openai-node VS caniuse

Okay, now we've confirmed the API endpoint is working, let's connect it to OpenAI first, install the OpenAI package, navigate to the route directory, and run the command below in our terminal

For my setup, I am using the node version of the openai sdk.

We try to keep it to a minimum, especially in JS (though we have some nice improvements coming soon when we deprecate node-fetch in favor of built-in fetch). The package sizes aren't tiny because we include thorough types and sourcemaps, but the bundle sizes are fairly tidy.

Here's an example of a typical RESTful endpoint (Lithic's `client.cards.create()`:

https://github.com/lithic-com/lithic-node/blob/36d4a6a70597e...

Here are some example repos produced by Stainless:

1. https://github.com/openai/openai-node

Have you seen/tried the `.runTools()` helper?

Docs: https://github.com/openai/openai-node?tab=readme-ov-file#aut...

Example: https://github.com/openai/openai-node/blob/bb4bce30ff1bfb06d...

(if what you're fundamentally trying to do is really just get JSON out, then I can see how json_mode is still easier).

And so, I impulsively upgraded to the latest version of openai (I guess not anymore) without the fear of getting cut by cutting edge 😝 and got it working for some random text

UPDATE 2023/11/15: I used fetch and custom streams because at the time of writing, the openai module on NPM did not properly support streaming responses. That issue has been fixed, and I think a better solution would be to use that module and pipe their data through a TransformStream to send to the client. That version is not reflected here.

You may notice the JavaScript package available on NPM called openai. We will not be using this, as it doesn’t quite support some things we’ll want to do, that fetch can.

openai - For using the GPT-3.5-turbo model to answer the questions

We have a bit of context about this in the readme: https://github.com/lastmile-ai/aiconfig#what-problem-it-solv.... The main issue with keeping it in code is that it tangles application code with prompts and model-specific logic.

That makes it hard to evaluate the genAI parts of the application, and also iterating on the prompts is not as straightforward as opening up a playground.

Having the config be the source of truth let's you connect it to your application code (and still source controlled), lets you evaluate the config as the AI artifact, and also lets you open the config in a playground to edit and iterate.

For example, compare how much simpler openai function calling becomes with storing the stuff as a config: https://github.com/lastmile-ai/aiconfig/blob/main/cookbooks/... vs using vanilla openai directly (https://github.com/openai/openai-node/blob/v4/examples/funct...)

In your preferred serverless environment, make sure you install the OpenAI API Library and Vercel AI library to get started.

We do have a great tool such as CanIUse and of course, BaseLine is not going to replace it.

Can I use...

Lots of parts to WebRTC ( https://developer.mozilla.org/en-US/docs/Web/API/WebRTC_API ) but none that I know that can knock out something outside of your browser. It could maybe overload RAM and get killed.

Try using the offending website on a browser/OS that _doesn't_ have WebRTC such as https://caniuse.com/?search=webrtc. Or try with WebRTC disabled.

Possible you're getting throttled by your router or ISP when certain connections are made.

And there's this https://browserleaks.com/webrtc

A11ySupport.io: The caniuse of accessibility. Lists compatibility of various browser accessibility features for different screen reader and browser combinations.

Ah yep! I just didn't wait long enough. Very cool. Seems like it took a lot of work. And it seems better than other browser-based video editors I've seen in the past, so kudos.

TIL about the webcodecs API to get frames of video and chunks of audio: https://caniuse.com/?search=webcodecs

Can I X, is a question about the readiness/compliance of a certain thing at time = now. Can I use CSS version X was the iconic early meme.

https://caniuse.com/?search=css3

For a generalized example, if you wanted to know if the basketball courts were ready for you to “ball it up” in a certain city, it’d be caniball.com

If you want to know if you can use a certain frontend technology, the idea is like: canwefigma?

It’s a glorified feature matrix, and usually a project of a passionate community. I approve, even if some of the memes are a bit dank.

https://caniuse.com/ is a popular tool to check what web features are working across different browsers - "can you use this and assume that it will work for others".

The article uses custom css @properties which are awesome and have 88% browser support [1].

One thing to watch out for is differences in how browsers handle setting the fallback initial-value. Chrome will use initial-value if CSS variable is undefined OR set to an invalid value. Firefox will only use initial-value if the variable is undefined. For most projects, this won't be an issue, but for a recent project, I ended up needing to use javascript to set default values in Firefox to iron out the inconsistency between browser implementations.

[1] https://caniuse.com/?search=%40property

Safari is the only browser that doesn't support extending HTML element

https://caniuse.com/?search=Custom%20Elements

You forgot to mention (Web)Workers. This is explicit creation, management, and communication with additional threads within JavaScript. What's more, they've been around in JavaScript longer than the V8 engine has even existed!

https://developer.mozilla.org/en-US/docs/Web/API/Web_Workers...

https://caniuse.com/?search=webworkers