Knowledge Graph

“So you'll see, you know, semantically or platforms are rebranding as context platforms and ontologies and knowledge graphs are rebranding as context platforms and data platforms are rebranding as context platforms. The model layers and the agent platforms are …”

“Normal rag often retrieves Chunks of text that look similar to the question, but it can struggle when the answer actually requires connecting different people across companies and topics and claims and events.”

“Eventually the truth is the best systems use both. The AI will understand relationships inside your business, and it will also know how to move through the right steps.”

“That actually interconnects things, not based on semantic, which is knowledge, but based on intention, which is in any conversation, in any process, there's one single unique intention at a time. And so it's a network of interconnected intentions. Anyways, we …”

“And we think that triplets actually Lead to worse performance because you have to traverse them a lot to get to any information.”

“I think like almost like every agent should have its own wiki that it's updating and that's, Persistent memory. That is a very weak knowledge graph. And you could strengthen it if you want more structure, but you may not need it.”

“Without SQL, you can't say you have a great knowledge graph.”

“Everything is the model. Like that's the thing that wins in the end. And it just, as the model gets better, it's it subsumes everything else. So, you know, at some point the model will encode its own knowledge graph. It'll encode its own like KV story if you j…”

“The core issue issue is actually to build the knowledge graph, right? The entities, the relationships. So if you say graph, graph, You know, databases or graph rag is going to kill vector rag and all that discussion. I think the first issue is to actually buil…”

“The reality is something gets lost in the chunking process in the, okay, well, those tend to, you know, like you don't really get the whole picture, so to speak, and maybe not even the right set of dimensions on the kind of broader picture. And it makes intuit…”

“Most ML practitioners would say that knowledge graph is kind of like a dirty word the graph database. People get graph religion, everything's a graph, and then they go really hard into it, and then they get a graph that is too complex to navigate.”

“The problem with knowledge graphs that we found is like, and I don't know if you can tell me what your experience has been, but they're great for representing the data, but then like using it at inference time is kind of challenging, like... Just like the LLM …”

“But I think in the real world, it gets a lot messier than like knowledge graph style of things where it's like, well, is there a relationship between these two nodes? Like, ah, I don't know. Like is, are these two separate nodes? Like those kinds of messy bord…”

“We believe that there's an opportunity to create a knowledge graph that has resolution that greatly exceeds what any You know, whether it's Bloomberg or LinkedIn currently has access to where we're getting as granular as person X submitted congressional testim…”

“The growth is coming primarily from, you know helping this company generate content with high accuracy by leveraging on the knowledge graph. So the knowledge graph is the foundation. And then on top of that, we start generating content and validating content. …”

“Of course, the data that you bring in, it's the first asset, but we have to improve it because otherwise there's no SEO value. But once we improve it, then there is not just SEO value. You have something way more valuable, which is you're going to build your A…”

“A knowledge graph is kind of a starting point for your AI strategy, but it's also important for Google because it represents a new sitemap. In terms of, you know, what are the concepts that matter for the business? How do we index them? What is the data, you k…”

“Whereas we had exposed hundreds of thousands of data sets and told people, go at it, the reality of the matter was that, you know, we had to connect the dots in our data in the data ourselves, and we had to merge the data together to make it Into one data mode…”

“There's two key components. One, it's the ability to embed metadata in the data structure itself, i.e. The attributes are known. So if you're talking about a person, they kind of always look away. A company, they always kind of look away, and that helps you mo…”

“Think of it as like a billion facts, ok?”

“Building these large graphs of information and knowledge that will completely revolutionize all fields in a very, you know, in the next few years.”

“We are looking to expand our ability to model this complicated problem out using information from something we call Knowledge Graph, where we collect very, very granular information about sharing behavior on just our content.”