vrite VS openai-node

These reasons (and many others) are why I decided to create Vrite - an open-source developer content platform.

Vrite is an open-source developer content platform, featuring extensible editing experience, content management tools, and powerful APIs. It’s intended as an all-in-one, collaborative solution for product documentation, technical blogs, and knowledge bases.

So, I've been building Vrite as an open-source project for a while now, and I'm happy to finally share it here - with v0.2.0 now having official self-hosting support.

Let’s start by getting into Vrite. You can use the hosted version (free while Vrite is in Beta) or self-host Vrite from the source code (with better self-hosting support coming soon)

You can use Vrite via the hosted version (that’s free while in Beta) or self-host it from the open-source repo (though good support for self-hosting is still in the works).

Since Vrite (and Vrite Editor for that matter) is currently in Public Beta, new features and improvements are in active development. The best way to try it out right now is through the hosted version at app.vrite.io (free while in Beta) with better self-hosting support in the works.

The editor itself is a standalone app, extracted from the larger Vrite CMS project (https://github.com/vriteio/vrite) which you can also test out (only with sign-in) here: https://app.vrite.io/

The main output is JSON ProseMirror format. Other formats are processed from this JSON using Transformers and Vrite SDK: https://github.com/vriteio/vrite/tree/main/packages/sdk/java...

In the GFM transformer I try to follow GitHub Flavored Markdown spec, which technically doesn't support embeds. Since I didn't find any "common" syntax to use for the embeds, I just left them out. They're still there in JSON and HTML outputs.

That's one of the drawbacks of MD. That said, I plan to add an option like Markdoc, which has clearly defined spec for implementing custom blocks like embeds.

That said, for now, if you sign up for the full Vrite CMS, you can create a custom Transformer and process the output so that embeds are included in your desired format. That's what I'm doing for auto-publishing extensions for platforms like Dev.to and Hashnode. I don't know what your use-case is, but I thought it's worth noting.

The process basically came down to figuring out the position and size of the block node, given a selection of an entire top-level node or just its child node (source code):

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.

A package I help maintain was released about a month ago, and we've had bug reports related to this: https://github.com/openai/openai-node/issues/304#issuecommen...

We simply chose to mark Jest 27 as unsupported in this case, but it did cost some debugging time.