Viewing profile — jonathan-adly

Do you know what NPS is? That's how the comment started. Patients like it. Because the alternative is to stay on hold for 20+ minutes, and then get it wrong. (Or have no pharmacies…

https://www.healthaffairs.org/doi/abs/10.1377/hlthaff.2024.0... Of the 88,930 retail pharmacies operating during 2010–20, 29.4 percent had closed by 2021.

Very much clueless commentary. Retail pharmacies in the US are dying dozens a day. They don't have margin to support people answering the phone like tech companies with 80% margin …

NPS typically improves because no one stays on hold for 20+ mins anymore. People have no ideas have pharmacies work. Pharmacies don't control how much they pay for drug, or how muc…

So - I run a company that does AI agents for pharmacy. We are at Series B now and growing well - series C in 9-12 months given growth. We just acquired a competitor of that vendor …

I can’t believe this has 1 point, and buried. This is great find, very juicy, and would kill a few hot startups.

Basically- the same math as modern automated manufacturing. Super expensive and complex build-out - then a money printer once running and optimized. I know there is lots of bearish…

We have been running this playbook for the last 2 years in healthcare, and we have been super successful. Doubling every quarter over the last year. 70%+ profitability, almost 7 fi…

One of the most pleasant experiences I had writing code, is early AI days when we did hyperscript SSE. Super locality of behavior, super interesting way of writing Server Sent Even…

Lots of YC companies copy each other process and selection criteria. Basically- they all have the same blind spots and look for the same type of engineer. So, super easy to scam al…

I send this article as part of onboarding for all new devs we hire. It is super great to keep a fast growing team from falling into the typical cycle of more people, more complexit…

The “equivalent” here would be Jina-Clip (architecture-wise), not necessarily performance. The ColPali paper(1) does a good job explaining why you don’t really want to directly use…

So, there is a whole world with vision based RAG/search. We have a good open-source repo here with a ColPali implementation: https://github.com/tjmlabs/ColiVara

Great work! Honestly it helps so much just explaining these metrics for folks. Early on RAG was an art, now when things are stabilized a bit, it’s more of a science - and vendors s…

I would like to through our project in the ring. We use ColQwen2 over a ColPali implementation. Basically, search & extract pipeline: https://docs.colivara.com/guide/markdown

Hi HN, We recently launched ColiVara - a state of the art RAG API that is based on vision LLMs with a state of art performance on both text-heavy documents and visually-complex pag…

Here is a nice use-case. Put this in a pharmacy - have people hit a button, and ask questions about over-the-counter medications. Really - any physical place where people are easil…

Hi HN! We benchmarked two ways to improve the latency in RAG workflows with a multi-vector setup. Hybrid search using Postgres native capabilities and a relatively new method of to…

So - the synthetic QAs datasets in the Vidore datasets are exactly like that 90% text, 10% charts/tables. OCR + BM25 is at ~90% NCDG@5 which is pretty decent. ColPali/Ours is at ~9…

I would like to throw our project in the ring that solves this problem: https://github.com/tjmlabs/ColiVara 1. Uses half-vecs, so you cut down everything by half with no recall los…

I will do it - you are right. Lots of materials in the space is basically people selling their complex tools w/ learning as a lower priority

I would strongly advise against people learning based on LangChain. It is abstraction hell, and will set you back thousands of engineers hours the moment you want to do something d…

I would check out vision models as a technique to go around OCR errors. ColPali is the standard implementation & SOTA. Much better than OCR. We maintain a ready to go retrieval API…