django-functest VS docquery

django-functest – Helpers for creating high-level functional tests in Django, with a unified API for WebTest and Selenium tests

I think the case for server-side HTML rendering has never been stronger, and of all Django projects I work on, the ones I enjoy most are those that never got on the SPA bandwagon. From both a developer and user point of view I find them much faster and less painful. There are many cases where you really, really don't need the massive amount of extra complexity involved in designing APIs, adding JS frameworks etc.

When you need a bit of extra UI goodness, [htmx](https://htmx.org/) is a fantastic solution, and you can still use SPA-type approaches for things that need them.

You can also benefit from massively faster (and more reliable) functional testing when you are mostly standard HTML - see [django-functest](https://github.com/django-functest/django-functest/) for an example of this.

There is a visual demo here: https://sites.google.com/view/llm4html/home.

This work is very exciting for a few reasons:

* HTML is an incredibly rich source of visually structured information, with a semi-structured representation. This is as opposed to PDFs, which are usually fed into models with a "flat" representation (words + bounding boxes). Intuitively, this offers the model a more direct way to learn about nested structure, over an almost unlimited source of unsupervised pre-training data.

* Many projects (e.g. Pix2Struct https://arxiv.org/pdf/2210.03347.pdf, also from Google) operate on pixels, which are expensive (both to render and process in the transformer). Operating on HTML directly means smaller, faster, more efficient models.

* (If open sourced) it will be the first (AFAIK) open foundation model for the RPA/automation space (there are several closed projects). They claim they plan to open source the dataset at least, which is very exciting.

I'm particularly excited to extend this and similar (https://arxiv.org/abs/2110.08518) for HTML question answering and web scraping.

Disclaimer: I'm the CEO of Impira, which creates OSS (https://github.com/impira/docquery) and proprietary (http://impira.com/) tools for analyzing business documents. I am not affiliated with this project.

DocQuery (https://github.com/impira/docquery), a project I work on, allows you to do something similar, but search over semantic information in the PDF files (using a large language model that is pre-trained to query business documents).

For example:

  $ docquery scan "What is the due date?" /my/invoices/

docquery – An easy way to extract information from documents