This project is forked from Chanzhaoyu/chatgpt-web. In addition to regularly merging this branch, some unique features have been added such as registration and login, setting API key on the front-end page.
Disclaimer: This project is only released on GitHub, under the MIT License, free and for open-source learning purposes. There will be no account selling, paid services, discussion groups, or forums. Beware of fraud.
- ChatGPT Web
Supports dual models, provides two unofficial ChatGPT API
methods:
Method | Free? | Reliability | Quality |
---|---|---|---|
ChatGPTAPI(gpt-3.5-turbo-0301) |
No | Reliable | Relatively clumsy |
ChatGPTUnofficialProxyAPI(Web accessToken) |
Yes | Relatively unreliable | Smart |
Comparison:
ChatGPTAPI
usesgpt-3.5-turbo-0301
to simulateChatGPT
through the officialOpenAI
completionAPI
(the most reliable method, but it is not free and does not use models specifically tuned for chat).ChatGPTUnofficialProxyAPI
accessesChatGPT
's backendAPI
via an unofficial proxy server to bypassCloudflare
(uses the realChatGPT
, is very lightweight, but depends on third-party servers and has rate limits).
Switching Methods:
- Go to the
service/.env.example
file and copy the contents to theservice/.env
file. - For
OpenAI API Key
, fill in theOPENAI_API_KEY
field (Get apiKey). - For
Web API
, fill in theOPENAI_ACCESS_TOKEN
field (Get accessToken). - When both are present,
OpenAI API Key
takes precedence.
Reverse Proxy:
Available when using ChatGPTUnofficialProxyAPI
.Details
# service/.env
API_REVERSE_PROXY=
Environment Variables:
For all parameter variables, check here or see:
/service/.env
[✓] Dual models
[✓] Multiple session storage and context logic
[✓] Formatting and beautifying code-like message types
[✓] Login or Register
[✓] Set API key and other information on the front-end page.
[✓] Data import and export
[✓] Save message to local image
[✓] Multilingual interface
[✓] Interface themes
[✗] More...
node
requires version ^16 || ^18
(node >= 14
requires installation of fetch polyfill), and multiple local node
versions can be managed using nvm.
node -v
If you have not installed pnpm
before:
npm install pnpm -g
Get Openai Api Key
or accessToken
and fill in the local environment variables jump
# service/.env file
# 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=
To make it easier for
backend developers
to understand, we did not use the front-endworkspace
mode, but stored it in different folders. If you only need to do secondary development of the front-end page, delete theservice
folder.
Enter the /service
folder and run the following command
pnpm install
Run the following command in the root directory
pnpm bootstrap
Enter the /service
folder and run the following command
pnpm start
Run the following command in the root directory
pnpm dev
OPENAI_API_KEY
one of twoOPENAI_ACCESS_TOKEN
one of two,OPENAI_API_KEY
takes precedence when both are presentOPENAI_API_BASE_URL
optional, available whenOPENAI_API_KEY
is setOPENAI_API_MODEL
optional, available whenOPENAI_API_KEY
is setAPI_REVERSE_PROXY
optional, available whenOPENAI_ACCESS_TOKEN
is set ReferenceAUTH_SECRET_KEY
Access Password,optionalTIMEOUT_MS
timeout, in milliseconds, optionalSOCKS_PROXY_HOST
optional, effective with SOCKS_PROXY_PORTSOCKS_PROXY_PORT
optional, effective with SOCKS_PROXY_HOSTHTTPS_PROXY
optional, support http,https, socks5ALL_PROXY
optional, support http,https, socks5
docker build -t chatgpt-web .
# foreground operation
docker run --name chatgpt-web --rm -it -p 127.0.0.1:3002:3002 --env OPENAI_API_KEY=your_api_key chatgpt-web
# background operation
docker run --name chatgpt-web -d -p 127.0.0.1:3002:3002 --env OPENAI_API_KEY=your_api_key chatgpt-web
# running address
http://localhost:3002/
version: '3'
services:
app:
image: kerwin1202/chatgpt-web # always use latest, pull the tag image again when updating
container_name: chatgptweb
restart: unless-stopped
ports:
- 3002:3002
depends_on:
- database
environment:
