outlines
custom-elements-everywhere
outlines | custom-elements-everywhere | |
---|---|---|
33 | 19 | |
5,799 | 1,144 | |
11.0% | 1.3% | |
9.7 | 8.9 | |
7 days ago | 3 days ago | |
Python | JavaScript | |
Apache License 2.0 | GNU General Public License v3.0 or later |
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.
outlines
-
Infini-Gram: Scaling unbounded n-gram language models to a trillion tokens
> [2]: https://github.com/outlines-dev/outlines?tab=readme-ov-file#...
It's interesting as speech recognition has become more popular than ever through services like Alexa, and other iot devices support for OS speech recognition
Unfortunately most implementations (especially those that are iot focused) don't have very important features for robust speech recognition.
1. Ability to enable and disable a grammar
-
Show HN: LLM-powered NPCs running on your hardware
[4] https://github.com/outlines-dev/outlines/tree/main
-
Advanced RAG with guided generation
The next step is defining how to guide generation. For this step, we'll use the Outlines library. Outlines is a library for controlling how tokens are generated. It applies logic to enforce schemas, regular expressions and/or specific output formats such as JSON.
-
Anthropic's Haiku Beats GPT-4 Turbo in Tool Use
No benchmarks, just my anecdotal experience trying to get local LLM's to respond with JSON. The method above works for my use case nearly 100% of the time. Other things I've tried (e.g. `outlines`[0]) are really slow or don't work at all. Would love to hear what others have tried!
0 - https://github.com/outlines-dev/outlines
-
Show HN: Chess-LLM, using constrained-generation to force LLMs to battle it out
As I was playing with the Outlines library (https://outlines-dev.github.io/outlines/), I discussed with my friend Maxime how funny it would be if we set up a way to pair LLMs in chess matches till one wins. The first time I tried it, it required substantial prompt engineering to get some of those LLMs to propose valid moves. Large language models can mostly stay focused and even play rather well; see https://news.ycombinator.com/item?id=37616170 for example. However small language models aren't as easy to convince.
Some of those LLMs have seen very little chess notation and so after the first few opening moves there aren't any valid tactics, let alone strategy, so they would end up either repeating the same move, or hallucinate moves that are not valid (Kxe5, but there would be a queen on e5!)
Then Outlines came along and we could force them to pick valid moves with little cost! Maxime worked super fast and got a first version of this idea as a gradio space.
I think it is pretty fun to see the (mostly terrible, but otherwise valid) chess that those LLMs play. Maybe it will even be instructive to how we can create small LLMs that can play much better than the ones on the leaderboard.
Anyway, you can check it out here:
https://huggingface.co/spaces/mlabonne/chessllm
What is interactive about it: you can pick the LLMs from available models on HuggingFace (within reason, small LLMs are preferable so that the space does not crash) or push one of your own small models to HF and have it fight with others. At the end of the game the leaderboard is updated.
Hope you find it fun!
-
Show HN: Prompts as (WASM) Programs
> The most obvious usage of this is forcing a model to output valid JSON
Isn't this something that Outlines [0], Guidance [1] and others [2] already solve much more elegantly?
0. https://github.com/outlines-dev/outlines
1. https://github.com/guidance-ai/guidance
2. https://github.com/sgl-project/sglang
- Show HN: Fructose, LLM calls as strongly typed functions
-
Unlocking the frontend – a call for standardizing component APIs pt.2
And I think “just” Markdown doesn’t quite cut it for safe guidance. For example: directly generating content for your components. But I’m really excited about tooling like outlines appearing, with a greater focus on guided generation for structured data. Because this is often what we actually need!
-
Ask HN: What are some actual use cases of AI Agents?
It's pretty easy to force a locally running model to always output valid JSON: when it gives you probabilities for the next tokens, discard all tokens that would result in invalid JSON at that point (basically reverse parsing), and then apply the usual techniques to pick the completion only from the remaining tokens. You can even validate against a JSON schema that way, so long as it is simple enough.
There are a bunch of libraries for this already, e.g.: https://github.com/outlines-dev/outlines
-
Launch HN: AgentHub (YC W24) – A no-code automation platform
https://github.com/outlines-dev/outlines/blob/7fae436345e621... squares with my experience using LLMs for anything real
sequence = generator("Alice had 4 apples and Bob ate 2. Write an expression for Alice's apples:")
custom-elements-everywhere
-
Unlocking the frontend – a call for standardizing component APIs pt.2
With React (it seems) finally moving to support everything needed (they are the last major framework lagging behind substantially), too, we might be moving to a world post-framework discussions, and real interoperability on a technical level. I think Jake Lazaroff motivates this beautifully with his articles “Web Components Eliminate JavaScript Framework Lock-in” and “The Web Component Success Story”.
-
Use web components for what they’re good at
Seems it doesn’t work in React, everything is sent as a string. There was a link in the article that shows how well web components work with various frameworks.
https://custom-elements-everywhere.com/
You can see how React fares for itself.
-
If Web Components are so great, why am I not using them?
React supports Web Components, just some quirks to be aware of: https://custom-elements-everywhere.com/
-
[AskJS] Asking advice on monorepo setup with multiple frameworks
You could wrap each component as a Web Component and then import them for each repo. Web Components are not native to frameworks, so the support for them could vary when passing props. Or you could wrap the render method of each framework as a function and then use the receiving frameworks life cycle method and inject it onto the page. If you use frameworks like Svelte or Lit that are "Web Component" based, then you'd need to see if the receiving framework supports Web Components inorder to import the seamlessly.
-
Am I the only one that thinks that the direction of React is wrong?
Check compatibility of React with web components: https://custom-elements-everywhere.com/ It's not directly because of jsx, but because of synthetic "let's make it up" approach of React.
-
Regarding converting svelte file into pure js file
I have been using this approach recently as well, working great thus far ! Some things to consider though: - I would recommend checking if the other frameworks you intend to use have good web components support (looking at you, react): https://custom-elements-everywhere.com/ - There are ways to do so without web components, but I wouldn't recommend them unless your framework has poor web components support.
-
HTML with Superpowers: An Introduction to Web Components
VueJS actually fails some advanced tests for WebComponents: https://custom-elements-everywhere.com/
So, VueJS docs are actually incorrect when they say it scores 100%. The actual score is 90%.
I had reported this 8 months ago.
-
Building Web Components 101 - Part 1
Since Web Components are supported natively by browsers, they can be used in any libraries and frameworks either directly or with configurations. https://custom-elements-everywhere.com/ is a great site to check custom elements support status by different libraries and frameworks.
- Check if a library/framework supports the usage of custom elements
- custom-elements-everywhere.com: Check if a library/framework supports the usage of custom elements
What are some alternatives?
guidance - A guidance language for controlling large language models.
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.
jsonformer - A Bulletproof Way to Generate Structured JSON from Language Models
details-dialog-element - A modal dialog that's opened with <details>.
json-schema-spec - The JSON Schema specification
hybrids - Extraordinary JavaScript UI framework with unique declarative and functional architecture
Constrained-Text-Genera
feelback-integrations - Feelback SDKs, integrations libraries and samples
torch-grammar
astro - The web framework for content-driven websites. ⭐️ Star to support our work!
langroid - Harness LLMs with Multi-Agent Programming
web-vitals - Essential metrics for a healthy site.