kor
shoelace-css
kor | shoelace-css | |
---|---|---|
8 | 73 | |
1,520 | 12,057 | |
- | 2.2% | |
6.9 | 9.5 | |
1 day ago | 16 days ago | |
Python | TypeScript | |
MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
kor
-
Pydentic in prompt engineering
Check out kor
-
27-Jun-2023
Extract structured data from text using LLMs (https://github.com/eyurtsev/kor)
- Kor: Extract structured data using LLMs
-
Guidance on creating a very lightweight model that does one task very well
Check out https://github.com/eyurtsev/kor
-
A minimal design pattern for LLM-powered microservices with FastAPI & LangChain
You're absolutely correct, and I agree that there's potentially a risk of quality loss. But likewise, since these are all intrinsically linked, it may be possible to leverage strength by combining these tasks. I'm unaware of a paper reviewing the reliability and/or performance of LLMs in this specific scenario. If you find any, do share :) With regards to generating JSON responses - there are simple ways to nudge the model and even validate it, using libraries such as https://github.com/promptslab/Promptify, https://github.com/eyurtsev/kor and https://github.com/ShreyaR/guardrails
-
Information extraction in large documents with LLMs
Currently, I'm experimenting with GPT-3.5-turbo in conjunction with the kor library (langchain for information extraction) to define a prompt template with various examples of what I'm looking for.
-
RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI
yes. there are a few approaches which i intend to take and some helpful resources:
You could implement a Dual LLM Pattern Model https://simonwillison.net/2023/Apr/25/dual-llm-pattern/
You could also leverage a concept like Kor which is a kind of pydantic for LLMs: https://github.com/eyurtsev/kor
in short and as mentioned in the README.md this is absolutely vulnerable to prompt injection. I think this is not a fully solved issue but some interesting community research has been done to help address these things in production
shoelace-css
-
Htmx and the Rule of Least Power
HTMX gets all the hype right now, but there are other tools in the same vain, my favorite being Unpoly (https://unpoly.com). Together with Shoelace (https://shoelace.style) you get nice GUIs real fast, without the burden of complicated dependency management and build steps. Also, you don't have to write a lot of JS, just what is needed for small enhancements, as it was meant to be. Some might say the main drawback is the tight coupling to your backend. In my case, this is also the main benefit as it integrates perfectly with the backend framework (Django).
-
Show HN: Hyperdiv β Reactive, immediate-mode web UI framework for Python
Hello HN,
I'm releasing Hyperdiv (https://hyperdiv.io), a framework for rapidly developing reactive browser UIs in Python, with immediate-mode syntax and using Shoelace (https://shoelace.style) as its built-in component system.
This short coding video will give you a good idea of what it is: https://www.youtube.com/watch?v=4XJKfxaqvGE
I wrote a brief article about the motivation and approach: https://hyperdiv.io/intro.html
Hyperdiv doesn't aim to compete with serious full-stack frameworks. The core aim was to make it easy and fast to prototype apps and build UI-based tools. I was originally motivated by internal tools at work -- feeling the need to quickly put together UI-based tools to share with both technical and non-technical coworkers, without having to stand up and maintain a full internal stack.
This is my first major open source release. I really appreciate your feedback and support. - Marius
-
Making Web Component properties behave closer to the platform
For example, all the following design systems can be used without tooling (some of them provide ready-to-use bundles, others can be used through import maps): Google's Material Web, Microsoft's Fluent UI, IBM's Carbon, Adobe's Spectrum, Nordhealth's Nord, Shoelace, etc.
- Shadcn: Beautifully designed components that you can copy-paste into your apps
- Shoelace: A forward-thinking library of web components
-
Stream Updates to Your Users with LiteCable for Ruby on Rails
Here's what this looks like - note that I'm using Shoelace components for styling purposes.
- Ask HN: Is there something like shadcn/UI for vanilla HTML and JavaScript?
-
Lit 3 Release Announcement
There are lots of open-source design systems built with Lit. Shoelace is a popular component set that you might check out: https://github.com/shoelace-style/shoelace There are many others...
Would it help if we listed more open source projects on our site?
Because of our focus on components and the fact that you really can use just about any libraries and scaffolding for apps, we don't really have an app starter kit, but it's something we've talked about.
-
Framework Interoperable Component Libraries Using Lit Web Components.
I'm really excited about all this, and it makes me have some faith in the web again. I think that Lit is a step in the right direction especially the ability to do SSR / SSG and hydrate a web page. Hopefully π€ Shoelace can get SSR running, which is currently one hurdle, but I think it is achievable.
What are some alternatives?
Promptify - Prompt Engineering | Prompt Versioning | Use GPT or other prompt based models to get structured output. Join our discord for Prompt-Engineering, LLMs and other latest research
carbon-components-svelte - Svelte implementation of the Carbon Design System
motorhead - π§ Motorhead is a memory and information retrieval server for LLMs.
ng-bootstrap - Angular powered Bootstrap
lambdaprompt - Ξ»prompt - A functional programming interface for building AI systems
storybook - Storybook is a frontend workshop for building UI components and pages in isolation. Made for UI development, testing, and documentation.
NeMo-Guardrails - NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.
material - Material design for AngularJS
sketch - AI code-writing assistant that understands data content
stencil - A toolchain for building scalable, enterprise-ready component systems on top of TypeScript and Web Component standards. Stencil components can be distributed natively to React, Angular, Vue, and traditional web developers from a single, framework-agnostic codebase.
rasa-haystack
spectrum-web-components - Spectrum Web Components