chore: version 2.7.0

* feat: 流式输出内容

* fix: 修复异常状态

* feat: markdown 链接颜色

.env

@@ -2,3 +2,6 @@
 VITE_GLOB_API_URL=/api
 
 VITE_APP_API_BASE_URL=http://localhost:3002/
+
+# Glob API Timeout (ms)
+VITE_GLOB_API_TIMEOUT=100000

.vscode/settings.json

@@ -25,6 +25,7 @@
     "chatgpt",
     "chenzhaoyu",
     "commitlint",
+    "davinci",
     "dockerhub",
     "esno",
     "GPTAPI",

CHANGELOG.md

@@ -1,3 +1,39 @@
+## v2.7.0
+
+`2023-02-23`
+
+### Feature
+- 使用消息流返回信息，反应更迅速
+
+### Enhancement
+- 样式的一点小改动
+
+## v2.6.2
+
+`2023-02-22`
+### BugFix
+- 还原修改代理导致的异常问题
+
+## v2.6.1
+
+`2023-02-22`
+
+### Feature
+- 新增 `Railway` 部署模版
+
+### BugFix
+- 手动打包 `Proxy` 问题
+
+## v2.6.0
+
+`2023-02-21`
+### Feature
+- 新增对 `网页 accessToken` 调用 `ChatGPT`，更智能不过不太稳定 [#51](https://github.com/Chanzhaoyu/chatgpt-web/issues/51)
+- 前端页面设置按钮显示查看当前后端服务配置
+
+### Enhancement
+- 新增 `TIMEOUT_MS` 环境变量设定后端超时时常（单位：毫秒）[#62](https://github.com/Chanzhaoyu/chatgpt-web/issues/62)
+
 ## v2.5.2
 
 `2023-02-21`

README.md

@@ -1,13 +1,69 @@
 # ChatGPT Web
 
-使用 express 和 vue3 搭建的 ChartGPT 演示网页
+> 使用 `express` 和 `vue3` 搭建的支持 `ChatGPT` 双模型演示网页
 
 ![cover](./docs/cover.png)
 ![cover2](./docs/cover2.png)
 
-> 提示：目前 `OpenAI` 开放的模型最高只有 `GPT-3`，和现在网页所使用的 `GPT-3.5` 或 `GPT-4` 有很大差距，需要等官方开放最新的模型接口。
+- [ChatGPT Web](#chatgpt-web)
+	- [介绍](#介绍)
+	- [待实现路线](#待实现路线)
+	- [前置要求](#前置要求)
+		- [Node](#node)
+		- [PNPM](#pnpm)
+		- [填写密钥](#填写密钥)
+	- [安装依赖](#安装依赖)
+		- [后端](#后端)
+		- [前端](#前端)
+	- [测试环境运行](#测试环境运行)
+		- [后端服务](#后端服务)
+		- [前端网页](#前端网页)
+	- [打包](#打包)
+		- [使用 Docker](#使用-docker)
+			- [Docker 参数示例](#docker-参数示例)
+			- [Docker build \& Run](#docker-build--run)
+			- [Docker compose](#docker-compose)
+		- [使用 Railway 部署](#使用-railway-部署)
+			- [Railway 环境变量](#railway-环境变量)
+		- [手动打包](#手动打包)
+			- [后端服务](#后端服务-1)
+			- [前端网页](#前端网页-1)
+	- [常见问题](#常见问题)
+	- [参与贡献](#参与贡献)
+	- [License](#license)
+## 介绍
+
+支持双模型，提供了两种非官方 `ChatGPT API` 方法
+
+|  方式   | 免费？  | 可靠性  | 质量 |
+|  ----  | ----  | ----  | ----  |
+| `ChatGPTAPI(GPT-3)`  | 否 | 	可靠 | 较笨 |
+| `ChatGPTUnofficialProxyAPI(网页 accessToken)`  | 	是 |  不可靠 | 聪明 |
+
+***Note:*** 网页 `accessToken` 存在大约 8 小时，而且国内地区网络问题更推荐使用 `GPT-3` 的方式
+
+对比：
+1. `ChatGPTAPI` 使用 `text-davinci-003` 通过官方`OpenAI`补全`API`模拟`ChatGPT`（最稳健的方法，但它不是免费的，并且没有使用针对聊天进行微调的模型）
+2. `ChatGPTUnofficialProxyAPI` 使用非官方代理服务器访问 `ChatGPT` 的后端`API`，绕过`Cloudflare`（使用真实的的`ChatGPT`，非常轻量级，但依赖于第三方服务器，并且有速率限制）
+
+切换方式：
+1. 进入 `service/.env` 文件
+2. 使用 `OpenAI API Key` 请填写 `OPENAI_API_KEY` 字段 [(获取 apiKey)](https://platform.openai.com/overview)
+3. 使用 `Web API` 请填写 `OPENAI_ACCESS_TOKEN` 字段 [(获取 accessToken)](https://chat.openai.com/api/auth/session)
+4. 同时存在时以 `OpenAI API Key` 优先
+
+反向代理：
+
+`ChatGPTUnofficialProxyAPI`时可用 [详情](https://github.com/transitive-bullshit/chatgpt-api#reverse-proxy)
+
+```shell
+# service/.env
+API_REVERSE_PROXY=
+```
 
