正在加载视频...

视频加载失败

返回首页

Not a fan of Knowledge Graphs, but recently I started using them more often for a surprising reason: to build non-trivial private verifiers for agentic search. For those who don't know, building a private eval set for a scaffolded LLM in 2026 is really challenging, like seriously hard. It...

hxiao's profile picture

Han Xiao

19,559 subscribers

58,118 次观看 • 2 个月前 •via X (Twitter)

科学技术
LIVE

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!
3:46

Our new short course, Knowledge Graphs for RAG, is now available! Knowledge graphs are a data structure that is great at capturing complex relationships between data of multiple types. By enabling more sophisticated retrieval of text than similarity search alone, knowledge graphs can improve the context you pass to the LLM and the performance of your RAG applications. In this course, taught by Andreas Kollegger of Neo4j, you’ll - Explore how knowledge graphs work by building a graph of public financial documents from scratch - Learn to write queries that retrieve text and data from the graph and use it to enhance the context you pass to an LLM chatbot - Combine a knowledge graph with a question-answer chain to build better RAG-powered chat systems Sign up here!

Andrew Ng

244,403 次观看 • 2 年前

IBM just dropped a 100% free 1-hour course on mastering Graph Engineering from scratch. this is the clearest breakdown of graph memory and multi-agent orchestration you'll find anywhere : • 00:00 - Introduction to knowledge graphs • 05:35 - Building your first agentic graph • 19:59 - Agentic memory powered by graphs • 30:39 - Graphs for multi-agent orchestration it replaces 10 paid courses on agentic engineering. watch it today, then read the article below on how to become a knowledge graph engineer ↓
50:30

IBM just dropped a 100% free 1-hour course on mastering Graph Engineering from scratch. this is the clearest breakdown of graph memory and multi-agent orchestration you'll find anywhere : • 00:00 - Introduction to knowledge graphs • 05:35 - Building your first agentic graph • 19:59 - Agentic memory powered by graphs • 30:39 - Graphs for multi-agent orchestration it replaces 10 paid courses on agentic engineering. watch it today, then read the article below on how to become a knowledge graph engineer ↓

Avid

157,171 次观看 • 22 天前

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:
2:26

Build better RAG by letting a team of agents extract and connect your reference materials into a knowledge graph. Our new short course, “Agentic Knowledge Graph Construction,” taught by Neo4j Innovation Lead Andreas Kollegger, shows you how. Knowledge graphs are an important way to store information accurately but they are a lot of work to build manually. In this course you’ll learn how to build a team of agents that turn data– in this case product reviews and invoices from suppliers–into structured graphs of entities and relationships for RAG. Learn how agents can automatically handle the time-consuming work of building graphs — extracting entities and relationships (e.g., Product "contains" Assembly, Part "supplied_by" Supplier, Customer review "mentions" Product), deduplicating them, fact-checking them, and committing them to a graph database — so your retrieval system can find right information to generate accurate output. For example, you can use agents to help trace customer complaints directly to specific suppliers, manufacturing processes, and product hierarchies, thus turning fragmented information into queryable business intelligence. Skills you’ll gain: - Build, store, and access knowledge graphs using the Neo4j graph database - Build multi-agent systems using Google’s Agent Development Kit (ADK) - Set up a loop of agentic workflows to propose and refine a graph schema through fact-checking - Connect agent-generated graphs of unstructured and structured data into a unified knowledge graph This course gets into the practicum of why knowledge graphs give more accurate information retrieval than vector search alone, especially for high-stakes applications where precision matters more than fuzzy similarity matching. Sign up here:

Andrew Ng

168,153 次观看 • 11 个月前

Stansbury: And you're not even here to answer that question. I literally find it disgusting. It is a privilege to serve in congress. I want to know from our colleagues who I can literally hear laughing and the other room, where were you? Where were you for the last eight weeks?
2:05

Stansbury: And you're not even here to answer that question. I literally find it disgusting. It is a privilege to serve in congress. I want to know from our colleagues who I can literally hear laughing and the other room, where were you? Where were you for the last eight weeks?

