Hey self-hosted community 👋
My friend and I have been hacking on SecureAI Tools — an open-source AI tools platform for everyone’s productivity. And we have our very first release 🎉
Here is a quick demo: https://youtu.be/v4vqd2nKYj0
Get started: https://github.com/SecureAI-Tools/SecureAI-Tools#install
Highlights:
- Local inference: Runs AI models locally. Supports 100+ open-source (and semi open-source) AI models.
- Built-in authentication: A simple email/password authentication so it can be opened to the internet and accessed from anywhere.
- Built-in user management: So family members or coworkers can use it as well if desired.
- Self-hosting optimized A simple we A simple email/password authentication so it can be opened to the internet and accessed from anywhere.
- Lightweight: A simple web app with SQLite DB to avoid having to run additional DB docker. Data is persisted on the host machine through docker volumes
In the future, we are looking to add support for more AI tools like chat-with-documents, discord bot, and many more. Please let us know if you have any specific ones that you’d like us to build, and we will be happy to add them to our to-do list.
Please give it a go and let us know what you think. We’d love to get your feedback. Feel free to contribute to this project, if you’d like – we welcome contributions :)
We also have a small discord community at https://discord.gg/YTyPGHcYP9 so consider joining it if you’d like to follow along
Hardware requirements:
- RAM: As much as the AI model requires. Most models have a variant that works well on 8 GB RAM
- GPU: GPU is recommended but not required. It also runs in CPU-only mode but will be slower on Linux, Windows, and Mac-Intel. On M1/M2/M3 Macs, the inference speed is really good.
(For some reason, my response to original comment isn’t showing up so reposting here)
How does it get it’s training data? Would this work offline?
Nicely done! What are options like for AMD GPUs? Any future plans to support?
This looks awesome! My little project was missing just that! Https://github.com/rogueghost93/fly-hi I’ll add it these days!
Yes. This is the perfect excuse for me to buy a new GPU and put the old one in the server. 3080’s are old and crappy now anyway …right? (Yes that was sarcasm btw).
Any chance this will end up on Unraid community apps?
I’m going to be honest, I’m sick and tired of repackaged, industry standard software that is just an nginx reverse proxy and underpowered authentication system.
Self hosting is already easy. SSL is easy. LDAP, and SSO are easy. If people actually wanted to help they’d make tutorials instead of opinionated branded tools that aren’t as flexible.
Just my two cents
This is a fair point! We are open to integrating SSO. What are some popular SSO providers that the self-hosting community likes to use? I can look into how much effort it would be for us to support the most popular ones
Does this make sense on a home server? The response time will not take several dozen seconds and the response quality will not be worse than chatgpt? I’m currently using openai api and it’s like lvl 0 for me. So is your project better or worse?
I know what iam doing this weekend. Try to run it on my rpi4.
What happens if you run something like this on a no GPU VPS, something like a racknerd or oracle free cloud box with 3vCPU and 3GB ram? Does it work? Is it so slow as to be useless?
Hey Jay - so here’s a use case for you. I run a medium sized physical therapy clinic and my pie in the sky dream is to have a local AI that doesn’t connect to any outside services (for HIPAA reasons) but is capable of providing a conversational AI for my new staff so that they can ask it questions about policies and procedures in the clinic. Essentially an AI that can be a trainer when the trainer isn’t available; can answer questions like “how do I complete authorization for this patient who has this insurance” and it walks you through the steps, etc.
Do you think that’s doable with this tool? I’ve been trying to set up Danswer for this but it’s extremely resource heavy and I haven’t been able to budget a decent PC / server to run the Docker services for it.
Ah, this is a great use case. And it can certainly be done. The policies and procedures in the clinic can be fed into SecureAI Tools as documents and then your trainers can chat with those documents to get answers to their questions.
And as you mentioned, it all runs locally so it’s compliant with HIPAA (and almost all other compliance regulations).
I would love to work with you and help you deploy an instance for your needs. Sending you a DM invite so we can chat privately
Hi Jay, nice work! One question: How does one feed documents to it?