 ## 待实现路线
+[✓] 双模型
+
 [✓] 多会话储存和上下文逻辑
 
 [✓] 对代码等消息类型的格式化美化处理
@@ -22,7 +78,7 @@
 
 ### Node
 
-`node` 需要 `^16 || ^18` 版本（或者 `node >= 14` 需要安装 [fetch polyfill](https://github.com/developit/unfetch#usage-as-a-polyfill)），使用 [nvm](https://github.com/nvm-sh/nvm) 可管理本地多个 `node` 版本
+`node` 需要 `^16 || ^18` 版本（`node >= 14` 需要安装 [fetch polyfill](https://github.com/developit/unfetch#usage-as-a-polyfill)），使用 [nvm](https://github.com/nvm-sh/nvm) 可管理本地多个 `node` 版本
 
 ```shell
 node -v
@@ -34,19 +90,24 @@ node -v
 npm install pnpm -g
 ```
 
-### OpenAI API Key
+### 填写密钥
-注册并获取 [OpenAI API key](https://platform.openai.com/overview) 并填写到本地环境变量
+获取 `Openai Api Key` 或 `accessToken` 并填写本地环境变量 [跳转](#介绍)
+
 ```
 # service/.env 文件
 
-OPENAI_API_KEY='Your key'
+# OpenAI API Key - https://platform.openai.com/overview
+OPENAI_API_KEY=
+
+# change this to an `accessToken` extracted from the ChatGPT site's `https://chat.openai.com/api/auth/session` response
+OPENAI_ACCESS_TOKEN=
 ```
 
 ## 安装依赖
 
 > 为了简便 `后端开发人员` 的了解负担，所以并没有采用前端 `workspace` 模式，而是分文件夹存放。如果只需要前端页面做二次开发，删除 `service` 文件夹即可。
 
-### 后端服务
+### 后端
 
 进入文件夹 `/service` 运行以下命令
 
@@ -54,13 +115,13 @@ OPENAI_API_KEY='Your key'
 pnpm install
 ```
 
-### 网页
+### 前端
 根目录下运行以下命令
 ```shell
 pnpm bootstrap
 ```
 
-## 运行
+## 测试环境运行
 ### 后端服务
 
 进入文件夹 `/service` 运行以下命令
@@ -69,7 +130,7 @@ pnpm bootstrap
 pnpm start
 ```
 
-### 网页
+### 前端网页
 根目录下运行以下命令
 ```shell
 pnpm dev
@@ -78,7 +139,17 @@ pnpm dev
 ## 打包
 
 ### 使用 Docker
-### Docker build & Run
+
+#### Docker 参数示例
+
+- `OPENAI_API_KEY` 二选一
+- `OPENAI_ACCESS_TOKEN`  二选一，同时存在时，`OPENAI_API_KEY` 优先
+- `API_REVERSE_PROXY` 可选，设置 `OPENAI_ACCESS_TOKEN` 时可用 [参考](#介绍)
+- `TIMEOUT_MS` 超时，单位毫秒，可选
+
+![docker](./docs/docker.png)
+
+#### Docker build & Run
 
