I have been building tons of applications.
My latest one is Gitroom. It helps you to:
- Schedule your posts on multiple social media platforms and cross-post them to publishing platforms such as DEV, Medium, and Hashnode.
- Track your GitHub repository metrics
- Monitor GitHub trendings
(it's open-sourced ππ»)
That's nice and all, but here is the real kicker.
Add AI to your application
I see tons of AI libraries every day, and most of them are really cool, but I ask myself, will they help me in real life?
Yes, babyagi might be the next big thing. But honestly, I don't see anything I can do with it.
So what can you do with AI, and what do people usually do?
I think in today's ChatGPT world and local LLMs, the use case is pretty simple:
Auto-complete content - perfect for Gitroom to let you generate additional information or use something like GitHub copilot.
Automation - You pass content to the LLM, which returns a JSON with operations you can perform.
Function calling - Mostly with ChatGPT, you pass different functions to the LLM, and they decide which one to run.
Miscellaneous - Classification, translation, etc.
I think "function calling" is not leveraged enough because adding it in a way that makes sense is complex.
Help your users with everything
I admit I love to build stuff, but I sometimes skip developing a good UX, which causes people to leave the system because they don't know what to do.
I think inherently, if you build systems for developers, you can get away with it - because they are more sophisticated.
But that is mostly not the case.
You should have:
- Onboardings
- Tutorials
- YouTube videos (inside your system, yes yes)
This is where AI can save you without writing too much code.
Add a chatbot that can do everything for you
So, one of the things more and more companies offer is a chatbot that can interact with your data and perform actions for the user.
For example, I can tell the chatbot I want to schedule a new post for Gitroom at 7:00 p.m. US time.
And it will do it for me.
The problem with most of the solutions I found is that they are:
- Not open-source
- It is not an infrastructure product but a complete product that is mainly for product managers.
CopilotKit can help you
So, I found this incredible open-source library licensed under MIT - which is fantastic.
It's just a chatbot sitting on your right sidebar.
You feed it with:
- Your current context information.
- Your data resources, such as your database, dropbox, Google Drive, etc.
- Different functions in the system can be called.
Once you have finished doing that, it's just like magic.
Does somebody want to schedule a post?
It will trigger the schedulePost
function.
Of course, it uses the ChatGPT "function calling" in the background, but it simplifies everything.
I think it fits any app. You can use it with big LLMs like ChatGPT / Gemini, but also with smaller ones like LLAMA2 and Mistral.
I started a new YouTube channel mostly about Tech, open-source, and marketing :)
If that's something that interests you, feel free to subscribe to it here:
https://www.youtube.com/@nevo-david?sub_confirmation=1
Top comments (12)
amazing
Thank you so much π
Cool! I'm glad you were able to leverage CopilotKit for gitroom (which is an awesome platform btw).
Thanks for the shout out!
github.com/CopilotKit/CopilotKit
It's just sooo good
Gitroom and Copilot both look very cool! Thanks for sharing!
Thank you for reading ππ»
I really love GitRoom and use it every day, thanks Nevo!
CopilotKit looks awesome too, I'll make sure to give it a try.
Thank you so much, Shai!
Great article Nevo, always a good read!
π
π
π