Based on model gpt-3.5-turbo
. Demo: https://fastgpt.app
Tested on Node.js 18.x.
$ pnpm install
Create a .env
file in the root directory and add your OpenAI API key:
OPENAI_API_KEY=sk-xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
# optional, support http or socks proxy
HTTP_PROXY=https://proxy-server:port
# development
$ pnpm run start
# watch mode
$ pnpm run start:dev
# production mode
$ pnpm run start:prod
Visit https://localhost:3000
$ docker build -t chatgpt-mirror .
$ docker run -d -p 3000:3000 --env-file .env chatgpt-mirror
$ docker run -d -p 3000:3000 --env-file .env -v $(pwd)/config/app.config.json:/app/config/app.config.json chatgpt-mirror
You can configure the app by copying the config/example.json
to config/app.config.json
and editing its values. Note: comments are not allowed in JSON files.
Error messages for the OpenAI API can be customized by editing the config/app.config.json
file. See the examples in the config/example.json
file.
Thanks: transitive-bullshit/chatgpt-api