 ```bash
 docker build -t chatgpt-web .
@@ -93,7 +164,7 @@ docker run --name chatgpt-web -d -p 3002:3002 --env OPENAI_API_KEY=your_api_key
 http://localhost:3002/
 ```
 
-### Docker compose
+#### Docker compose
 
 [Hub 地址](https://hub.docker.com/repository/docker/chenzhaoyu94/chatgpt-web/general)
 
@@ -106,12 +177,34 @@ services:
     ports:
       - 3002:3002
     environment:
+      # 二选一
       OPENAI_API_KEY: xxxxxx
+      # 二选一
+      OPENAI_ACCESS_TOKEN: xxxxxx
+      # 反向代理，可选
+      API_REVERSE_PROXY: xxx
+      # 超时，单位毫秒，可选
+      TIMEOUT_MS: 60000
 ```
 
+###  使用 Railway 部署
 
-## 手动打包
+[![Deploy on Railway](https://railway.app/button.svg)](https://railway.app/new/template/yytmgc)
-### 后端服务
+
+#### Railway 环境变量
+
+| 环境变量名称                | 必填 | 备注                    |
+| --------------------------- | ---- | ----------------------- |
+| `PORT` | 必填    | 默认 `3002`  |
+| `TIMEOUT_MS` | 可选    | 超时时间，单位毫秒，   |
+| `OPENAI_API_KEY` | `OpenAI API` 二选一    | 使用 `OpenAI API` 所需的 `apiKey` [(获取 apiKey)](https://platform.openai.com/overview)   |
+| `OPENAI_ACCESS_TOKEN` | `Web API` 二选一   | 使用 `Web API` 所需的 `accessToken` [(获取 accessToken)](https://chat.openai.com/api/auth/session)   |
+| `API_REVERSE_PROXY` | 可选，`Web API` 时可用    | `Web API` 反向代理地址 [详情](https://github.com/transitive-bullshit/chatgpt-api#reverse-proxy)   |
+
+> 注意: `Railway` 修改环境变量会重新 `Deploy`
+
+### 手动打包
+#### 后端服务
 > 如果你不需要本项目的 `node` 接口，可以省略如下操作
 