TZ: Asia/Shanghai
# one of two
OPENAI_API_KEY: xxxxxx
# one of two
OPENAI_ACCESS_TOKEN: xxxxxx
# api interface url, optional, available when OPENAI_API_KEY is set
OPENAI_API_BASE_URL: xxxx
# api model, optional, available when OPENAI_API_KEY is set
OPENAI_API_MODEL: xxxx
# reverse proxy, optional
API_REVERSE_PROXY: xxx
# timeout, in milliseconds, optional
TIMEOUT_MS: 60000
# socks proxy, optional, effective with SOCKS_PROXY_PORT
SOCKS_PROXY_HOST: xxxx
# socks proxy port, optional, effective with SOCKS_PROXY_HOST
SOCKS_PROXY_PORT: xxxx
# HTTPS Proxy,optional, support http, https, socks5
HTTPS_PROXY: http://xxx:7890
# Title for site
SITE_TITLE: ChatGpt Web
# access salt,optional Allow login if not empty.
AUTH_SECRET_KEY: xxx
# mongodb's connection string
MONGODB_URL: 'mongodb://chatgpt:xxxx@database:27017'
# Register enabled
REGISTER_ENABLED: true
# After register enabled, Allowed mailbox suffixes for website registration. If empty, any suffix is allowed
REGISTER_MAILS: '@qq.com,@sina.com,@163.com'
# After register enabled, Salt for password encryption
PASSWORD_MD5_SALT: xxx
# After register enabled, super administrator
ROOT_USER: [email protected]
# After register enabled, The website's domain ending without /
SITE_DOMAIN: http://127.0.0.1:3002
# After register enabled, The smtp settings
SMTP_HOST: smtp.exmail.qq.com
SMTP_PORT: 465
SMTP_TSL: true
SMTP_USERNAME: [email protected]
SMTP_PASSWORD: xxx
links:
- database
database:
image: mongo
container_name: chatgptweb-database
restart: unless-stopped
ports:
- '27017:27017'
expose:
- '27017'
volumes:
- mongodb:/data/db
environment:
MONGO_INITDB_ROOT_USERNAME: chatgpt
MONGO_INITDB_ROOT_PASSWORD: xxxx
MONGO_INITDB_DATABASE: chatgpt
volumes:
mongodb: {}
The OPENAI_API_BASE_URL
is optional and only used when setting the OPENAI_API_KEY
.
The OPENAI_API_MODEL
is optional and only used when setting the OPENAI_API_KEY
.
Environment Variable | Required | Description |
---|---|---|
PORT |
Required | Default: 3002 |
AUTH_SECRET_KEY |
Optional | access password |
TIMEOUT_MS |
Optional | Timeout in milliseconds |
OPENAI_API_KEY |
Optional | Required for OpenAI API . apiKey can be obtained from here. |
OPENAI_ACCESS_TOKEN |
Optional | Required for Web API . accessToken can be obtained from here. |
OPENAI_API_BASE_URL |
Optional, only for OpenAI API |
API endpoint. |
OPENAI_API_MODEL |
Optional, only for OpenAI API |
API model. |
API_REVERSE_PROXY |
Optional, only for Web API |
Reverse proxy address for Web API . Details |
SOCKS_PROXY_HOST |
Optional, effective with SOCKS_PROXY_PORT |
Socks proxy. |
SOCKS_PROXY_PORT |
Optional, effective with SOCKS_PROXY_HOST |
Socks proxy port. |
HTTPS_PROXY |
Optional | HTTPS Proxy. |
ALL_PROXY |
Optional | ALL Proxy. |
Note: Changing environment variables in Railway will cause re-deployment.
If you don't need the
node
interface of this project, you can skip the following steps.
Copy the service
folder to a server that has a node
service environment.
# Install
pnpm install
# Build
pnpm build
# Run
pnpm prod
PS: You can also run pnpm start
directly on the server without packaging.
- Refer to the root directory
.env.example
file content to create.env
file, modifyVITE_GLOB_API_URL
in.env
at the root directory to your actual backend interface address. - Run the following command in the root directory and then copy the files in the
dist
folder to the root directory of your website service.
pnpm build
Q: Why does Git always report an error when committing?
A: Because there is submission information verification, please follow the Commit Guidelines.
Q: Where to change the request interface if only the frontend page is used?
A: The VITE_GLOB_API_URL
field in the .env
file at the root directory.
Q: All red when saving the file?
A: For vscode
, please install the recommended plug-in of the project or manually install the Eslint
plug-in.
Q: Why doesn't the frontend have a typewriter effect?
A: One possible reason is that after Nginx reverse proxying, buffering is turned on, and Nginx will try to buffer a certain amount of data from the backend before sending it to the browser. Please try adding proxy_buffering off;
after the reverse proxy parameter and then reloading Nginx. Other web server configurations are similar.
Please read the Contributing Guidelines before contributing.
Thanks to all the contributors!
If you find this project helpful, please give me a star.
MIT © Kerwin1202