English Compiler

The English Compiler
> English is all you need
We know that all great™ projects start with awesome™ detailed functional specifications.
Which is typically written in English, or its many other spoken language alternatives.
So what if, instead of writing code from functional specs, we simply compile it directly to code?
Into a future, where we replace nearly everything, with just written text.
On a smaller scale, instead of generating giant class files, it can convert smaller specifications like the following
Into the following code
> Does it work? Yes
> Is it production ready? No
>
> This is simply a POC. However if you like to take it further, you may give it a try.
For more details, see the 3 minute youtube presentation
How is this "better" then ChatGPT ?
Existing Open AI models, have an upper cap to the size of their input and output.
This limits their usage to small code snippets as of now.
We work around this limitation, by using ridiculous amount of impractical prompt chaining and engineering. Where we are be able to generate both entire applications across multiple files.
Or really large (java) files. Or both.
> An example of how large the OAuth2 integration specification and code with comment results into
This unfortunately means its a slow process
Where in order to build a large code file, multiple calls to the AI process needs to be done (almost every arrow in the digram, is an AI call)
**If the chart does not make it clear, having 10+ AI calls per file: this giant process is slow as ass**
But the point is not in its practicality, but validating the practicality of a possible future. Where the AI is a potential new abstraction compiler layer, to existing modern programming language.
Just as how modern programming languages are an abstract layer to operating system apis, which is in turn is an abstraction to machine code.
How do I install it?
The easiest way is to simply install it from NPM
How do I configure it?
From the project you wish to build from, you should at minimum have a folder for the specs file, and the source code.
You can then setup an english-compiler.jsonc file, which should contain all the required settings. Including the openai API key.
For obvious reasons, please do not checkin your openai API key to a public repo
The following is an example of the settings
Run one of our demo !
Note that the demo, include a precomputed cache of the AI compilation process, so unless you change part of the spec file. You do not need to update the openai key in the settings.
All demos, also come preloaded with the specification files
And the prebuilt code output (you can delete, and build again)
> Also yes, the output has some minor bugs here and there. This is a Proof-of-concept.
>
> I have spent over 4 hours, trying to slowly change the specs, and fix all the bugs. But the write-compile-test loop is just too damn slow. And I am out of time for the hackaton.
Demo 1 : Building a simple "twitter clone" demo
This is a simple complete application for a twitter clone, without login or authentication.
Including both the UI, and the API endpoints.
Go into the demo/twitter-clone folder
**Ask the AI for suggestions on a spec file**
EnglishCompiler spec suggest spec/ui/index.spec.md
**Build a single spec file**
EnglishCompiler build file spec/core/db.spec.md
**Build all spec file**
EnglishCompiler build all
If you want to really check, that it buidls the file feel free to delete the src directory, and run the build process.