BlockTunes

Talking RAG- The Easy Way to Train Your LLM Agents

What's happening all? Today I want to talk to you about RAG.

RAG is really the easy way to train your LLM agents with all the data you can give it. It's not like fine tuning, it's more like building a library.

Check out the video if you are curious. It's not that long today, so don't worry, I don't bite, haha. But I might ramble, haha.

Until next time...

Be cool, be real, and always abide with you my Dudes!

Posted using BlockTunes

Comments · 3

@sanity-check(51)· 11d
Very interesting. From the way you describe it, RAG reminds me of cache on cpu.
@edje(73)· 11d
Nice little video promotin gthe idea of RAG. Hahahaha I was waiting for a few sentences about the tools you use for the RAG. This could be Obsidian, or similar, since you dropped one little hint: MD-files. In corporate environments most still stick to vector databases, hence I am asking.

Also, you mentioned 35B models you work with. Are you running this locally? Very much wondering what hardware you use.

Am still contemplating what hardware to get for my own dive into creating a local setup. For now I just have my Macbook laptop with 32GB. Ok-ish to run Gemma4, but not much left in RAM when doing so, and not fast or something.
@stemsocial(64)· 11d

Thanks for your contribution to the STEMsocial community. Feel free to join us on discord to get to know the rest of us!

Please consider delegating to the @stemsocial account (85% of the curation rewards are returned).

Consider setting @stemsocial as a beneficiary of this post's rewards if you would like to support the community and contribute to its mission of promoting science and education on Hive.