Acyn

102,316 次观看 • 9 个月前

Davide Cameron at the Foreign Affairs Committee: .. I don't know .. I don't really care for what I say .. It's a very difficult question to answer .. I'll answer a different question if I may .. I haven't seen it, I have't asked to see it .. I can't recall every single bit of paper that's put in front of me .. I don't want to be difficult .. I'm not a lawyer .. I'm not sure we'll get a lot further with this .. It's not for a government to say that's genocide ..The only way you get true peace and security is a two state solution
0:55

Davide Cameron at the Foreign Affairs Committee: .. I don't know .. I don't really care for what I say .. It's a very difficult question to answer .. I'll answer a different question if I may .. I haven't seen it, I have't asked to see it .. I can't recall every single bit of paper that's put in front of me .. I don't want to be difficult .. I'm not a lawyer .. I'm not sure we'll get a lot further with this .. It's not for a government to say that's genocide ..The only way you get true peace and security is a two state solution

Farrukh

248,245 次观看 • 2 年前

In a recent interview, Howard Stern asked celebrated singer-songwriter Paul Simon a deeply personal question: “Is there a God? Because I need to know. I’m getting older. Is this it for me? Am I going to die, and that’s it? Or am I going somewhere?” Then Howard added, “Please answer this in a serious manner.” That’s a really important question—one that everyone should eventually ask. And I want to give an answer. Not my answer, because my personal opinion isn’t any more or less important than anyone else’s. What matters is God’s answer to that question, and we find it in the pages of the Bible. Check out this video..
4:03

In a recent interview, Howard Stern asked celebrated singer-songwriter Paul Simon a deeply personal question: “Is there a God? Because I need to know. I’m getting older. Is this it for me? Am I going to die, and that’s it? Or am I going somewhere?” Then Howard added, “Please answer this in a serious manner.” That’s a really important question—one that everyone should eventually ask. And I want to give an answer. Not my answer, because my personal opinion isn’t any more or less important than anyone else’s. What matters is God’s answer to that question, and we find it in the pages of the Bible. Check out this video..

Greg Laurie

32,653 次观看 • 1 年前

$GOOG's Ruth Porat says the biggest risk in the AI buildout is the ROI question, and focusing on short-term tactics at the cost of building a great company. "I think the biggest risk for everyone is when the question is asked, which it often is, how do you get to an ROI? That's going to force our teams to do something short-term and tactical. You can always do a cost cut to get something to drop to the bottom line, and that is not a way to build a great company." "So I think the risk is don't be so in the moment maniacally focused on what is it, but have a right mix of an engine that's continuing to drive the business, which also explains why you need to start building early for growth so that you can grow into it." ____ Follow Fireside Alpha for more daily highlights of key business and technology conversations.
0:32

$GOOG's Ruth Porat says the biggest risk in the AI buildout is the ROI question, and focusing on short-term tactics at the cost of building a great company. "I think the biggest risk for everyone is when the question is asked, which it often is, how do you get to an ROI? That's going to force our teams to do something short-term and tactical. You can always do a cost cut to get something to drop to the bottom line, and that is not a way to build a great company." "So I think the risk is don't be so in the moment maniacally focused on what is it, but have a right mix of an engine that's continuing to drive the business, which also explains why you need to start building early for growth so that you can grow into it." ____ Follow Fireside Alpha for more daily highlights of key business and technology conversations.

Fireside Alpha

38,361 次观看 • 1 个月前

Queer theorist Judith Butler attempts a response to Matt Walsh's "What Is a Woman?" and it's just "You're angry and you hate Socrates" "I can't help noting that the people who pound the table like, 'It's a simple fact, we should have a simple answer.' They're angry. They're insistent. They're frustrated. I mean, just look at what the emotional aura is of that claim. 'We need a simple truth.' And like, whoa, why are we so angry about that?" "I ask the same question. What is a woman? Freud asked the question: what does a woman want? But you could also say, what is a woman? My own sensibilities say it's a great question, but it's wondrous. It's wonderful. Let's keep that question open, because you know what? There are going to be a lot of different ways of answering and will give us access to human complexity. And then we'll know more about the world and we'll be able to affirm the human in its complexity rather than putting it into fixed boxes and smashing in those nails. So for me, 'What is a woman' is a great question, but I would just keep it open." "This is a movement that seeks to control knowledge, to suppress knowledge, to stop us from questioning -- even to attack Socrates, who taught us the absolute importance of open inquiry." "The anti-gender ideology movement is an attack on knowledge and an attack on open inquiry."
4:35

