi-2.0.0-cp313-cp313-win_amd64.whl", hash = "sha256:19f705ada2530c1167abacb171925dd886168931e0a7b78f5bffcae5c6b5be75", size = 183402 }, + { url = "https://files.pythonhosted.org/packages/cb/0e/02ceeec9a7d6ee63bb596121c2c8e9b3a9e150936f4fbef6ca1943e6137c/cffi-2.0.0-cp313-cp313-win_arm64.whl", hash = "sha256:256f80b80ca3853f90c21b23ee78cd008713787b1b1e93eae9f3d6a7134abd91", size = 177780 }, + { url = "https://files.pythonhosted.org/packages/92/c4/3ce07396253a83250ee98564f8d7e9789fab8e58858f35d07a9a2c78de9f/cffi-2.0.0-cp314-cp314-macosx_10_13_x86_64.whl", hash = "sha256:fc33c5141b55ed366cfaad382df24fe7dcbc686de5be719b207bb248e3053dc5", size = 185320 }, + { url = "https://files.pythonhosted.org/packages/59/dd/27e9fa567a23931c838c6b02d0764611c62290062a6d4e8ff7863daf9730/cffi-2.0.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:c654de545946e0db659b3400168c9ad31b5d29593291482c43e3564effbcee13", size = 181487 }, + { url = "https://files.pythonhosted.org/packages/d6/43/0e822876f87ea8a4ef95442c3d766a06a51fc5298823f884ef87aaad168c/cffi-2.0.0-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:24b6f81f1983e6df8db3adc38562c83f7d4a0c36162885ec7f7b77c7dcbec97b", size = 220049 }, + { url = "https://files.pythonhosted.org/packages/b4/89/76799151d9c2d2d1ead63c2429da9ea9d7aac304603de0c6e8764e6e8e70/cffi-2.0.0-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:12873ca6cb9b0f0d3a0da705d6086fe911591737a59f28b7936bdfed27c0d47c", size = 207793 }, + { url = "https://files.pythonhosted.org/packages/bb/dd/3465b14bb9e24ee24cb88c9e3730f6de63111fffe513492bf8c808a3547e/cffi-2.0.0-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:d9b97165e8aed9272a6bb17c01e3cc5871a594a446ebedc996e2397a1c1ea8ef", size = 206300 }, + { url = "https://files.pythonhosted.org/packages/47/d9/d83e293854571c877a92da46fdec39158f8d7e68da75bf73581225d28e90/cffi-2.0.0-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:afb8db5439b81cf9c9d0c80404b60c3cc9c3add93e114dcae767f1477cb53775", size = 219244 }, + { url = "https://files.pythonhosted.org/packages/2b/0f/1f177e3683aead2bb00f7679a16451d302c436b5cbf2505f0ea8146ef59e/cffi-2.0.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:737fe7d37e1a1bffe70bd5754ea763a62a066dc5913ca57e957824b72a85e205", size = 222828 }, + { url = "https://files.pythonhosted.org/packages/c6/0f/cafacebd4b040e3119dcb32fed8bdef8dfe94da653155f9d0b9dc660166e/cffi-2.0.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:38100abb9d1b1435bc4cc340bb4489635dc2f0da7456590877030c9b3d40b0c1", size = 220926 }, + { url = "https://files.pythonhosted.org/packages/3e/aa/df335faa45b395396fcbc03de2dfcab242cd61a9900e914fe682a59170b1/cffi-2.0.0-cp314-cp314-win32.whl", hash = "sha256:087067fa8953339c723661eda6b54bc98c5625757ea62e95eb4898ad5e776e9f", size = 175328 }, + { url = "https://files.pythonhosted.org/packages/bb/92/882c2d30831744296ce713f0feb4c1cd30f346ef747b530b5318715cc367/cffi-2.0.0-cp314-cp314-win_amd64.whl", hash = "sha256:203a48d1fb583fc7d78a4c6655692963b860a417c0528492a6bc21f1aaefab25", size = 185650 }, + { url = "https://files.pythonhosted.org/packages/9f/2c/98ece204b9d35a7366b5b2c6539c350313ca13932143e79dc133ba757104/cffi-2.0.0-cp314-cp314-win_arm64.whl", hash = "sha256:dbd5c7a25a7cb98f5ca55d258b103a2054f859a46ae11aaf23134f9cc0d356ad", size = 180687 }, + { url = "https://files.pythonhosted.org/packages/3e/61/c768e4d548bfa607abcda77423448df8c471f25dbe64fb2ef6d555eae006/cffi-2.0.0-cp314-cp314t-macosx_10_13_x86_64.whl", hash = "sha256:9a67fc9e8eb39039280526379fb3a70023d77caec1852002b4da7e8b270c4dd9", size = 188773 }, + { url = "https://files.pythonhosted.org/packages/2c/ea/5f76bce7cf6fcd0ab1a1058b5af899bfbef198bea4d5686da88471ea0336/cffi-2.0.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:7a66c7204d8869299919db4d5069a82f1561581af12b11b3c9f48c584eb8743d", size = 185013 }, + { url = "https://files.pythonhosted.org/packages/be/b4/c56878d0d1755cf9caa54ba71e5d049479c52f9e4afc230f06822162ab2f/cffi-2.0.0-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7cc09976e8b56f8cebd752f7113ad07752461f48a58cbba644139015ac24954c", size = 221593 }, + { url = "https://files.pythonhosted.org/packages/e0/0d/eb704606dfe8033e7128df5e90fee946bbcb64a04fcdaa97321309004000/cffi-2.0.0-cp314-cp314t-manylinux2014_ppc64le.manylinux_2_17_ppc64le.whl", hash = "sha256:92b68146a71df78564e4ef48af17551a5ddd142e5190cdf2c5624d0c3ff5b2e8", size = 209354 }, + { url = "https://files.pythonhosted.org/packages/d8/19/3c435d727b368ca475fb8742ab97c9cb13a0de600ce86f62eab7fa3eea60/cffi-2.0.0-cp314-cp314t-manylinux2014_s390x.manylinux_2_17_s390x.whl", hash = "sha256:b1e74d11748e7e98e2f426ab176d4ed720a64412b6a15054378afdb71e0f37dc", size = 208480 }, + { url = "https://files.pythonhosted.org/packages/d0/44/681604464ed9541673e486521497406fadcc15b5217c3e326b061696899a/cffi-2.0.0-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:28a3a209b96630bca57cce802da70c266eb08c6e97e5afd61a75611ee6c64592", size = 221584 }, + { url = "https://files.pythonhosted.org/packages/25/8e/342a504ff018a2825d395d44d63a767dd8ebc927ebda557fecdaca3ac33a/cffi-2.0.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:7553fb2090d71822f02c629afe6042c299edf91ba1bf94951165613553984512", size = 224443 }, + { url = "https://files.pythonhosted.org/packages/e1/5e/b666bacbbc60fbf415ba9988324a132c9a7a0448a9a8f125074671c0f2c3/cffi-2.0.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6c6c373cfc5c83a975506110d17457138c8c63016b563cc9ed6e056a82f13ce4", size = 223437 }, + { url = "https://files.pythonhosted.org/packages/a0/1d/ec1a60bd1a10daa292d3cd6bb0b359a81607154fb8165f3ec95fe003b85c/cffi-2.0.0-cp314-cp314t-win32.whl", hash = "sha256:1fc9ea04857caf665289b7a75923f2c6ed559b8298a1b8c49e59f7dd95c8481e", size = 180487 }, + { url = "https://files.pythonhosted.org/packages/bf/41/4c1168c74fac325c0c8156f04b6749c8b6a8f405bbf91413ba088359f60d/cffi-2.0.0-cp314-cp314t-win_amd64.whl", hash = "sha256:d68b6cef7827e8641e8ef16f4494edda8b36104d79773a334beaa1e3521430f6", size = 191726 }, + { url = "https://files.pythonhosted.org/packages/ae/3a/dbeec9d1ee0844c679f6bb5d6ad4e9f198b1224f4e7a32825f47f6192b0c/cffi-2.0.0-cp314-cp314t-win_arm64.whl", hash = "sha256:0a1527a803f0a659de1af2e1fd700213caba79377e27e4693648c2923da066f9", size = 184195 }, +] + [[package]] name = "click" version = "8.3.1" @@ -84,6 +133,59 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/d1/d6/3965ed04c63042e047cb6a3e6ed1a63a35087b6a609aa3a15ed8ac56c221/colorama-0.4.6-py2.py3-none-any.whl", hash = "sha256:4f1d9991f5acc0ca119f9d443620b77f9d6b33703e51011c16baf57afb285fc6", size = 25335 }, ] +[[package]] +name = "cryptography" +version = "46.0.6" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "cffi", marker = "platform_python_implementation != 'PyPy'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/a4/ba/04b1bd4218cbc58dc90ce967106d51582371b898690f3ae0402876cc4f34/cryptography-46.0.6.tar.gz", hash = "sha256:27550628a518c5c6c903d84f637fbecf287f6cb9ced3804838a1295dc1fd0759", size = 750542 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/47/23/9285e15e3bc57325b0a72e592921983a701efc1ee8f91c06c5f0235d86d9/cryptography-46.0.6-cp311-abi3-macosx_10_9_universal2.whl", hash = "sha256:64235194bad039a10bb6d2d930ab3323baaec67e2ce36215fd0952fad0930ca8", size = 7176401 }, + { url = "https://files.pythonhosted.org/packages/60/f8/e61f8f13950ab6195b31913b42d39f0f9afc7d93f76710f299b5ec286ae6/cryptography-46.0.6-cp311-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:26031f1e5ca62fcb9d1fcb34b2b60b390d1aacaa15dc8b895a9ed00968b97b30", size = 4275275 }, + { url = "https://files.pythonhosted.org/packages/19/69/732a736d12c2631e140be2348b4ad3d226302df63ef64d30dfdb8db7ad1c/cryptography-46.0.6-cp311-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:9a693028b9cbe51b5a1136232ee8f2bc242e4e19d456ded3fa7c86e43c713b4a", size = 4425320 }, + { url = "https://files.pythonhosted.org/packages/d4/12/123be7292674abf76b21ac1fc0e1af50661f0e5b8f0ec8285faac18eb99e/cryptography-46.0.6-cp311-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:67177e8a9f421aa2d3a170c3e56eca4e0128883cf52a071a7cbf53297f18b175", size = 4278082 }, + { url = "https://files.pythonhosted.org/packages/5b/ba/d5e27f8d68c24951b0a484924a84c7cdaed7502bac9f18601cd357f8b1d2/cryptography-46.0.6-cp311-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:d9528b535a6c4f8ff37847144b8986a9a143585f0540fbcb1a98115b543aa463", size = 4926514 }, + { url = "https://files.pythonhosted.org/packages/34/71/1ea5a7352ae516d5512d17babe7e1b87d9db5150b21f794b1377eac1edc0/cryptography-46.0.6-cp311-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:22259338084d6ae497a19bae5d4c66b7ca1387d3264d1c2c0e72d9e9b6a77b97", size = 4457766 }, + { url = "https://files.pythonhosted.org/packages/01/59/562be1e653accee4fdad92c7a2e88fced26b3fdfce144047519bbebc299e/cryptography-46.0.6-cp311-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:760997a4b950ff00d418398ad73fbc91aa2894b5c1db7ccb45b4f68b42a63b3c", size = 3986535 }, + { url = "https://files.pythonhosted.org/packages/d6/8b/b1ebfeb788bf4624d36e45ed2662b8bd43a05ff62157093c1539c1288a18/cryptography-46.0.6-cp311-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:3dfa6567f2e9e4c5dceb8ccb5a708158a2a871052fa75c8b78cb0977063f1507", size = 4277618 }, + { url = "https://files.pythonhosted.org/packages/dd/52/a005f8eabdb28df57c20f84c44d397a755782d6ff6d455f05baa2785bd91/cryptography-46.0.6-cp311-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:cdcd3edcbc5d55757e5f5f3d330dd00007ae463a7e7aa5bf132d1f22a4b62b19", size = 4890802 }, + { url = "https://files.pythonhosted.org/packages/ec/4d/8e7d7245c79c617d08724e2efa397737715ca0ec830ecb3c91e547302555/cryptography-46.0.6-cp311-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:d4e4aadb7fc1f88687f47ca20bb7227981b03afaae69287029da08096853b738", size = 4457425 }, + { url = "https://files.pythonhosted.org/packages/1d/5c/f6c3596a1430cec6f949085f0e1a970638d76f81c3ea56d93d564d04c340/cryptography-46.0.6-cp311-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:2b417edbe8877cda9022dde3a008e2deb50be9c407eef034aeeb3a8b11d9db3c", size = 4405530 }, + { url = "https://files.pythonhosted.org/packages/7e/c9/9f9cea13ee2dbde070424e0c4f621c091a91ffcc504ffea5e74f0e1daeff/cryptography-46.0.6-cp311-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:380343e0653b1c9d7e1f55b52aaa2dbb2fdf2730088d48c43ca1c7c0abb7cc2f", size = 4667896 }, + { url = "https://files.pythonhosted.org/packages/ad/b5/1895bc0821226f129bc74d00eccfc6a5969e2028f8617c09790bf89c185e/cryptography-46.0.6-cp311-abi3-win32.whl", hash = "sha256:bcb87663e1f7b075e48c3be3ecb5f0b46c8fc50b50a97cf264e7f60242dca3f2", size = 3026348 }, + { url = "https://files.pythonhosted.org/packages/c3/f8/c9bcbf0d3e6ad288b9d9aa0b1dee04b063d19e8c4f871855a03ab3a297ab/cryptography-46.0.6-cp311-abi3-win_amd64.whl", hash = "sha256:6739d56300662c468fddb0e5e291f9b4d084bead381667b9e654c7dd81705124", size = 3483896 }, + { url = "https://files.pythonhosted.org/packages/01/41/3a578f7fd5c70611c0aacba52cd13cb364a5dee895a5c1d467208a9380b0/cryptography-46.0.6-cp314-cp314t-macosx_10_9_universal2.whl", hash = "sha256:2ef9e69886cbb137c2aef9772c2e7138dc581fad4fcbcf13cc181eb5a3ab6275", size = 7117147 }, + { url = "https://files.pythonhosted.org/packages/fa/87/887f35a6fca9dde90cad08e0de0c89263a8e59b2d2ff904fd9fcd8025b6f/cryptography-46.0.6-cp314-cp314t-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:7f417f034f91dcec1cb6c5c35b07cdbb2ef262557f701b4ecd803ee8cefed4f4", size = 4266221 }, + { url = "https://files.pythonhosted.org/packages/aa/a8/0a90c4f0b0871e0e3d1ed126aed101328a8a57fd9fd17f00fb67e82a51ca/cryptography-46.0.6-cp314-cp314t-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:d24c13369e856b94892a89ddf70b332e0b70ad4a5c43cf3e9cb71d6d7ffa1f7b", size = 4408952 }, + { url = "https://files.pythonhosted.org/packages/16/0b/b239701eb946523e4e9f329336e4ff32b1247e109cbab32d1a7b61da8ed7/cryptography-46.0.6-cp314-cp314t-manylinux_2_28_aarch64.whl", hash = "sha256:aad75154a7ac9039936d50cf431719a2f8d4ed3d3c277ac03f3339ded1a5e707", size = 4270141 }, + { url = "https://files.pythonhosted.org/packages/0f/a8/976acdd4f0f30df7b25605f4b9d3d89295351665c2091d18224f7ad5cdbf/cryptography-46.0.6-cp314-cp314t-manylinux_2_28_ppc64le.whl", hash = "sha256:3c21d92ed15e9cfc6eb64c1f5a0326db22ca9c2566ca46d845119b45b4400361", size = 4904178 }, + { url = "https://files.pythonhosted.org/packages/b1/1b/bf0e01a88efd0e59679b69f42d4afd5bced8700bb5e80617b2d63a3741af/cryptography-46.0.6-cp314-cp314t-manylinux_2_28_x86_64.whl", hash = "sha256:4668298aef7cddeaf5c6ecc244c2302a2b8e40f384255505c22875eebb47888b", size = 4441812 }, + { url = "https://files.pythonhosted.org/packages/bb/8b/11df86de2ea389c65aa1806f331cae145f2ed18011f30234cc10ca253de8/cryptography-46.0.6-cp314-cp314t-manylinux_2_31_armv7l.whl", hash = "sha256:8ce35b77aaf02f3b59c90b2c8a05c73bac12cea5b4e8f3fbece1f5fddea5f0ca", size = 3963923 }, + { url = "https://files.pythonhosted.org/packages/91/e0/207fb177c3a9ef6a8108f234208c3e9e76a6aa8cf20d51932916bd43bda0/cryptography-46.0.6-cp314-cp314t-manylinux_2_34_aarch64.whl", hash = "sha256:c89eb37fae9216985d8734c1afd172ba4927f5a05cfd9bf0e4863c6d5465b013", size = 4269695 }, + { url = "https://files.pythonhosted.org/packages/21/5e/19f3260ed1e95bced52ace7501fabcd266df67077eeb382b79c81729d2d3/cryptography-46.0.6-cp314-cp314t-manylinux_2_34_ppc64le.whl", hash = "sha256:ed418c37d095aeddf5336898a132fba01091f0ac5844e3e8018506f014b6d2c4", size = 4869785 }, + { url = "https://files.pythonhosted.org/packages/10/38/cd7864d79aa1d92ef6f1a584281433419b955ad5a5ba8d1eb6c872165bcb/cryptography-46.0.6-cp314-cp314t-manylinux_2_34_x86_64.whl", hash = "sha256:69cf0056d6947edc6e6760e5f17afe4bea06b56a9ac8a06de9d2bd6b532d4f3a", size = 4441404 }, + { url = "https://files.pythonhosted.org/packages/09/0a/4fe7a8d25fed74419f91835cf5829ade6408fd1963c9eae9c4bce390ecbb/cryptography-46.0.6-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:8e7304c4f4e9490e11efe56af6713983460ee0780f16c63f219984dab3af9d2d", size = 4397549 }, + { url = "https://files.pythonhosted.org/packages/5f/a0/7d738944eac6513cd60a8da98b65951f4a3b279b93479a7e8926d9cd730b/cryptography-46.0.6-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:b928a3ca837c77a10e81a814a693f2295200adb3352395fad024559b7be7a736", size = 4651874 }, + { url = "https://files.pythonhosted.org/packages/cb/f1/c2326781ca05208845efca38bf714f76939ae446cd492d7613808badedf1/cryptography-46.0.6-cp314-cp314t-win32.whl", hash = "sha256:97c8115b27e19e592a05c45d0dd89c57f81f841cc9880e353e0d3bf25b2139ed", size = 3001511 }, + { url = "https://files.pythonhosted.org/packages/c9/57/fe4a23eb549ac9d903bd4698ffda13383808ef0876cc912bcb2838799ece/cryptography-46.0.6-cp314-cp314t-win_amd64.whl", hash = "sha256:c797e2517cb7880f8297e2c0f43bb910e91381339336f75d2c1c2cbf811b70b4", size = 3471692 }, + { url = "https://files.pythonhosted.org/packages/c4/cc/f330e982852403da79008552de9906804568ae9230da8432f7496ce02b71/cryptography-46.0.6-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:12cae594e9473bca1a7aceb90536060643128bb274fcea0fc459ab90f7d1ae7a", size = 7162776 }, + { url = "https://files.pythonhosted.org/packages/49/b3/dc27efd8dcc4bff583b3f01d4a3943cd8b5821777a58b3a6a5f054d61b79/cryptography-46.0.6-cp38-abi3-manylinux2014_aarch64.manylinux_2_17_aarch64.whl", hash = "sha256:639301950939d844a9e1c4464d7e07f902fe9a7f6b215bb0d4f28584729935d8", size = 4270529 }, + { url = "https://files.pythonhosted.org/packages/e6/05/e8d0e6eb4f0d83365b3cb0e00eb3c484f7348db0266652ccd84632a3d58d/cryptography-46.0.6-cp38-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl", hash = "sha256:ed3775295fb91f70b4027aeba878d79b3e55c0b3e97eaa4de71f8f23a9f2eb77", size = 4414827 }, + { url = "https://files.pythonhosted.org/packages/2f/97/daba0f5d2dc6d855e2dcb70733c812558a7977a55dd4a6722756628c44d1/cryptography-46.0.6-cp38-abi3-manylinux_2_28_aarch64.whl", hash = "sha256:8927ccfbe967c7df312ade694f987e7e9e22b2425976ddbf28271d7e58845290", size = 4271265 }, + { url = "https://files.pythonhosted.org/packages/89/06/fe1fce39a37ac452e58d04b43b0855261dac320a2ebf8f5260dd55b201a9/cryptography-46.0.6-cp38-abi3-manylinux_2_28_ppc64le.whl", hash = "sha256:b12c6b1e1651e42ab5de8b1e00dc3b6354fdfd778e7fa60541ddacc27cd21410", size = 4916800 }, + { url = "https://files.pythonhosted.org/packages/ff/8a/b14f3101fe9c3592603339eb5d94046c3ce5f7fc76d6512a2d40efd9724e/cryptography-46.0.6-cp38-abi3-manylinux_2_28_x86_64.whl", hash = "sha256:063b67749f338ca9c5a0b7fe438a52c25f9526b851e24e6c9310e7195aad3b4d", size = 4448771 }, + { url = "https://files.pythonhosted.org/packages/01/b3/0796998056a66d1973fd52ee89dc1bb3b6581960a91ad4ac705f182d398f/cryptography-46.0.6-cp38-abi3-manylinux_2_31_armv7l.whl", hash = "sha256:02fad249cb0e090b574e30b276a3da6a149e04ee2f049725b1f69e7b8351ec70", size = 3978333 }, + { url = "https://files.pythonhosted.org/packages/c5/3d/db200af5a4ffd08918cd55c08399dc6c9c50b0bc72c00a3246e099d3a849/cryptography-46.0.6-cp38-abi3-manylinux_2_34_aarch64.whl", hash = "sha256:7e6142674f2a9291463e5e150090b95a8519b2fb6e6aaec8917dd8d094ce750d", size = 4271069 }, + { url = "https://files.pythonhosted.org/packages/d7/18/61acfd5b414309d74ee838be321c636fe71815436f53c9f0334bf19064fa/cryptography-46.0.6-cp38-abi3-manylinux_2_34_ppc64le.whl", hash = "sha256:456b3215172aeefb9284550b162801d62f5f264a081049a3e94307fe20792cfa", size = 4878358 }, + { url = "https://files.pythonhosted.org/packages/8b/65/5bf43286d566f8171917cae23ac6add941654ccf085d739195a4eacf1674/cryptography-46.0.6-cp38-abi3-manylinux_2_34_x86_64.whl", hash = "sha256:341359d6c9e68834e204ceaf25936dffeafea3829ab80e9503860dcc4f4dac58", size = 4448061 }, + { url = "https://files.pythonhosted.org/packages/e0/25/7e49c0fa7205cf3597e525d156a6bce5b5c9de1fd7e8cb01120e459f205a/cryptography-46.0.6-cp38-abi3-musllinux_1_2_aarch64.whl", hash = "sha256:9a9c42a2723999a710445bc0d974e345c32adfd8d2fac6d8a251fa829ad31cfb", size = 4399103 }, + { url = "https://files.pythonhosted.org/packages/44/46/466269e833f1c4718d6cd496ffe20c56c9c8d013486ff66b4f69c302a68d/cryptography-46.0.6-cp38-abi3-musllinux_1_2_x86_64.whl", hash = "sha256:6617f67b1606dfd9fe4dbfa354a9508d4a6d37afe30306fe6c101b7ce3274b72", size = 4659255 }, + { url = "https://files.pythonhosted.org/packages/0a/09/ddc5f630cc32287d2c953fc5d32705e63ec73e37308e5120955316f53827/cryptography-46.0.6-cp38-abi3-win32.whl", hash = "sha256:7f6690b6c55e9c5332c0b59b9c8a3fb232ebf059094c17f9019a51e9827df91c", size = 3010660 }, + { url = "https://files.pythonhosted.org/packages/1b/82/ca4893968aeb2709aacfb57a30dec6fa2ab25b10fa9f064b8882ce33f599/cryptography-46.0.6-cp38-abi3-win_amd64.whl", hash = "sha256:79e865c642cfc5c0b3eb12af83c35c5aeff4fa5c672dc28c43721c2c9fdd2f0f", size = 3471160 }, +] + [[package]] name = "fastapi" version = "0.135.2" @@ -168,6 +270,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008 }, ] +[[package]] +name = "pycparser" +version = "3.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/1b/7d/92392ff7815c21062bea51aa7b87d45576f649f16458d78b7cf94b9ab2e6/pycparser-3.0.tar.gz", hash = "sha256:600f49d217304a5902ac3c37e1281c9fe94e4d0489de643a9504c5cdfdfc6b29", size = 103492 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/0c/c3/44f3fbbfa403ea2a7c779186dc20772604442dde72947e7d01069cbe98e3/pycparser-3.0-py3-none-any.whl", hash = "sha256:b727414169a36b7d524c1c3e31839a521725078d7b2ff038656844266160a992", size = 48172 }, +] + [[package]] name = "pydantic" version = "2.12.5" @@ -236,6 +347,18 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/9f/ed/068e41660b832bb0b1aa5b58011dea2a3fe0ba7861ff38c4d4904c1c1a99/pydantic_core-2.41.5-cp314-cp314t-win_arm64.whl", hash = "sha256:35b44f37a3199f771c3eaa53051bc8a70cd7b54f333531c59e29fd4db5d15008", size = 1974769 }, ] +[[package]] +name = "python-dateutil" +version = "2.9.0.post0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "six" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/66/c0/0c8b6ad9f17a802ee498c46e004a0eb49bc148f2fd230864601a86dcf6db/python-dateutil-2.9.0.post0.tar.gz", hash = "sha256:37dd54208da7e1cd875388217d5e00ebd4179249f90fb72437e91a35459a0ad3", size = 342432 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ec/57/56b9bcc3c9c6a792fcbaf139543cee77261f3651ca9da0c93f5c1221264b/python_dateutil-2.9.0.post0-py2.py3-none-any.whl", hash = "sha256:a8b2bc7bffae282281c8140a97d3aa9c14da0b136dfe83f850eea9a5f7470427", size = 229892 }, +] + [[package]] name = "python-dotenv" version = "1.2.2" @@ -290,6 +413,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/f1/12/de94a39c2ef588c7e6455cfbe7343d3b2dc9d6b6b2f40c4c6565744c873d/pyyaml-6.0.3-cp314-cp314t-win_arm64.whl", hash = "sha256:ebc55a14a21cb14062aa4162f906cd962b28e2e9ea38f9b4391244cd8de4ae0b", size = 149341 }, ] +[[package]] +name = "six" +version = "1.17.