 复制 `service` 文件夹到你有 `node` 服务环境的服务器上。
@@ -129,7 +222,7 @@ pnpm prod
 
 PS: 不进行打包，直接在服务器上运行 `pnpm start` 也可
 
-### 前端打包
+#### 前端网页
 
 1、修改根目录下 `.env` 内 `VITE_APP_API_BASE_URL` 为你的实际后端接口地址
 
@@ -141,7 +234,7 @@ PS: 不进行打包，直接在服务器上运行 `pnpm start` 也可
 pnpm build
 ```
 
-### 常见问题
+## 常见问题
 Q: 为什么 `Git` 提交总是报错？
 
 A: 因为有提交信息验证，请遵循 [Commit 指南](./CONTRIBUTING.md)

config/index.ts

@@ -0,0 +1 @@
+export * from './proxy'

config/proxy.ts

@@ -0,0 +1,16 @@
+import type { ProxyOptions } from 'vite'
+
+export function createViteProxy(isOpenProxy: boolean, viteEnv: ImportMetaEnv) {
+  if (!isOpenProxy)
+    return
+
+  const proxy: Record<string, string | ProxyOptions> = {
+    '/api': {
+      target: viteEnv.VITE_GLOB_API_URL,
+      changeOrigin: true,
+      rewrite: path => path.replace(/^\/api/, ''),
+    },
+  }
+
+  return proxy
+}

package.json

@@ -1,6 +1,6 @@
 {
   "name": "chatgpt-web",
-  "version": "2.5.2",
+  "version": "2.7.0",
   "private": false,
   "description": "ChatGPT Web",
   "author": "ChenZhaoYu <chenzhaoyu1994@gmail.com>",

service/.env

@@ -1,2 +1,11 @@
 # OpenAI API Key - https://platform.openai.com/overview
 OPENAI_API_KEY=
+
+# change this to an `accessToken` extracted from the ChatGPT site's `https://chat.openai.com/api/auth/session` response
+OPENAI_ACCESS_TOKEN=
+
+# Reverse Proxy
+API_REVERSE_PROXY=
+
+# timeout
+TIMEOUT_MS=60000

service/package.json

@@ -15,6 +15,7 @@
   },
   "scripts": {
     "start": "esno ./src/index.ts",
+    "dev": "esno watch ./src/index.ts",
     "prod": "esno ./build/index.js",
     "build": "pnpm clean && tsup",
     "clean": "rimraf build",
@@ -23,7 +24,7 @@
     "common:cleanup": "rimraf node_modules && rimraf pnpm-lock.yaml"
   },
   "dependencies": {
-    "chatgpt": "^4.7.1",
+    "chatgpt": "^4.7.2",
     "dotenv": "^16.0.3",
     "esno": "^0.16.3",
     "express": "^4.18.2",

service/pnpm-lock.yaml

@@ -4,7 +4,7 @@ specifiers:
   '@antfu/eslint-config': ^0.35.2
   '@types/express': ^4.17.17
   '@types/node': ^18.14.0
-  chatgpt: ^4.7.1
+  chatgpt: ^4.7.2
   dotenv: ^16.0.3
   eslint: ^8.34.0
   esno: ^0.16.3
@@ -15,7 +15,7 @@ specifiers:
   typescript: ^4.9.5
 
 dependencies:
-  chatgpt: 4.7.1
+  chatgpt: 4.7.2
   dotenv: 16.0.3
   esno: 0.16.3
   express: 4.18.2
@@ -878,8 +878,8 @@ packages:
     resolution: {integrity: sha512-mKKUkUbhPpQlCOfIuZkvSEgktjPFIsZKRRbC6KWVEMvlzblj3i3asQv5ODsrwt0N3pHAEvjP8KTQPHkp0+6jOg==}
     dev: true
 
-  /chatgpt/4.7.1:
+  /chatgpt/4.7.2:
-    resolution: {integrity: sha512-FRXfpjn//Y4gUMcUo60W5byJ0CbFhC1Xp3PCm2qcBthBYFbC+LyRrwxvSVTdNwgQywHV4Pc5SFkaZ72f5rCNdQ==}
+    resolution: {integrity: sha512-c5CNqvB98IMEz/Byopwu5FlXGS3w/3iNiZITdDlcZLue4VSjEfzMRWrOrdGidzcE+ud2My6nO8/sSnY7W04WJA==}
     engines: {node: '>=14'}
     hasBin: true
     dependencies:

service/src/chatgpt.ts

@@ -1,27 +1,46 @@
 import * as dotenv from 'dotenv'
 import 'isomorphic-fetch'
-import type { ChatGPTAPI, SendMessageOptions } from 'chatgpt'
+import type { ChatGPTAPI, ChatMessage, SendMessageOptions } from 'chatgpt'
+import { ChatGPTUnofficialProxyAPI } from 'chatgpt'
 import { sendResponse } from './utils'
 
-export interface ChatContext {
+dotenv.config()
+
+let apiModel: 'ChatGPTAPI' | 'ChatGPTUnofficialProxyAPI' | undefined
+
+interface ChatContext {
   conversationId?: string
   parentMessageId?: string
 }
 
-dotenv.config()
+const timeoutMs: number = !isNaN(+process.env.TIMEOUT_MS) ? +process.env.TIMEOUT_MS : 30 * 1000
 
-const apiKey = process.env.OPENAI_API_KEY
+if (!process.env.OPENAI_API_KEY && !process.env.OPENAI_ACCESS_TOKEN)
+  throw new Error('Missing OPENAI_API_KEY or OPENAI_ACCESS_TOKEN environment variable')
 
-if (apiKey === undefined)
+let api: ChatGPTAPI | ChatGPTUnofficialProxyAPI
-  throw new Error('OPENAI_API_KEY is not defined')
-
-let api: ChatGPTAPI
 
 // To use ESM in CommonJS, you can use a dynamic import
 (async () => {
