promptable icon indicating copy to clipboard operation
promptable copied to clipboard

Build LLM apps in Typescript/Javascript. 🧑‍💻 🧑‍💻 🧑‍💻 🚀 🚀 🚀

Results 29 promptable issues
Sort by recently updated
recently updated
newest added

New completions example in the apps/web/src/pages/api directory with my production code.

So this is a bigger PR than what I would have like initially and would like some feedback before finishing # Context: [#16](https://github.com/cfortuner/promptable/issues/16) the main reason for this change was...

Adds a new utility -> Retry! - Updated Openai provider's embedOne, generate and stream methods to use Retry! It's a typescript decorator that lets you retry N number of times:...

Thank you for building this. Is `promptable` using any node.js specific APIs (eg. crypto) etc which would make it incompatible with [Cloudflare Workers](https://developers.cloudflare.com/workers/runtime-apis/)?

This library is cool but I feel like prompt templates should just use the language instead of being their own object. https://www.typescriptlang.org/docs/handbook/2/template-literal-types.html https://www.typescriptlang.org/play?#code/C4TwDgpgBACg9hAtgFTmAlgYwM5QLxQBEANnAG4SFQA+RAZgE7oQB2AJtgBbphW2F1SAdwgNshAFBSJoSLASIYDOIjDBkSMMQCGwaAQAGAdSZ6o2qGAXmARnACuwKABIA3vCSoMOAL4GpQA Maybe use zod to enforce at runtime.

Running into rate limit ``` Rate limit reached for default-global-with-image-limits in organization XXX on requests per min. Limit: 60.000000 / min. Current: 70.000000 / min. Contact [email protected] if you continue...

Following the **Examples** instructions, I get the following error when running `pnpm dev` https://github.com/cfortuner/promptable#examples ``` web:dev: ❌ Invalid environment variables: web:dev: DATABASE_URL: Required web:dev: web:dev: error - Failed to load...

Promptable tracing UI dropdown doesn't close when clicking the dropdown arrow after opening. Relevant info: - docs: https://github.com/cfortuner/promptable/blob/main/apps/docs/docs/modules/tracing.md - source code: https://github.com/cfortuner/promptable/blob/main/apps/web/src/components/Content.tsx#L73

The rate limits on OpenAI seem a little wonky. Not sure if that's only true for Codex or for all the models but I was definitely getting rate limited even...