Its called two step verification. Prevents someone from “guessing” the password but doesn’t stop someone who has physical access to the device with the password stored. Same as with e-mail or SMS codes, basically. I don’t think i recall any websites that detect i am using my phone and rely on a true “second factor” aside from enterprise applications where i got a hardware yubi key.
It is called 2 factor or multi-factor authentication. It should be something you know (password) and something you have (device). Storing totp with your password defeats the entire point of it.
How does someone take structured data from a database and turn it into unstructured data for an LLM? I know RAG is a thing but they talk in terms of documents not tables and fields.
Could the LLM derive that same California sales answer from just knowing the dataset, but not by writing sql?
Rather than converting the entirety of structured data into unstructured text, we opt to provide the language model with sample rows and the database schema. Utilizing this approach, the LLM is then tasked with generating a SQL query to address the posed question. An alternative strategy, as you've suggested, involves transforming all structured data into textual format and subsequently training an LLM to directly respond to queries. This method, however, presents several challenges:
Linearizing structured data into text risks losing the inherent organization by columns and rows, potentially obfuscating the structured information.
The amount of information encapsulated within large tables poses significant challenges for training or fine-tuning models, attributable to the extensive number of tokens required, which may prove prohibitive for many due to resource constraints.
I’m not sure if this is the same as pg queues but I just started using pg_notify with channels, and it’s so good.
Row update occurs as normal express api, but at the end I call pg_notify on some channel name. I pickup the message in a new thread via polling, and perform aggregate queries to a agg table. It’s like materialized views, but with no wasteful refreshes. Then I push the updates aggs back to the frontend via websockets.
What’s the right way to manage npm installs and deploy it to an AWS ec2 instance from github? Kubernetes? GitOps? EKS? I roll my own solution now with cron and bash because everything seems so bloated.
