Rinat Abdullin

@abdullin
238 Followers
23 Following
55 Posts

Technical Consultant helping to build ML-driven products.

Newsletter "ML Under the Hood": https://abdullin.substack.com

Bloghttps://abdullin.com
Newsletterhttps://abdullin.substack.com/

Did you ever want to talk to your knowledge base or a journal?

Here is how to to build that with ChatGPTin less than 30 lines of Python code.

permalink: https://abdullin.com/llm/talk-to-your-knowledge-base/

How to talk to your knowledge base?

Use LLamaIndex and LangChain to build a conversational knowledge base.

I found a way to save 30min of doom scrolling and anxiety every day!

Solution: stop reading news and deploy an agent to track news-sites according to MY interests.

It would summarise relevant ones and send update in time for the morning coffee. Or will tell: ā€œI scanned 55 trending news articles today, nothing worthy of your attention.ā€

Check your inbox for the next newsletter on building ML-driven products!

- News Recap
- LangChain and LlamaIndex are awesome
- AI-driven businesses will come

You can also find it in the archive: https://tinyletter.com/abdullin

Being the Worst by Rinat Abdullin

Check your inbox for the next newsletter. This time on Meta LLaMa, OpenAI Turbo, and making ML product provide answers in 2-10 seconds.

https://tinyletter.com/abdullin

Being the Worst by Rinat Abdullin

Check your inbox for next newsletter šŸ—žļø

This time I’m writing about ML inference pipeline for a hardware prototype. Like Siri or Alexa, but covers a small native language that tech giants never care about.

Also available in archive here: https://tinyletter.com/abdullin/

Being the Worst by Rinat Abdullin

Not every week has to be super-productive. Or productive at all.

It is OK to just carry on.

This weekend newsletter was about Machine Learning Pipelines: what are they, how do they compare to CI/CD pipelines and why are they even needed?

You can find it in the archive:
https://tinyletter.com/abdullin

Being the Worst by Rinat Abdullin

I heard about using Chat GPT to boost productivity for so long, but didn't get a chance to use it.

Until today, when I asked it to write a polite inquiry about a delayed order in German šŸ˜‚

Today I realised that any NixOS instance could be used as a binary cache for the other systems.

It means, I could build a server or workstation once, then reuse my specific binaries across a fleet. Or to quickly setup my workspace VM.

Updating my development machine to the latest OS version.

This is the first time when I'm updating stuff in confidence, while knowing that I could safely boot to the previous version, if something goes wrong. NixOS is magical. šŸŖ„