Viewing profile — joewferrara

[dead]

I think you mean x*x = -1, for which I agree with your point.

right now we support txt, csv, tsv, docx, xlsx, pdf, png, tif, tiff, jpg, and jpeg filetypes. we support either local files or aws s3 as the document store where the files are read…

that's a good question. for this use case, we have a custom models feature where the user can define an entity type (types) they're interested in and then a custom ner model is tra…

The built in static, I'm not sure if it's purposeful or not, but I like it. If it is purposeful, it's a nice touch.

kevin buzzard is a very good(usually math) expositor with a bent towards programming. love it

I tried out Amazon Bedrock, and used Tonic Validate to do a head to head comparison of very simple RAG system's built using embedding and text models available in Amazon Bedrock. I…

Is the staff (which includes you) is all volunteers, there’s so reason to expect or want people to have a “get shit done” attitude. You should all appreciate that you’re putting in…

Tonic's RAG evaluation platform is Tonic Validate, which has open source RAG metrics https://github.com/TonicAI/tonic_validate , and a web app for tracking and monitoring RAG perfo…

They show that a decoder only transformer (which gpts are) are rnns with infinite hidden state size. Infinite hidden state size is a pretty strong thing! Sounds interesting to me.

Where we are today is a world where people do not generally worry about nuclear bombs being dropped. So seems like a pretty good outcome in that example.

Yeah but for non profits it’s worse than for profits and that’s the point. At for profit companies everyone (the board included) is trying to make money. That’s the end goal, and m…

Every prime is odd and 2 is the oddest of them all!

Amazing how simple the proof is. 37 is my new favorite prime number, haha.

The interesting point/question in this is whether Open AI will invest in hardware to build a ChatGPT interface in the future that allows for less friction of use than just “being a…

Gauss died in 1855 and his work still influences modern mathematics. Someone told me while in grad school that in number theory we’re still figuring out stuff that Gauss already kn…

I enjoy Sharp Tech (Stratechery’s podcast), though unfortunately it’s mostly paywalled but has free episodes. It’s good for the business side of big tech and the two people on it, …

Author here. The linked Jupyter notebook shows how to use tvalmetrics, a RAG metrics Python package, to evaluate RAG query engines built using LlamaIndex on a dataset of Paul Graha…

It's true that there are not a lot of datasets for benchmarking RAG. RAG applications are so tailored to the specific data being used as well as the use case, that a benchmark data…

tvalmetrics is similar to ragas for sure, and we really like ragas. tvalmetrics has structural differences as well as differences in the specific metrics when compared to ragas. Wi…

Joe here. This is a good question, and always a challenge when using a test set to measure the performance of an LLM/AI/ML application. The answer is to make the test dataset consi…