429 Error code with gpt-4

[RCSnyder]

This is an incredible concept! Awesome job!

I am trying this out, but even with the following code above the openai call here, https://github.com/eylonmiz/react-agent/blob/main/backend/main/react-agent/utils/ChatBot.ts#L156

const sleep = (ms: number) => new Promise(r => setTimeout(r, ms))
await sleep(5000);

I am getting this error 429 error from yarn backend:dev

generateComponents start
generateSkeletonCompositionFromStory: skipping - composition already exists
generateComponentsConfigurations: skipping - configuration already exists
generateComponent: generating Component DashboardNav
generateComponent: generating Component TotalRevenueCard
generateComponent: generating Component UserNav
generateComponent: generating Component TeamSwitcher
generateComponent: generating Component SubscriptionsCard
generateComponent: generating Component SalesCard
generateComponent: generating Component RecentSalesCard
generateComponent: generating Component UserNav
generateComponent: generating Component SubscriptionsCard
generateComponent: generating Component ActiveNowCard
generateComponent: generating Component SalesCard
generateComponent: generating Component OverviewCard
generateComponent: generating Component RecentSalesCard
Error: Request failed with status code 429
    at createError (C:\Users\Cooper\Documents\GitHub\react-agent\node_modules\openai\node_modules\axios\lib\core\createError.js:16:15)
    at settle (C:\Users\Cooper\Documents\GitHub\react-agent\node_modules\openai\node_modules\axios\lib\core\settle.js:17:12)
    at IncomingMessage.handleStreamEnd (C:\Users\Cooper\Documents\GitHub\react-agent\node_modules\openai\node_modules\axios\lib\adapters\http.js:322:11)
    at IncomingMessage.emit (node:events:525:35)
    at endReadableNT (node:internal/streams/readable:1359:12)
    at processTicksAndRejections (node:internal/process/task_queues:82:21)
[ERROR] 19:16:48 Error: Request failed with status code 429

I was wondering if anyone else had encountered this.

Thanks

[akshay-shrivastava]

@RCSnyder Even i was facing the same issue but for me status is coming as 404. @eylonmiz First of all great work on the repo, could you help us in resolving the issue.

[eylonmiz]

Thank you guys! These issues come from your API access and limitations by OpenAI. The project uses OpenAI GPT4, which is disabled or limited for most users. 429 -> too many requests, I'm generating independent components in parallel (Promise.all), maybe if you change it to one by one it will work better in your setup. 404 -> Make sure you have the right API key with access to GPT4, (if you do, please make sure you don't have necessary spaces or quotes in '.env' file. I will make sure to resolve these issues soon, please sign up for updates on reactagent.io or join the Discord. Currently, I'm working on designing the V1 Architecture, so no fixes/features for the next week, but after that, I'll be working on resolving issues and cooler features, possibly supporting GPT3.5 and possibly a free limited hosted version! @akshay-shrivastava @RCSnyder If you found a fix you are more than welcome to open a PR and I'll review!

[areibman]

Wrote a fix in #21. Basically, introduced retries with exponential backoff. Solves the problem nicely