   // More Info: https://github.com/transitive-bullshit/chatgpt-api
   const { ChatGPTAPI } = await import('chatgpt')
-  api = new ChatGPTAPI({ apiKey: process.env.OPENAI_API_KEY })
+
+  if (process.env.OPENAI_API_KEY) {
+    api = new ChatGPTAPI({ apiKey: process.env.OPENAI_API_KEY })
+    apiModel = 'ChatGPTAPI'
+  }
+  else {
+    let options = {}
+
+    if (process.env.API_REVERSE_PROXY)
+      options = { apiReverseProxyUrl: process.env.API_REVERSE_PROXY }
+
+    api = new ChatGPTUnofficialProxyAPI({
+      accessToken: process.env.OPENAI_ACCESS_TOKEN,
+      ...options,
+    })
+    apiModel = 'ChatGPTUnofficialProxyAPI'
+  }
 })()
 
 async function chatReply(
@@ -32,7 +51,7 @@ async function chatReply(
     return sendResponse({ type: 'Fail', message: 'Message is empty' })
 
   try {
-    let options: SendMessageOptions = { timeoutMs: 30 * 1000 }
+    let options: SendMessageOptions = { timeoutMs }
 
     if (lastContext)
       options = { ...lastContext }
@@ -46,4 +65,45 @@ async function chatReply(
   }
 }
 
-export { chatReply }
+async function chatReplyProcess(
+  message: string,
+  lastContext?: { conversationId?: string; parentMessageId?: string },
+  process?: (chat: ChatMessage) => void,
+) {
+  if (!message)
+    return sendResponse({ type: 'Fail', message: 'Message is empty' })
+
+  try {
+    let options: SendMessageOptions = { timeoutMs }
+
+    if (lastContext)
+      options = { ...lastContext }
+
+    const response = await api.sendMessage(message, {
+      ...options,
+      onProgress: (partialResponse) => {
+        process?.(partialResponse)
+      },
+    })
+
+    return sendResponse({ type: 'Success', data: response })
+  }
+  catch (error: any) {
+    return sendResponse({ type: 'Fail', message: error.message })
+  }
+}
+
+async function chatConfig() {
+  return sendResponse({
+    type: 'Success',
+    data: {
+      apiModel,
+      reverseProxy: process.env.API_REVERSE_PROXY,
+      timeoutMs,
+    },
+  })
+}
+
+export type { ChatContext, ChatMessage }
+
+export { chatReply, chatReplyProcess, chatConfig }

service/src/index.ts

@@ -1,6 +1,6 @@
 import express from 'express'
-import type { ChatContext } from './chatgpt'
+import type { ChatContext, ChatMessage } from './chatgpt'
-import { chatReply } from './chatgpt'
+import { chatConfig, chatReply, chatReplyProcess } from './chatgpt'
 
 const app = express()
 const router = express.Router()
@@ -26,6 +26,33 @@ router.post('/chat', async (req, res) => {
   }
 })
 
+router.post('/chat-process', async (req, res) => {
+  res.setHeader('Content-type', 'application/octet-stream')
+
+  try {
+    const { prompt, options = {} } = req.body as { prompt: string; options?: ChatContext }
+    await chatReplyProcess(prompt, options, (chat: ChatMessage) => {
+      res.write(JSON.stringify(chat))
+    })
+  }
+  catch (error) {
+    res.write(JSON.stringify(error))
+  }
+  finally {
+    res.end()
+  }
+})
+
+router.post('/config', async (req, res) => {
+  try {
+    const response = await chatConfig()
+    res.send(response)
+  }
+  catch (error) {
+    res.send(error)
+  }
+})
+
 app.use('', router)
 app.use('/api', router)
 

src/api/index.ts

@@ -1,4 +1,4 @@
-import type { GenericAbortSignal } from 'axios'
+import type { AxiosProgressEvent, GenericAbortSignal } from 'axios'
 import { post } from '@/utils/request'
 
 export function fetchChatAPI<T = any>(
@@ -12,3 +12,24 @@ export function fetchChatAPI<T = any>(
     signal,
   })
 }
+
+export function fetchChatAPIProcess<T = any>(
+  params: {
+    prompt: string
+    options?: { conversationId?: string; parentMessageId?: string }
+    signal?: GenericAbortSignal
+    onDownloadProgress?: (progressEvent: AxiosProgressEvent) => void },
+) {
+  return post<T>({
+    url: '/chat-process',
+    data: { prompt: params.prompt, options: params.options },
+    signal: params.signal,
+    onDownloadProgress: params.onDownloadProgress,
