floneum
outlines
floneum | outlines | |
---|---|---|
10 | 33 | |
979 | 5,882 | |
10.5% | 12.2% | |
9.8 | 9.7 | |
7 days ago | 2 days ago | |
Rust | Python | |
Apache License 2.0 | Apache License 2.0 |
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.
floneum
-
Dioxus 0.5: Web, Desktop, Mobile Apps in Rust
It is pretty good. I am working on an application that uses SVGs as a way to draw a workflow editor UI with Dioxus: https://github.com/floneum/floneum
-
Show HN: Kalosm an embeddable framework for pre-trained models in Rust
```
## What can you build with Kalosm?
Kalosm is designed to be a flexible and powerful tool for building AI into your applications. It is a great fit for any application that uses AI models to process sensitive information where local processing is important.
Here are a few examples of applications that are built with Kalosm:
- Floneum (https://floneum.com/): A local open source workflow editor and automation tool that uses Kalosm to provide natural language processing and other AI features.
-
Launch HN: AgentHub (YC W24) – A no-code automation platform
This reminds me of Floneum (https://github.com/floneum/floneum), this open-sourced tool for graph-based workflows using local LLMs.
-
Announcing Kalosm - an local first AI meta-framework for Rust
Kalosm is a meta-framework for AI written in Rust using candle. Kalosm supports local quantized large language models like Llama, Mistral, Phi-1.5, and Zephyr. It also supports other quantized models like Wuerstchen, Segment Anything, and Whisper. In addition to local models, Kalosm supports remote models like GPT-4 and ada embeddings.
- Show HN: Kalosm – an local first AI meta-framework in Rust
- Floneum 0.2 released: Headless browsing, package manager, cloud saves, and more
- Floneum, a graph editor for local AI workflows
-
Show HN: Floneum, a graph editor for local AI workflows
1. I would love to support additional model runners including exLlama and API based models like chat GPT. I'm less familiar with how c transformers and GPTQ compare to llama.cpp. GPTQ used to run faster because it supported GPU acceleration, but now llama.cpp supports the GPU as well so that may have changed. Feel free to open a GitHub issue to discuss this: https://github.com/floneum/floneum/issues/new/choose
2. There are a few differences:
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:")
What are some alternatives?
indexify - A scalable realtime and continuous indexing and structured extraction engine for Unstructured Data to build Generative AI Applications
guidance - A guidance language for controlling large language models.
chatty-llama - A fullstack Rust + React chat app using open-source Llama language models
jsonformer - A Bulletproof Way to Generate Structured JSON from Language Models
text-embeddings-inference - A blazing fast inference solution for text embeddings models
json-schema-spec - The JSON Schema specification
awesome-ml - Curated list of useful LLM / Analytics / Datascience resources
Constrained-Text-Genera
opentau - Using Large Language Models for Gradual Type Inference
torch-grammar
langroid - Harness LLMs with Multi-Agent Programming
TypeChat - TypeChat is a library that makes it easy to build natural language interfaces using types.