liboai VS openai-node

Imagine you have an AI-powered personal alerting chat assistant that interacts using up-to-date data. Whether it's a big move in the stock market that affects your investments, any significant change on your shared SharePoint documents, or discounts on Amazon you were waiting for, the application is designed to keep you informed and alert you about any significant changes based on the criteria you set in advance using your natural language. In this post, we will learn how to build a full-stack event-driven weather alert chat application in Python using pretty cool tools: Streamlit, NATS, and OpenAI. The app can collect real-time weather information, understand your criteria for alerts using AI, and deliver these alerts to the user interface.

1.OpenAI API

OpenAI Account – make an OpenAI Account here

Their big advantage is that they can quickly deal with data they’ve never seen before and scale. NVIDIA and Open AI are currently leading providers of such technologies. Read more.

You need an API key https://openai.com/api

To run ChatGPT, you need access to OpenAI’s API3, which provides a cloud-based platform for interacting with various models, including ChatGPT. You can sign up for an account and request access to the API here: https://openai.com/api/

To get started, go to OpenAI and create an account. After that, click on your profile on the top right corner, and select view API keys.

As far as I know the ChatGPT API isn’t public yet. However you can use the GPT3 version from OpenAI which do have an API you can connect to. The Davinci-003 text model is pretty damn good. https://openai.com/api/ for more info

GPT-3: GPT-3 is an advanced language generation model developed by OpenAI. It is capable of generating high-quality human-like text with a high degree of coherence and coherence. The model has been trained on a vast corpus of text, making it capable of generating text across a range of topics. GPT-3 can be used for a variety of content creation tasks such as blog posts, articles, and social media updates. One of the most significant advantages of using GPT-3 is that it can save a significant amount of time when creating content. The model can generate text much faster than a human writer, and the output can be used as a starting point for further refinement.

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.