+  })
+}
+
+export function fetchChatConfig<T = any>() {
+  return post<T>({
+    url: '/config',
+  })
+}

src/components/common/Setting/index.vue

@@ -0,0 +1,67 @@
+<script setup lang='ts'>
+import { computed, ref, watch } from 'vue'
+import { NCard, NModal } from 'naive-ui'
+import { fetchChatConfig } from '@/api'
+
+interface Props {
+  visible: boolean
+}
+
+interface Emit {
+  (e: 'update:visible', visible: boolean): void
+}
+
+interface ConfigState {
+  timeoutMs?: number
+  reverseProxy?: string
+  apiModel?: string
+}
+
+const props = defineProps<Props>()
+
+const emit = defineEmits<Emit>()
+
+const show = computed({
+  get() {
+    return props.visible
+  },
+  set(visible: boolean) {
+    emit('update:visible', visible)
+  },
+})
+
+const config = ref<ConfigState>()
+
+async function fetchConfig() {
+  try {
+    const { data } = await fetchChatConfig<ConfigState>()
+    config.value = data
+  }
+  catch (error) {
+    // ...
+  }
+}
+
+watch(
+  () => props.visible,
+  (val) => {
+    if (val)
+      fetchConfig()
+  },
+)
+</script>
+
+<template>
+  <NModal v-model:show="show" style="width: 80%; max-width: 460px;">
+    <NCard>
+      <div class="space-y-4">
+        <h1 class="text-xl font-bold">
+          当前后台设置
+        </h1>
+        <p>API方式：{{ config?.apiModel ?? '-' }}</p>
+        <p>反向代理：{{ config?.reverseProxy ?? '-' }}</p>
+        <p>超时时间：{{ config?.timeoutMs ?? '-' }}</p>
+      </div>
+    </NCard>
+  </NModal>
+</template>

src/components/common/index.ts

@@ -2,5 +2,6 @@ import HoverButton from './HoverButton/index.vue'
 import NaiveProvider from './NaiveProvider/index.vue'
 import SvgIcon from './SvgIcon/index.vue'
 import UserAvatar from './UserAvatar/index.vue'
+import Setting from './Setting/index.vue'
 
-export { HoverButton, NaiveProvider, SvgIcon, UserAvatar }
+export { HoverButton, NaiveProvider, SvgIcon, UserAvatar, Setting }

src/typings/env.d.ts

@@ -2,5 +2,6 @@
 
 interface ImportMetaEnv {
 	readonly VITE_GLOB_API_URL: string;
+	readonly VITE_GLOB_API_TIMEOUT: string;
 	readonly VITE_APP_API_BASE_URL: string;
 }

src/utils/functions/includeCode.ts

@@ -1,8 +1,6 @@
 function includeCode(text: string | null | undefined) {
   const regexp = /^(?:\s{4}|\t).+/gm
-  if (text?.includes(' = ') || text?.match(regexp))
+  return !!(text?.includes(' = ') || text?.match(regexp))
-    return true
-  return false
 }
 
 export default includeCode

src/utils/request/axios.ts

@@ -2,7 +2,7 @@ import axios, { type AxiosResponse } from 'axios'
 
 const service = axios.create({
   baseURL: import.meta.env.VITE_GLOB_API_URL,
-  timeout: 30 * 1000,
+  timeout: !isNaN(+import.meta.env.VITE_GLOB_API_TIMEOUT) ? Number(import.meta.env.VITE_GLOB_API_TIMEOUT) : 60 * 1000,
 })
 
 service.interceptors.request.use(

src/utils/request/index.ts

@@ -1,4 +1,4 @@
-import type { AxiosResponse, GenericAbortSignal } from 'axios'
+import type { AxiosProgressEvent, AxiosResponse, GenericAbortSignal } from 'axios'
 import request from './axios'
 
 export interface HttpOption {
@@ -6,6 +6,7 @@ export interface HttpOption {
   data?: any
   method?: string
   headers?: any
+  onDownloadProgress?: (progressEvent: AxiosProgressEvent) => void
   signal?: GenericAbortSignal
   beforeRequest?: () => void
   afterRequest?: () => void
@@ -17,9 +18,11 @@ export interface Response<T = any> {
   status: string
 }
 
-function http<T = any>({ url, data, method, headers, signal, beforeRequest, afterRequest }: HttpOption) {
+function http<T = any>(
+  { url, data, method, headers, onDownloadProgress, signal, beforeRequest, afterRequest }: HttpOption,
+) {
   const successHandler = (res: AxiosResponse<Response<T>>) => {
-    if (res.data.status === 'Success')
+    if (res.data.status === 'Success' || typeof res.data === 'string')
       return res.data
 
     return Promise.reject(res.data)
@@ -37,17 +40,18 @@ function http<T = any>({ url, data, method, headers, signal, beforeRequest, afte
