awesome-tagged-templates VS gptcli

When zx first appeared, it was a tiny esm script that just proposed a new idea for how child_process.spawn API could be enhanced with string template literals.

The template combines HTML and JavaScript. To understand this approach, consider how PHP pages are generated. In PHP, code is embedded within the HTML. Similarly, this library leverages JavaScript template literals to achieve the same objective. From the definition: "Template literals are literals delimited with backtick (`) characters, allowing for multi-line strings, string interpolation with embedded expressions, and special constructs called tagged templates".

The numbers we are printing are monetary values so they are missing a decimal value and a currency symbol. One way we can do this is by using JavaScript template literals to append and prepend the pieces we are missing.

Tagged templates[0], the language feature that enables this, were introduced in ECMAScript 2015 apparently – arguably at least somewhat new in the lifespan of JavaScript. :)

Java is getting a similar feature with template processors[1]. It would be nice to have it in Python as well – i.e. not just f-strings, but something that (like tagged templates) allows a template function process the interpolated values to properly encode them for whatever language is appropriate (e.g. shell, SQL, HTML, etc.).

[0] https://developer.mozilla.org/en-US/docs/Web/JavaScript/Refe...

[1] https://openjdk.org/jeps/459

References: Template literals (Template strings)

We are using a string template literal to create the tag and the ${} syntax to provide string interpolation, that is, substituting the values of href and altText into our string.

In TypeScript, a string literal type is a type that represents a specific set of string values. For example, the type "red" | "green" | "blue" represents the set of three string values "red", "green", and "blue". Template literal types allow you to perform operations on these string literal types using the same syntax as template literal strings in JavaScript.

The example also showcases the use of inline templates, employing JavaScript Template Literals. The JSON data obtained from the GET request is accessible through the "data" variable.

These are called "tagged templates": https://developer.mozilla.org/en-US/docs/Web/JavaScript/Refe...

You must have an account with Open AI. If you don't have one, go here and create one.

For a long time, I was looking for something exciting to work on and this was it. The fact that ChatCraft already supported Speech to Text transcription using Whisper, which is another one of OpenAI's models with unique capabilities, integrating Text-to-Speech would essentially turn our application into something like an Amazon Alexa but with a brain powered the same LLM that ChatGPT uses.

With your API key, you’ll be able to make authenticated HTTP requests to OpenAI. So it’s a good idea to get familiar with the API itself. I’d encourage you to take a brief look through the OpenAI Documentation and become familiar with some concepts. The models are particularly good to understand because they have varying capabilities.

Next, we’ll also need an OpenAI account to have access to their API.

Capable of reasoning:The application can be connected to a large language model like OpenAI, Cohere, or Hugging Face. This enables the application to answer based on the context it is given.

Beyond that, "AI tools" is a pretty broad category. Odds are you're asking about LLMs (perhaps even specifically GPT), in which case a good place to start is with OpenAI and their API. Alternatively, Hugging Face is a good place to find models (not just LLMs, either) and they have tooling to let you interact with them in a consistent way. In these cases, you're not actually developing an AI, per se, but just utilizing it. But when I think of "AI Tools" at this point in time, I'm thinking of tools built on top of LLMs.

Like most things in IT and programming, this imo is also best learned by doing rather than reading a bunch of technical papers. I recommend starting with ChatGPT and testing out varieties of prompts asking it to fill in your knowledge. There are great documentation by both OpenAI and Microsoft Azure on using these models with examples. For open-source models (and transformers in general) HuggingFace is a great resource and you can get started on some smaller models by downloading it and trying right away. Karpathy's nanoGPT video on Youtube is also very useful to get started.

It's just a gui to (most of) what you get through the API. Read the API docs for details of each option: https://platform.openai.com/docs/introduction

For the full list of options, check out the OpenAI API documentation.

If you are interested in an API for ChatGPT in general, you can go look at the documentation or this starter guide for gpt-4 and gpt-3.5-turbo on the openai website. This should then be adapted to the language you are using.