Queer theorist Judith Butler attempts a response to Matt Walsh's "What Is a Woman?" and it's just "You're angry and you hate Socrates" "I can't help noting that the people who pound the table like, 'It's a simple fact, we should have a simple answer.' They're angry. They're insistent. They're frustrated. I mean, just look at what the emotional aura is of that claim. 'We need a simple truth.' And like, whoa, why are we so angry about that?" "I ask the same question. What is a woman? Freud asked the question: what does a woman want? But you could also say, what is a woman? My own sensibilities say it's a great question, but it's wondrous. It's wonderful. Let's keep that question open, because you know what? There are going to be a lot of different ways of answering and will give us access to human complexity. And then we'll know more about the world and we'll be able to affirm the human in its complexity rather than putting it into fixed boxes and smashing in those nails. So for me, 'What is a woman' is a great question, but I would just keep it open." "This is a movement that seeks to control knowledge, to suppress knowledge, to stop us from questioning -- even to attack Socrates, who taught us the absolute importance of open inquiry." "The anti-gender ideology movement is an attack on knowledge and an attack on open inquiry."

Breitbart News

221,924 次观看 • 1 个月前

Tucker: "Who is 'them'? Clearly there is a very well-organized, very well-funded effort to eliminate the White population of Europe?" Eva pontificates for a minute then says, “Honestly… I don’t know. I can’t answer that question.” Really? These people aren’t going to make it.
1:06

Tucker: "Who is 'them'? Clearly there is a very well-organized, very well-funded effort to eliminate the White population of Europe?" Eva pontificates for a minute then says, “Honestly… I don’t know. I can’t answer that question.” Really? These people aren’t going to make it.

Tom Hennessy

83,498 次观看 • 7 个月前

A DoorDasher left someone's order in a parking lot so a guy from one of the buildings decided to try and find out who it belonged to. I don't know what the policy is when you can't find the person but leaving it in a parking lot is probably not on the list.
2:34

A DoorDasher left someone's order in a parking lot so a guy from one of the buildings decided to try and find out who it belonged to. I don't know what the policy is when you can't find the person but leaving it in a parking lot is probably not on the list.

꧁Bobbi꧂

52,017 次观看 • 4 个月前

Engineers and salespeople think in completely different ways. - Engineers: "If you ask them a question, a hundred percent of them will try and think of what is the correct answer to that question." - Salespeople: "If you're a salesperson, your first thought isn't: what's the answer? It's: why are you asking me that question?" "And so if you have an engineer talking to a good sales guy, it's going to upset them. Because they're often not gonna answer the question." "The guys who are good at the job get rejected, because you don't like them. And then the people who are terrible at it, those are the ones that ended up getting hired." "These CEOs just wanna take a guy who failed the engineering test, put a clean shirt on him and make him the head of sales." benahorowitz.eth with Brian Halligan
1:27

Engineers and salespeople think in completely different ways. - Engineers: "If you ask them a question, a hundred percent of them will try and think of what is the correct answer to that question." - Salespeople: "If you're a salesperson, your first thought isn't: what's the answer? It's: why are you asking me that question?" "And so if you have an engineer talking to a good sales guy, it's going to upset them. Because they're often not gonna answer the question." "The guys who are good at the job get rejected, because you don't like them. And then the people who are terrible at it, those are the ones that ended up getting hired." "These CEOs just wanna take a guy who failed the engineering test, put a clean shirt on him and make him the head of sales." benahorowitz.eth with Brian Halligan