   const params = Object.assign(typeof data === 'function' ? data() : data ?? {}, {})
 
   return method === 'GET'
-    ? request.get(url, { params, signal }).then(successHandler, failHandler)
+    ? request.get(url, { params, signal, onDownloadProgress }).then(successHandler, failHandler)
-    : request.post(url, params, { headers, signal }).then(successHandler, failHandler)
+    : request.post(url, params, { headers, signal, onDownloadProgress }).then(successHandler, failHandler)
 }
 
 export function get<T = any>(
-  { url, data, method = 'GET', signal, beforeRequest, afterRequest }: HttpOption,
+  { url, data, method = 'GET', onDownloadProgress, signal, beforeRequest, afterRequest }: HttpOption,
 ): Promise<Response<T>> {
   return http<T>({
     url,
     method,
     data,
+    onDownloadProgress,
     signal,
     beforeRequest,
     afterRequest,
@@ -55,13 +59,14 @@ export function get<T = any>(
 }
 
 export function post<T = any>(
-  { url, data, method = 'POST', headers, signal, beforeRequest, afterRequest }: HttpOption,
+  { url, data, method = 'POST', headers, onDownloadProgress, signal, beforeRequest, afterRequest }: HttpOption,
 ): Promise<Response<T>> {
   return http<T>({
     url,
     method,
     data,
     headers,
+    onDownloadProgress,
     signal,
     beforeRequest,
     afterRequest,

src/views/chat/components/Message/Text.vue

@@ -15,7 +15,7 @@ const props = defineProps<Props>()
 const wrapClass = computed(() => {
   return [
     'text-wrap',
-    'p-2',
+    'p-3',
     'min-w-[20px]',
     'rounded-md',
     props.inversion ? 'bg-[#d2f9d1]' : 'bg-[#f4f6f8]',
@@ -51,6 +51,9 @@ const text = computed(() => {
     max-width: 100%;
     vertical-align: middle;
   }
+  a {
+    color: #2d5cf6
+  }
 }
 
 .hljs {

src/views/chat/index.vue

@@ -8,7 +8,7 @@ import { useChat } from './hooks/useChat'
 import { HoverButton, SvgIcon } from '@/components/common'
 import { useBasicLayout } from '@/hooks/useBasicLayout'
 import { useChatStore } from '@/store'
-import { fetchChatAPI } from '@/api'
+import { fetchChatAPIProcess } from '@/api'
 
 let controller = new AbortController()
 
@@ -80,22 +80,39 @@ async function onConversation() {
   )
   scrollToBottom()
 
+  let offset = 0
   try {
-    const { data } = await fetchChatAPI<Chat.ConversationResponse>(message, options, controller.signal)
+    await fetchChatAPIProcess<Chat.ConversationResponse>({
-    updateChat(
+      prompt: message,
-      +uuid,
+      options,
-      dataSources.value.length - 1,
+      signal: controller.signal,
-      {
+      onDownloadProgress: ({ event }) => {
-        dateTime: new Date().toLocaleString(),
+        const xhr = event.target
-        text: data.text ?? '',
+        const { responseText } = xhr
-        inversion: false,
+        const chunk = responseText.substring(offset)
-        error: false,
+        offset = responseText.length
-        loading: false,
+        try {
-        conversationOptions: { conversationId: data.conversationId, parentMessageId: data.id },
+          const data = JSON.parse(chunk)
-        requestOptions: { prompt: message, options: { ...options } },
+          updateChat(
+            +uuid,
+            dataSources.value.length - 1,
+            {
+              dateTime: new Date().toLocaleString(),
+              text: data.text ?? '',
+              inversion: false,
+              error: false,
+              loading: false,
+              conversationOptions: { conversationId: data.conversationId, parentMessageId: data.id },
+              requestOptions: { prompt: message, options: { ...options } },
+            },
+          )
+          scrollToBottom()
+        }
+        catch (error) {
+          //
+        }
       },
-    )
+    })
-    scrollToBottom()
   }
   catch (error: any) {
