feat: 支持 accessToken 请求 web api 调用 (#80)

* feat: 支持 markdown 格式和图片

* perf: 重载的时候滚动条保持

* chore: version 2.5.2

* feat: 添加文字换行

* chore: 添加新封面

* chore: 更新 cover

* feat: 支持 web api 的形式

* feat: 支持新模型和调整超时

* feat: 添加反向代理

* chore: 更新 README.md

* feat: 添加超时和反向代理显示

* chore: version 2.6.0

* chore: update README
main
Redon 2 years ago committed by GitHub
parent ac9536ab87
commit f40048fb08
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

@ -2,3 +2,5 @@
VITE_GLOB_API_URL=/api VITE_GLOB_API_URL=/api
VITE_APP_API_BASE_URL=http://localhost:3002/ VITE_APP_API_BASE_URL=http://localhost:3002/
VITE_GLOB_API_TIMEOUT=100000

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

@ -1,3 +1,13 @@
## 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 ## v2.5.2
`2023-02-21` `2023-02-21`

@ -1,13 +1,43 @@
# ChatGPT Web # ChatGPT Web
使用 express 和 vue3 搭建的 ChartGPT 演示网页 使用 `express``vue3` 搭建的支持 `ChatGPT` 双模型演示网页
![cover](./docs/cover.png) ![cover](./docs/cover.png)
![cover2](./docs/cover2.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``GPT-4` 有很大差距,需要等官方开放最新的模型接口。 ## 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 ## 待实现路线
[✓] 双模型
[✓] 多会话储存和上下文逻辑 [✓] 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 [✓] 对代码等消息类型的格式化美化处理
@ -34,12 +64,17 @@ node -v
npm install pnpm -g 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``accessToken` 并填写本地环境变量 [跳转](#介绍)
``` ```
# service/.env 文件 # 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 ## 安装依赖
@ -60,7 +95,7 @@ pnpm install
pnpm bootstrap pnpm bootstrap
``` ```
## 运行 ## 测试环境运行
### 后端服务 ### 后端服务
进入文件夹 `/service` 运行以下命令 进入文件夹 `/service` 运行以下命令
@ -69,7 +104,7 @@ pnpm bootstrap
pnpm start pnpm start
``` ```
### 网页 ### 前端网页
根目录下运行以下命令 根目录下运行以下命令
```shell ```shell
pnpm dev pnpm dev
@ -78,6 +113,16 @@ pnpm dev
## 打包 ## 打包
### 使用 Docker ### 使用 Docker
### 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 ### Docker build & Run
```bash ```bash
@ -106,7 +151,14 @@ services:
ports: ports:
- 3002:3002 - 3002:3002
environment: environment:
# 二选一
OPENAI_API_KEY: xxxxxx 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
``` ```
@ -129,7 +181,7 @@ pnpm prod
PS: 不进行打包,直接在服务器上运行 `pnpm start` 也可 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``VITE_APP_API_BASE_URL` 为你的实际后端接口地址 1、修改根目录下 `.env``VITE_APP_API_BASE_URL` 为你的实际后端接口地址

Binary file not shown.

After

Width:  |  Height:  |  Size: 108 KiB

@ -1,6 +1,6 @@
{ {
"name": "chatgpt-web", "name": "chatgpt-web",
"version": "2.5.2", "version": "2.6.0",
"private": false, "private": false,
"description": "ChatGPT Web", "description": "ChatGPT Web",
"author": "ChenZhaoYu <chenzhaoyu1994@gmail.com>", "author": "ChenZhaoYu <chenzhaoyu1994@gmail.com>",

@ -1,2 +1,11 @@
# OpenAI API Key - https://platform.openai.com/overview # OpenAI API Key - https://platform.openai.com/overview
OPENAI_API_KEY= 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

@ -23,7 +23,7 @@
"common:cleanup": "rimraf node_modules && rimraf pnpm-lock.yaml" "common:cleanup": "rimraf node_modules && rimraf pnpm-lock.yaml"
}, },
"dependencies": { "dependencies": {
"chatgpt": "^4.7.1", "chatgpt": "^4.7.2",
"dotenv": "^16.0.3", "dotenv": "^16.0.3",
"esno": "^0.16.3", "esno": "^0.16.3",
"express": "^4.18.2", "express": "^4.18.2",