a16z

173,173 次观看 • 5 个月前

.Elon Musk (worth $250B) answers why he’s still working: I think it's a good question you asked, because it goes to, like, at a foundational level, what is my philosophy, and why does it lead to this conclusion? So the reason is that when I was a teenager, I had, like, an existential crisis to try to figure out what's the meaning of life. There doesn't seem to be any meaning. For me, at least the religious texts, and I read all of them that I could get my hands on did not seem convincing. Then I started reading the philosophers. Be careful of reading German philosophers as a teenager. It's definitely not going to help with your depression. So reading Schopenhauer, Nietzsche, as an adult, it's much more manageable. But as a kid, you're like, “Whoa.” So then I was like, “Man, I'm just struggling to find meaning in life here.” And then I read Hitchhiker's Guide to the Galaxy. And basically what Douglas Adams was saying is that we don't really know what the right questions are to ask. The question is not, “What's the meaning of life?” In The Hitchiker's Guide to the Galaxy, Earth it turns out is a big computer, and its goal is to answer the question, “What's the meaning of life?” And Earth comes up with the answer “42”. This is where the 42 number comes from. And 420 is just ten times 42. In that book, which is really sort of a book about, it's an existential philosophy book disguised as humor. They come to the conclusion that, no, the real problem is trying to formulate the question. And to really have the right question, you need a much bigger computer than Earth. And so maybe one way, I think, of characterizing this would be to say, “The universe is the answer. What is the question? Or what are the questions?” The more we can expand the scope and scale of consciousness, the better we can understand what questions to ask about the answer that is the universe. The more we can expand consciousness, become a multi-planet species, ultimately a multistellar species… we have a chance of figuring out what the hell is going on. And so this is why I think we should have more humans and both biological and digital consciousness. And why we should become a multi-planet species and a multistellar species is so that we can understand the nature of the universe. And then in order for that to occur, then we have to make sure that things are good on Earth. We don't want Earth to disappear, so sustainable energy is important.
3:11

.Elon Musk (worth $250B) answers why he’s still working: I think it's a good question you asked, because it goes to, like, at a foundational level, what is my philosophy, and why does it lead to this conclusion? So the reason is that when I was a teenager, I had, like, an existential crisis to try to figure out what's the meaning of life. There doesn't seem to be any meaning. For me, at least the religious texts, and I read all of them that I could get my hands on did not seem convincing. Then I started reading the philosophers. Be careful of reading German philosophers as a teenager. It's definitely not going to help with your depression. So reading Schopenhauer, Nietzsche, as an adult, it's much more manageable. But as a kid, you're like, “Whoa.” So then I was like, “Man, I'm just struggling to find meaning in life here.” And then I read Hitchhiker's Guide to the Galaxy. And basically what Douglas Adams was saying is that we don't really know what the right questions are to ask. The question is not, “What's the meaning of life?” In The Hitchiker's Guide to the Galaxy, Earth it turns out is a big computer, and its goal is to answer the question, “What's the meaning of life?” And Earth comes up with the answer “42”. This is where the 42 number comes from. And 420 is just ten times 42. In that book, which is really sort of a book about, it's an existential philosophy book disguised as humor. They come to the conclusion that, no, the real problem is trying to formulate the question. And to really have the right question, you need a much bigger computer than Earth. And so maybe one way, I think, of characterizing this would be to say, “The universe is the answer. What is the question? Or what are the questions?” The more we can expand the scope and scale of consciousness, the better we can understand what questions to ask about the answer that is the universe. The more we can expand consciousness, become a multi-planet species, ultimately a multistellar species… we have a chance of figuring out what the hell is going on. And so this is why I think we should have more humans and both biological and digital consciousness. And why we should become a multi-planet species and a multistellar species is so that we can understand the nature of the universe. And then in order for that to occur, then we have to make sure that things are good on Earth. We don't want Earth to disappear, so sustainable energy is important.

