Hacker News new | ask | show | jobs
by dmezzetti 598 days ago
I really appreciate that! Thank you.

It's been quite a ride from 2020. When I started txtai, the first use case was RAG in a way. Except instead of an LLM, it used an extractive QA model. But it was really the same idea, get a relevant context then find the useful information in it. LLMs just made it much more "creative".

Right before ChatGPT, I was working on semantic graphs. That took the wind out of the sails on that for a while until GraphRAG came along. Definitely was a detour adding the LLM framework into txtai during 2023.

The next release will be a major release (8.0) with agent support (https://github.com/neuml/txtai/issues/804). I've been hesitant to buy into the "agentic" hype as it seems quite convoluted and complicated at this point. But I believe there are some wins available.

In 2024, it's hard to get noticed. There are tons of RAG and Agent frameworks. Sometimes you see something trend and surge past txtai in terms of stars in a matter of days. txtai has 10% of the stars of LangChain but I feel it competes with it quite well.

Nonetheless I keep chugging along because I believe in the project and that it can solve real-world use cases better than many other options.

1 comments

I have a dozen or so tabs open at the moment to wrap my head around txtai and its very broad feature set. The plethora of examples is nice even if the python idioms are dense. The semantic graph bits are of keen interest for my use case, as are the pipelines and workflows. I really appreciate you continuing to hack on this.
You got it. Hopefully the project continues it's slow growth trajectory.