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

@ -1,27 +1,46 @@
import * as dotenv from 'dotenv' import * as dotenv from 'dotenv'
import 'isomorphic-fetch' import 'isomorphic-fetch'
import type { ChatGPTAPI, SendMessageOptions } from 'chatgpt' import type { ChatGPTAPI, SendMessageOptions } from 'chatgpt'
import { ChatGPTUnofficialProxyAPI } from 'chatgpt'
import { sendResponse } from './utils' import { sendResponse } from './utils'
dotenv.config()
let apiModel: 'ChatGPTAPI' | 'ChatGPTUnofficialProxyAPI' | undefined
export interface ChatContext { export interface ChatContext {
conversationId?: string conversationId?: string
parentMessageId?: 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 (apiKey === undefined) if (!process.env.OPENAI_API_KEY && !process.env.OPENAI_ACCESS_TOKEN)
throw new Error('OPENAI_API_KEY is not defined') throw new Error('Missing OPENAI_API_KEY or OPENAI_ACCESS_TOKEN environment variable')
let api: ChatGPTAPI let api: ChatGPTAPI | ChatGPTUnofficialProxyAPI
// To use ESM in CommonJS, you can use a dynamic import // To use ESM in CommonJS, you can use a dynamic import
(async () => { (async () => {
// More Info: https://github.com/transitive-bullshit/chatgpt-api // More Info: https://github.com/transitive-bullshit/chatgpt-api
const { ChatGPTAPI } = await import('chatgpt') 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( async function chatReply(
@ -32,7 +51,7 @@ async function chatReply(
return sendResponse({ type: 'Fail', message: 'Message is empty' }) return sendResponse({ type: 'Fail', message: 'Message is empty' })
try { try {
let options: SendMessageOptions = { timeoutMs: 30 * 1000 } let options: SendMessageOptions = { timeoutMs }
if (lastContext) if (lastContext)
options = { ...lastContext } options = { ...lastContext }
@ -46,4 +65,15 @@ async function chatReply(
} }
} }
export { chatReply } async function chatConfig() {
return sendResponse({
type: 'Success',
data: {
apiModel,
reverseProxy: process.env.API_REVERSE_PROXY,
timeoutMs,
},
})
}
export { chatReply, chatConfig }

@ -1,6 +1,6 @@
import express from 'express' import express from 'express'
import type { ChatContext } from './chatgpt' import type { ChatContext } from './chatgpt'
import { chatReply } from './chatgpt' import { chatConfig, chatReply } from './chatgpt'
const app = express() const app = express()
const router = express.Router() const router = express.Router()
@ -26,6 +26,16 @@ router.post('/chat', async (req, res) => {
} }
}) })
router.post('/config', async (req, res) => {
try {
const response = await chatConfig()
res.send(response)
}
catch (error) {
res.send(error)
}
})
app.use('', router) app.use('', router)
app.use('/api', router) app.use('/api', router)

@ -12,3 +12,9 @@ export function fetchChatAPI<T = any>(
signal, signal,
}) })
} }
export function fetchChatConfig<T = any>() {
return post<T>({
url: '/config',
})
}

@ -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>

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

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

@ -2,7 +2,7 @@ import axios, { type AxiosResponse } from 'axios'
const service = axios.create({ const service = axios.create({
baseURL: import.meta.env.VITE_GLOB_API_URL, 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( service.interceptors.request.use(

@ -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>

@ -3,7 +3,7 @@ import type { CSSProperties } from 'vue'
import { computed, watch } from 'vue' import { computed, watch } from 'vue'
import { NButton, NLayoutSider } from 'naive-ui' import { NButton, NLayoutSider } from 'naive-ui'
import List from './List.vue' import List from './List.vue'
import { HoverButton, SvgIcon, UserAvatar } from '@/components/common' import Footer from './Footer.vue'
import { useAppStore, useChatStore } from '@/store' import { useAppStore, useChatStore } from '@/store'
import { useBasicLayout } from '@/hooks/useBasicLayout' import { useBasicLayout } from '@/hooks/useBasicLayout'
@ -67,14 +67,7 @@ watch(
<List /> <List />
</div> </div>
</main> </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> </div>
</NLayoutSider> </NLayoutSider>
<template v-if="isMobile"> <template v-if="isMobile">

Loading…
Cancel
Save