     let errorMessage = error?.message ?? 'Something went wrong, please try again later.'
@@ -119,6 +136,7 @@ async function onConversation() {
     scrollToBottom()
   }
   finally {
+    offset = 0
     loading.value = false
   }
 }
@@ -154,24 +172,41 @@ async function onRegenerate(index: number) {
     },
   )
 
+  let offset = 0
   try {
-    const { data } = await fetchChatAPI<Chat.ConversationResponse>(message, options, controller.signal)
+    await fetchChatAPIProcess<Chat.ConversationResponse>({
-    updateChat(
+      prompt: message,
-      +uuid,
+      options,
-      index,
+      signal: controller.signal,
-      {
+      onDownloadProgress: ({ event }) => {
-        dateTime: new Date().toLocaleString(),
+        const xhr = event.target
-        text: data.text ?? '',
+        const { responseText } = xhr
-        inversion: false,
+        const chunk = responseText.substring(offset)
-        error: false,
+        offset = responseText.length
-        loading: false,
+        try {
-        conversationOptions: { conversationId: data.conversationId, parentMessageId: data.id },
+          const data = JSON.parse(chunk)
-        requestOptions: { prompt: message, ...options },
+          updateChat(
+            +uuid,
+            index,
+            {
+              dateTime: new Date().toLocaleString(),
+              text: data.text ?? '',
+              inversion: false,
+              error: false,
+              loading: false,
+              conversationOptions: { conversationId: data.conversationId, parentMessageId: data.id },
+              requestOptions: { prompt: message, ...options },
+            },
+          )
+        }
+        catch (error) {
+          //
+        }
       },
-    )
+    })
   }
   catch (error: any) {
-    let errorMessage = 'Something went wrong, please try again later.'
+    let errorMessage = error?.message ?? 'Something went wrong, please try again later.'
 
     if (error.message === 'canceled')
       errorMessage = 'Request canceled. Please try again.'
@@ -192,6 +227,7 @@ async function onRegenerate(index: number) {
   }
   finally {
     loading.value = false
+    offset = 0
   }
 }
 

src/views/chat/layout/sider/Footer.vue

@@ -0,0 +1,19 @@
+<script setup lang='ts'>
+import { ref } from 'vue'
+import { HoverButton, Setting, SvgIcon, UserAvatar } from '@/components/common'
+
+const show = ref(false)
+</script>
+
+<template>
+  <footer class="flex items-center justify-between min-w-0 p-4 overflow-hidden border-t">
+    <UserAvatar />
+    <HoverButton tooltip="Setting" @click="show = true">
+      <span class="text-xl text-[#4f555e]">
+        <SvgIcon icon="ri:settings-4-line" />
+      </span>
+    </HoverButton>
+
+    <Setting v-model:visible="show" />
+  </footer>
+</template>

src/views/chat/layout/sider/index.vue

@@ -3,7 +3,7 @@ import type { CSSProperties } from 'vue'
 import { computed, watch } from 'vue'
 import { NButton, NLayoutSider } from 'naive-ui'
 import List from './List.vue'
-import { HoverButton, SvgIcon, UserAvatar } from '@/components/common'
+import Footer from './Footer.vue'
 import { useAppStore, useChatStore } from '@/store'
 import { useBasicLayout } from '@/hooks/useBasicLayout'
 
@@ -67,14 +67,7 @@ watch(
           <List />
         </div>
       </main>
-      <footer class="flex items-center justify-between min-w-0 p-4 overflow-hidden border-t">
+      <Footer />
-        <UserAvatar />
-        <HoverButton tooltip="Setting">
-          <span class="text-xl text-[#4f555e]">
-            <SvgIcon icon="ri:settings-4-line" />
-          </span>
-        </HoverButton>
-      </footer>
     </div>
   </NLayoutSider>
   <template v-if="isMobile">

vite.config.ts

@@ -13,8 +13,8 @@ export default defineConfig((env) => {
     },
     plugins: [vue()],
     server: {
-      port: 1002,
       host: '0.0.0.0',
+      port: 1002,
       open: false,
       proxy: {
         '/api': {