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/94/e7/b2c673351809dca68a0e064b6af791aa332cf192da575fd474ed7d6f16a2/six-1.17.0.tar.gz", hash = "sha256:ff70335d468e7eb6ec65b95b99d3a2836546063f63acc5171de367e834932a81", size = 34031 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/b7/ce/149a00dd41f10bc29e5921b496af8b574d8413afcd5e30dfa0ed46c2cc5e/six-1.17.0-py2.py3-none-any.whl", hash = "sha256:4721f391ed90541fddacab5acf947aa0d3dc7d27b2e1e8eda2be8970586c3274", size = 11050 }, +] + [[package]] name = "starlette" version = "1.0.0" @@ -323,6 +455,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/dc/9b/47798a6c91d8bdb567fe2698fe81e0c6b7cb7ef4d13da4114b41d239f65d/typing_inspection-0.4.2-py3-none-any.whl", hash = "sha256:4ed1cacbdc298c220f1bd249ed5287caa16f34d44ef4e9c3d0cbad5b521545e7", size = 14611 }, ] +[[package]] +name = "urllib3" +version = "2.6.3" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/c7/24/5f1b3bdffd70275f6661c76461e25f024d5a38a46f04aaca912426a2b1d3/urllib3-2.6.3.tar.gz", hash = "sha256:1b62b6884944a57dbe321509ab94fd4d3b307075e0c2eae991ac71ee15ad38ed", size = 435556 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/39/08/aaaad47bc4e9dc8c725e68f9d04865dbcb2052843ff09c97b08904852d84/urllib3-2.6.3-py3-none-any.whl", hash = "sha256:bf272323e553dfb2e87d9bfd225ca7b0f467b919d7bbd355436d3fd37cb0acd4", size = 131584 }, +] + [[package]] name = "uvicorn" version = "0.42.0" @@ -373,6 +514,29 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/e4/16/c1fd27e9549f3c4baf1dc9c20c456cd2f822dbf8de9f463824b0c0357e06/uvloop-0.22.1-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:6cde23eeda1a25c75b2e07d39970f3374105d5eafbaab2a4482be82f272d5a5e", size = 4296730 }, ] +[[package]] +name = "volcengine-python-sdk" +version = "5.0.21" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "certifi" }, + { name = "python-dateutil" }, + { name = "six" }, + { name = "urllib3" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/0a/5e/1d1c1ffc27cd552df55bd75e43b5160d5a5224c2459f8cafe04982921340/volcengine_python_sdk-5.0.21.tar.gz", hash = "sha256:324eded08082fcc65c55c304aca62f5bf1bc5dc472d8ed0bb9b50bdffb768a9b", size = 8283723 } +wheels = [ + { url = "https://files.pythonhosted.org/packages/41/0e/4fdb25614ba83c42135b5eeb5d182ac22493bd7c221dd3477090c3c15897/volcengine_python_sdk-5.0.21-py2.py3-none-any.whl", hash = "sha256:a478bdf3036d8b2e42c19b04c9b708018316a4daac8d8cd58b882074e9d03546", size = 32571307 }, +] + +[package.optional-dependencies] +ark = [ + { name = "anyio" }, + { name = "cryptography" }, + { name = "httpx" }, + { name = "pydantic" }, +] + [[package]] name = "watchfiles" version = "1.1.1"