agency
simpleAI
agency | simpleAI | |
---|---|---|
5 | 11 | |
43 | 323 | |
- | - | |
7.0 | 7.3 | |
about 2 months ago | 12 months ago | |
Go | Python | |
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.
agency
-
Show HN: LLaMA tokenizer that runs in browser
Tokenizers seem to be a massive pain in the neck if you are just calling into an API to use your model. The algorithm itself is non-trivial, and they need pretty sizable data to function: the vocabulary and the merges, which just sit there, using memory. I'm writing https://github.com/ryszard/agency in Go, and while there's a good library for the OpenAI tokenization, if you want a tokenizer for the HF models the best I found was a library calling HF's Rust implementation, which makes it horrible for distribution.
However, at some point I realized that I needed not really the tokens, but the token count, as my most important use was implementing a Token Buffer Memory (trim messages from the beginning in such a way that you never exceed a context size number of tokens). And in order to do that I don't need it to be exactly right, just mostly right, if I am ok with slightly suboptimal efficiency (keeping slightly less tokens than the model supports). So, I took files from Project Gutenberg, and compared the ratio of tokens I get using a proper tokenizer and just calling `strings.Split`, and it seems to be remarkably stable for a given model and language (multiply the length of the result of splitting on spaces by 1.55 for OpenAI and 1.7 for Claude, which leaves a tiny safety margin).
I'm not throwing shade at this project – just being able to call the tokenizer would've saved me a lot of time. But I hope that if I'm wrong about the estimates bring good enough some good person will point out the error of my ways :)
-
Understanding GPT Tokenizers
How I wish this post had appeared a few days earlier... I am writing on my own library for some agent experiments (in go, to make my life more interesting I guess), and knowing the number of tokens is important to implement a token buffer memory (as you approach the model's context window size, you prune enough messages from the beginning of the conversation that the whole thing keeps some given size, in tokens). While there's a nice native library in go for OpenAI models (https://github.com/tiktoken-go/tokenizer), the only library I found for Hugging Face models (and Claude, they published their tokenizer spec in the same JSON format) calls into HF's Rust implementation, which makes it challenging as a dependency in Go. What is more, any tokenizer needs to keep some representation of its vocabulary in memory. So, in the end I removed the true tokenizers, and ended up using an approximate version (just split it in on spaces and multiply by a factor I determined experimentally for the models I use using the real tokenizer, with a little extra for safety). If it turns out someone needs the real thing they can always provide their own token counter). I was actually rather happy with this result: I have less dependencies, and use less memory. But to get there I needed to do a deep dive too understand BPE tokenizers :)
(The library, if anyone is interested: https://github.com/ryszard/agency.)
-
[P] I got fed up with LangChain, so I made a simple open-source alternative for building Python AI apps as easy and intuitive as possible.
I completely agree about langchain being brittle; what I really hate is that it's really hard to make sense about what is going on by reading the code. I was similarly frustrated and rolled my own thing on go (shameless plug): https://github.com/ryszard/agency
- 🏢🤖Agency - An Idiomatic Go Interface for the OpenAI API🚀
- Agency - An Idiomatic Go Interface for the OpenAI API (request for feedback)
simpleAI
-
[P] I got fed up with LangChain, so I made a simple open-source alternative for building Python AI apps as easy and intuitive as possible.
Not related to my own project SimpleAI despite the name, but looks like we can easily make the two work together, to keep it « simple ». Nice work!
-
Run and create custom ChatGPT-like bots with OpenChat
Using this as an opportunity to mention my own related project, perhaps it can end up on your nice list one day. :)
https://github.com/lhenault/SimpleAI
- [D] OpenAI API vs. Open Source Self hosted for AI Startups
-
StableLM released
You could have a look at a project I’ve been working on, SimpleAI, doing exactly this by replicating the OpenAI endpoints (you can then use their JS client for integration). Adding StableLM should be straightforward, I plan to add it to the examples in the upcoming days once I have a bit of time.
-
[P] LoopGPT: A Modular Auto-GPT Framework
I’ve built SimpleAI with exactly these kinds of use cases in mind. That should allow supporting any model with minimal / no change to your project. Good job and good luck with LoopGPT, that looks nice!
-
Using the API in Node
You could give this a shot: https://github.com/lhenault/simpleAI
-
[D] Would a Tesla M40 provide cheap inference acceleration for self-hosted LLMs?
I don't know if this applies to your use case but this would probably work if you are looking for an llm to help with programming. Haven't really played around with it but this may work for general llm tasks, it doesn't have a web UI though.
-
Alpaca, LLaMa, Vicuna [D]
As per llama.cpp specifically, you can indeed add any model, it's just a matter of doing a bit of glue code and declaring it in your models.toml config. It's quite straightforward thanks to some provided tools for Python (see here for instance). For any other language it's a matter of integrating it through the gRPC interface (which shouldn't be too hard for Llama.cpp if you're comfortable in C++). I'm planning to also add support for REST for model in the backend at some point too.
-
[D] Is there currently anything comparable to the OpenAI API?
Shameless plug but I’ve been recently working on SimpleAI, a project replicating the main endpoints from OpenAI API, allowing you to seamlessly switch from their API to your own one, as it’s compatible with OpenAI client.
-
[P] SimpleAI : A self-hosted alternative to OpenAI API
I wanted to share with you SimpleAI, a self-hosted alternative to OpenAI API.
What are some alternatives?
tokenizer - Pure Go implementation of OpenAI's tiktoken tokenizer
OpenChat - LLMs custom-chatbots console ⚡
Constrained-Text-Genera
dalai - The simplest way to run LLaMA on your local machine
Constrained-Text-Generation-Studio - Code repo for "Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio" at the (CAI2) workshop, jointly held at (COLING 2022)
AlpacaDataCleaned - Alpaca dataset from Stanford, cleaned and curated
llama-tokenizer-js - JS tokenizer for LLaMA and LLaMA 2
gptcli - ChatGPT in command line with OpenAI API (gpt-3.5-turbo/gpt-4/gpt-4-32k)
panml - PanML is a high level generative AI/ML development and analysis library designed for ease of use and fast experimentation.
StableLM - StableLM: Stability AI Language Models
feste - Feste is a free and open-source framework allowing scalable composition of NLP tasks using a graph execution model that is optimized and executed by specialized schedulers.
loopgpt - Modular Auto-GPT Framework