Just got to know about pinokio, I think they are taking the approach of replacing existing browsers. We are trying to empower existing browsers, both pros and cons and that's the major difference I can see.
We use Webllm under the hood and for text-to-text generation, the model compression is awesome and RAM usage is also less. But we are conducting more experiments, One thing we noticed is some quantized models using MLC sometimes start throwing gibberish, so will get back to you after more experiments on which is better.
Oh yes, because the library was so large, we decided to start by removing some things and porting, to be honest, one of the bad decisions of my life trying to Port JS to TS but luckily it only took 3 days and a few headaches!
Will add the encoders as needed, should be easy now, but a great point.
This is the start so yes at the current state, we aren't offering much, if you check the GitHub repo, we don't directly use Transformers.js but have forked their code to ts and removed things that caused build issues in some frameworks like next, etc due to node modules.
We are adding features like RAG and observability integrations so people can use these llms to perform more complicated tasks!
We are building a framework to run this tiny language model in the web so anyone can access private LLMs in their browser: https://github.com/sauravpanda/BrowserAI.
With just three lines of code, you can run Small LLM models inside the browser. We feel this unlocks a ton of potential for businesses so that they can introduce AI without fear of cost and can personalize the experience using AI.
Would love your thoughts and what we can do more or better!
btw had a request, I saw your repo lacks proper documentation. We are building an open source ai documentation system, I would love to try if I may have your permission to build docs and create a PR!
Our main focus is to create high-quality documentation as we improve. We are also considering how this documentation will be used by future developers and AI agents. One of our ideas is to implement an interface similar to Perplexity, but integrated with WebLLM, so users won’t have to worry about costs. You can find more information about it here; although it currently has many issues, we plan to launch a fine-tuned version of the LLM to enhance its performance. You can play with it here: https://demo.akiradocs.ai/aiSearch. Heads up its very slow and tends to break but we are improving on it constantly!
Additionally, we are exploring ways to improve the consumption of these documents and ensure they reach customers when they need them. Unfortunately, this project will be closed-source!
We have been developing an AI-powered documentation framework that automates generating user-facing documentation. We’ve designed a Notion-like user interface for editing content while maintaining support for MDX.
We would love your feedback on this and any additional features you would like to see.
Currently, we are also working on the capability to automatically generate documentation from your repository using AI.