Yeah, but you’re kinda missing the point, there is an existing eco system of ontologies and technologies using RDF, without need to reinvent something likely not as well thought out.
I'm not quite sure I follow. Today, graphiti extracts entities as nodes and facts between those nodes as edges. The nodes and edges store semantic data, like summaries of entities and facts representing the relationships between them (in addition to other metadata). Our searches are also based on this semantic data, and we aren't intending the extracted edge names to be used as filters as we are not doing any taxonomical classifications of nodes and edges.
In the near future, we intend to allow users of graphiti to input a custom schema (ontology), and we would use that to enforce a classifications of the extracted nodes and edges. In this case we are un-opinionated on what custom schema is being provided. You would be able to use an ontology that is made in-house or one of the many open source ones that exist in whatever field you are working in.
In neither case are we trying to recreate our own custom ontology or reinventing the wheel on how things are being classified.
Say I have a news article that describes a Government agency with a few departments and people who work in that department. Graphiti gives 2 options
1. Use whatever node and fact schemas Graphiti comes up with will be different everytime because it's using a non-deterministic LLM
2. Input my own schemas
1 will not be standardized deterministically, 2 will require a lot of work from me to figure out how to structure an organization. There are a million edge cases to think through
I think a big value add would be to just automatically use the Organization Ontology [1] and everyone who uses Graphiti on a text block that describes an organization will get that back.
Then defacto everyone's schemas can interact with each other. My business value prop is not going to be in defining an organization's structure, but it's still useful data for me have. Forming good Ontologies takes a lot of work.
I was thinking of just fine tuning my own LLM with RDF ontologies so it always returns graphs formatted in commonly used RDF schemas
EDIT: Just saw your edit 2 comments above. And yes exactly that is what I think would be useful. I'm looking for a project in this space that is opinionated cause frankly using a graph with a random assortment of node and edge types everytime I run it is not very useful.
So 4 years ago you was a junior (and your over 30, so how did you move into that, what’s your background). So junior, 4 years later given inflated title of ‘Head of’ and salary more than doubled… think you’re doing ok. If you was on job market I doubt you would get more than that and mostly be considered a senior engineer (although I have my suspicions you might not pass that, based on past experience of people working in start up silos, I may be wrong), I’m UK based.
Okay book, starts well but increasingly relies on math rather than an intuitive description of concepts at least to give you some context, had to go outside of the book at lot on later chapters, and found the diagrams decreasingly useful. The later chapters are more advanced to be fair
Yeah but don’t worry about it, benefit of maturity and wisdom and seniority, is you can forget son minor details.
Sleep, exercise, testosterone sups (nothing crazy) and some quite time to compose your thoughts will all help, you need to take some dedicated time/care for yourself, and you’ll be fine.
Are your notes really that interesting? I’ve written software that does this sort of thing commercially, if your materials are that sensitive you’d be using one of those packages.
I suspect this is just a dev with a fetish for obsessing over security. Like putting an expensive lock on a cheap bike!
One of those things is a reachable legal entity. The other is a pop-up content farm whose next instance is a few hours of work away. Google is the logical one to ask.
A library is a reachable entity. Do we ask them to purge their catalog of metadata that indicates a particular source contains particular data about someone? The premise is absurd.
>Google doesn’t produce the content, sites do, the issue is with those sites surely?
Google decides what someone will see when they Google your name, they might decide that the articles where you were accused of CP have much more priority then the single article 1 month later where you were found not guilty.
That can be extremely difficult to do false information is spread widely. Say a story is published by the Associated Press and then is republished on hundreds of other websites.
reply