This is a replication project for the typescript version of [gpt4free](https://github.com/xtekky/gpt4free) ## Demo [GPTGOD](http://gptgod.site) In the next two weeks, I will open source all the code for GPTGOD. If you need, Please watch this project or follow me to receive notifications. Why now? because there are stil some secret config should be removed from that project. ## Reverse target Still striving to keep updating. Have implemented models here: If you do not want your website to appear here, please raise an issue and I will remove it immediately. - [x] [aidream](http://aidream.cloud) GPT-3.5 ***Still active after 2023-05-11*** - [x] [you.com](you.com) GPT-3.5 / Internet / good search **Still active after 2023-05-11** - [x] [forefront.ai](forefront.ai) GPT-4/3.5 ***Not valid from 2023-05-10, but it will be right back*** - [ ] [bing.com/chat](bing.com/chat) GPT-4/3.5 - [ ] [poe.com](poe.com) GPT-4/3.5 - [ ] [writesonic.com](writesonic.com) GPT-3.5 / Internet - [ ] [t3nsor.com](t3nsor.com) GPT-3.5 ## Run local ```shell # install module yarn # start server yarn start ``` ## Run with docker first, you should create file .env ```env http_proxy=http://host:port # you should config this if you use forefront api, this apikey is used for receive register email # get api key here https://rapidapi.com/calvinloveland335703-0p6BxLYIH8f/api/temp-mail44 rapid_api_key=xxxxxxxxxx ``` ``` docker run --env-file .env xiangsx/gpt4free-ts:latest ``` ## Deploy with docker-compose first, you should create file .env; Follow step "Run with docker deploy ``` docker-compose up --build -d ``` ## Test with curl ### params in query ``` prompt: string; // required ``` aidread options ```typescript interface options { parentMessageId: string // if you need context try this systemMessage: string // default: You are ChatGPT, a large language model trained by OpenAI. Follow the user's instructions carefully. Respond using markdown. temperature: number; // default: 1 top_p: number // default:1 parse: boolean; // default:true only valid in stream;if set false,return source data contains parentMessageId... } ``` forefront options ``` chatId?: string; actionType?: Action; // 'new' or 'continue' defaultPersona?: string; gptmodel?: Model; // gpt-4 or gpt-3.5-turbo resignup?: number; // default 0 if set 1, auto sign up when gpt4 times use up // event: error // data: GPT-4 rate limit exceeded (>5 messages every 3 hours). Time remaining: 179 minutes // if you see this try set resignup=1 or use gpt-3.5-turbo // if you want chat with context, set actionType=continue and chatId={Defined constant uuid} ``` ### test now! common request ```shell # test default model aidream curl "http://127.0.0.1:3000/ask?prompt=hello&model=aidream" # test default model chat.forefront.at curl "http://127.0.0.1:3000/ask?prompt=hello&model=forefront&gptmodel=gpt-4&resignup=1" # test you.com curl "http://127.0.0.1:3000/ask?prompt=hello&model=you" ``` request event-stream ```shell # test default model aidream curl "http://127.0.0.1:3000/ask/stream?prompt=hello&model=aidream" # test chat.forefront.at curl "http://127.0.0.1:3000/ask/stream?prompt=hello&model=forefront&gptmodel=gpt-4&resignup=1" # test you curl "http://127.0.0.1:3000/ask/stream?prompt=hello&model=you" ``` ## 🌟 Star History [![Star History Chart](https://api.star-history.com/svg?repos=xiangsx/gpt4free-ts&type=Date)](https://star-history.com/#xiangsx/gpt4free-ts&&type=Date)
You may join our discord: discord.gg/gpt4free for further updates.