SoundSearch VS hof

Currently building a search engine that allows you to search within a select list of websites. The idea is to allow users to search for content in sites that may not have the best search on indexing features. I started this as there are few websites that I use that have ancient indexing. How am I meant to know which year/month the article that I'm trying to find was published in??

https://github.com/AbdullahRehmat/SoundSearch

It's very much work in progress...

Hi HN, this is a project I've created initially for code gen from Yaml DSLs, but after hacking imports into Yaml... I went soul searching and discovered CUE. Since then I've become a big fan of the language and have been experimenting with various ways to use CUE, many of which have landed in hof

https://docs.hofstadter.io

Go's text/template (basically the same as html/template, with fewer safe guards) is pretty powerful. You can add custom functions and partial templates too. I use these concepts in https://docs.hofstadter.io to generate any code, not just frontend.

For frontend, as in your example, this has the older feel for UI, where each navigation requires a round trip to the server and a full-page response to the client. This is part of the reason people have moved to React and full-stack TS. I love Go, but I'm definitely a big fan of writing webapps in Next at this point. React Server Components are a really nice DX.

I'm sure it is still a good learning experience. I learned a lot by working on a universal formatting setup.

https://github.com/hofstadter-io/hof/tree/_dev/formatters

Mainly an overview of using CUE from Go, with a little flair of validating the returned JSON of an LLM with CUE.

A while back, I used a CUE-like schema instead of OpenAPI. Most of the time, you can get the model to output JSON/CUE from example objects rather than full schemas, which I have a hunch will be distracting and not reasoned about.

https://github.com/hofstadter-io/hof/blob/_dev/lib/chat/cmd/...

For a auth product, you probably should go with traditional code generation, not LLMs (re: all the unsolvable problems they have (hallucinations, incomplete code answers). For an auth product, you want something definite and reproducible, or you are asking for trouble.

If you are interested in a flexible code gen framework, I built one that had this very use case in mind. (https://github.com/hofstadter-io/hof)

I'd be happy to think / talk this through with you

I recently built a TUI for exploring and developing CUE, JSON, Yaml.

Large inspiration for the overall UX comes from the Bloomberg terminal, where every function is reachable with four letter shortcut from the command box. It was really the command box that I liked. I've also built a sort of "flex" panel component for the layout so you can create as many panels as you like.

https://docs.hofstadter.io/getting-started/hof-tui/

https://github.com/hofstadter-io/hof/tree/_dev/lib/tui

Many business analysts use SQL, have for a long time. They are probably not your target audience. With the problem being JAVA specific, you'd likely want to start there

This sounds similar to the goals of my hof tool (https://github.com/hofstadter-io/hof), lift type definitions out of code so they can be defined in one place, then generate the code for all the places. Is that sounding like what you are after?

Having built something similar, the biggest challenge for users is that they have to use a bespoke language, like WASP here. I suspect that it is also your biggest challenge as well.

Mine is built on CUE, which at least has the potential to become a more widely used language. CUE hasn't reached sufficient maturity for broader adoption yet, so I continue to face this same problem.

https://github.com/hofstadter-io/hof

Here's a big one I needed to get ChatGPT to do something more sophisticated with a JSON object response (predates functions and all that)

https://github.com/hofstadter-io/hof/blob/_dev/flow/chat/pro...

It no longer worked after a model update some time ago, haven't tried recently.

I found codellama to be much better for this and require fewer instructions, an anecdotal validation for smaller, focussed models

I was surprised out how you can define arbitrary grammars using arbitrary formulation and it would follow it. Of course you have to redo the prompt every time there is an update... such a pain

https://github.com/hofstadter-io/hof/blob/_dev/flow/chat/pro...