datadm VS joia

We've made a lot of data tooling things based on LLMs, and are in the process of rebranding and launching our main product.

1. sketch (in notebook, ai for pandas) https://github.com/approximatelabs/sketch

2. datadm (open source, "chat with data", with support for the open source LLMs (https://github.com/approximatelabs/datadm)

3. Our main product: julyp. https://julyp.com/ (currently under very active rebrand and cleanup) -- but a "chat with data" style app, with a lot of specialized features. I'm also streaming me using it (and sometimes building it) every weekday on twitch to solve misc data problems (https://www.twitch.tv/bluecoconut)

For your next question, about the stack and deploy:

From making a few variations on data chatbots in the past year, I found that my favorite / most fun to use ones seem to be more "chain-of-thought" and conversational rather than "retrieval-augmented" style.

Less about one-shotting the answer, and more about showing its work, if it errors, letting it self-correct. Latency goes up, but quality of the entire conversation also goes up, and feels like it builds more trust with the user. Key steps are asking it to "check its work", and watching it work through new code etc. (I open-sourced one version of this: https://github.com/approximatelabs/datadm that can be run entirely locally / privately)

From their article: I'm surprised they got something working well by going through an intermediate DSL -- thats moving even further away from the source-material that the LLMs are trained on, so it's an entirely new thing to either teach or assume is part of the in-context learning.

All that said, interesting: I'll definitely have to try out tencentmusic/supersonic and see how it feels myself.

Pretty good examples and simple explanations. I didn't realize Claude 2 was so good at working with PDFs natively. I wonder if they're doing anything special? Is this just due to larger context length they have?

Also, biased opinion on my part: I'm especially interested in watching how these things affect data science and data literacy as a whole. Code interpreter is a game changer in my opinion, the most powerful tool that somehow isn't getting as much press I think it deserves. I released an open source code-interpreter for data (https://github.com/approximatelabs/datadm) and even though I know how to code and use Jupyter daily, I still find myself doing analysis with it instead.

All in all, it does seem like the different models and agents are gaining "specialization" skill is actually good for the user (rather than just using a single jack of all trades super chat model). Even though GPT-4 takes the language model crown, there's still specialization that matters and improves quality for different tasks as discussed here.

I wonder if in 2-5 years we'll all use "a single" AI chat interface for everything, or every specialization continues to "win at its own vertical" and we just have AI embedded inside of every app

I completely agree that greatly increasing data accessibility is a huge unlock and value add.

A package I open sourced recently might be useful for use cases like this, https://github.com/approximatelabs/datadm It's essentially a chatGPT code interpreter, specifically designed to work with data, that can be run entirely on open models (eg. StarChat). True local mode operation.

Here's the github repo https://github.com/approximatelabs/datadm

I've built an open-source ChatGPT UI designed for team collaboration.

Github Link: https://github.com/joiahq/joia

Benefits vs the original:

Over the past few months, we've been building Joia, an open-source alternative to "ChatGPT for Teams" that allows organizations to provide their people with access to Large Language Models. Joia's Chat UI connects not only to OpenAI but also to any LLM, including popular open-source ones like Llama 2, Mixtral, and Zephyr.

We're thrilled to share our beta with you at https://github.com/joiahq/joia

Why We Built This:

We believe that all organizations, from startups to enterprises, will soon integrate LLMs into their day-to-day operations. And while the AI ecosystem is flourishing with a wide range of models, the current providers like ChatGPT, Bard or Copilot are creating closed environments that limit interactions to their owned models only.

We envision a future where AI is interoperable, and where people will choose the pick best model for their job. We are building Joia to make this freedom of choice a reality, offering an open-source product that is easy to use, organizations-ready and built for collaboration.

Features of Our Beta Version:

User Management: Easily provide user access to LLMs by adding them to a collaborative workspace.

Multi-LLM Access: Interact smoothly with models like GPT-4, Llama 2, Mixtral, Zephyr, Perplexity, Gemini, and others. More to be added soon.

Reusable Chatbots: Create pre-configured chatbots (also known as GPTs within the OpenAI ecosystem) and share them with your teammates.

Bring Your Own API Keys: Connect directly with the LLM provider of your choice by simply inserting their API keys. We currently support OpenAI, Openrouter, and Amazon Bedrock; with more to come soon.

Purchase Credits with Us and Consolidate Payments: In our cloud version, you can buy credits and centralize the billing for all users in the organization.

Open Source License: We offer the software under the Affero license, allowing anyone to self-host the platform.

We're still in the early stages and eagerly welcome your feedback and suggestions. Please feel free to try it out at no cost and tell us what you think.

Our main website: https://joia.so

GitHub: https://github.com/joiahq/joia

[Coming soon] Open source version: We are just preparing the code to make it available to anyone who wants to self host it. We'll also welcome anyone willing to contribute. Check out our Github Repository and star it if you're interested in the project!