Arjun Khemani

15,599,354 次观看 • 1 年前

I added a Knowledge Graph to Cursor using MCP. You gotta see this working! Knowledge graphs are a game-changer for AI Agents, and this is one example of how you can take advantage of them. How this works: 1. Cursor connects to Graphiti's MCP Server. Graphiti is a very popular open-source Knowledge Graph library for AI agents. 2. Graphiti connects to Neo4j running locally. Now, every time I interact with Cursor, the information is synthesized and stored in the knowledge graph. In short, Cursor now "remembers" everything about our project. Huge! Here is the video I recorded.
11:39

I added a Knowledge Graph to Cursor using MCP. You gotta see this working! Knowledge graphs are a game-changer for AI Agents, and this is one example of how you can take advantage of them. How this works: 1. Cursor connects to Graphiti's MCP Server. Graphiti is a very popular open-source Knowledge Graph library for AI agents. 2. Graphiti connects to Neo4j running locally. Now, every time I interact with Cursor, the information is synthesized and stored in the knowledge graph. In short, Cursor now "remembers" everything about our project. Huge! Here is the video I recorded.

Santiago

155,647 次观看 • 1 年前

✨ To inspire more people to go build something now that we have AI to help us (especially non-tech people, cause I still know so many who are scared of building something): I added a [ BUILD IT ] button to It's like a mini-Lovable/Replit/v0: Any idea you see you like, you can click [ BUILD IT ], and it will use Opus 4.6 to build a landing page for it And then you can download the code it generated It's not a full startup of course, but a nice preview of what it can be, to give you an idea and inspire you to build it out further The code is live streamed also so you can see it being built 😊 Ironically this itself took me 1 hour to build with AI too Completely free and I pay for the tokens (please don't abuse it :D)
0:55

✨ To inspire more people to go build something now that we have AI to help us (especially non-tech people, cause I still know so many who are scared of building something): I added a [ BUILD IT ] button to It's like a mini-Lovable/Replit/v0: Any idea you see you like, you can click [ BUILD IT ], and it will use Opus 4.6 to build a landing page for it And then you can download the code it generated It's not a full startup of course, but a nice preview of what it can be, to give you an idea and inspire you to build it out further The code is live streamed also so you can see it being built 😊 Ironically this itself took me 1 hour to build with AI too Completely free and I pay for the tokens (please don't abuse it :D)

@levelsio

277,155 次观看 • 4 个月前

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:
6:02

Knowledge graphs for representing information are unbeatable. After this, you will never build a RAG system without knowledge graphs. It will take you five lines of code to build a knowledge graph with your data. I recorded a video to show you how you can do this. I used Cognee, an open-source library that outperforms any basic vector search approach in terms of retrieval relevance. They are collaborating with me on this post. Cognee is: • Easy to use • Reduces hallucinations • Open-source Here is a link to the repository: They also offer a comprehensive platform and UI with Python notebooks you can utilize to manage your data. Here is the link:

Santiago

126,434 次观看 • 10 个月前

The Sixers got better today, I can admit that But LeBron is not a good fit for Philly. The depth is still a major question mark And of course, Embiid’s health in a long playoff run can’t be counted on It takes a TEAM to win a championship…
1:07

The Sixers got better today, I can admit that But LeBron is not a good fit for Philly. The depth is still a major question mark And of course, Embiid’s health in a long playoff run can’t be counted on It takes a TEAM to win a championship…

Jack Settleman

50,383 次观看 • 24 天前

Great balance of showing compassion while sharing truth as Wes Huff responds to the question of why a good God would allow evil: "Well, that is arguably the hardest and most pressing apologetic question there is, because ultimately, the very tidy philosophical and theological answer isn't the right answer sometimes. You know, sometimes the right answer to the wrong question is the wrong answer, because I've encountered situations where someone has brought up a variation of the problem of evil to me, and I've just felt uneasy about maybe the tenor that they're coming at with the question...and asking them, 'You know, that's a great question. Why are you asking that question in particular?' and finding out once again (like the previous question related to it), they're personally hurting. And so, in that sense, I could give a tidy answer about if you're positing that something is good, you're positing that there's an objective good and evil, and if there's an objective good and evil, then you're positing an objective law, and objective law needs an objective lawgiver. So where do we find the groundwork for an objective lawgiver to begin with? Otherwise, you may not like certain things, but to say they ought not to happen is actually an ethical leap to an objective reality that you may or may not have groundwork for. But if that person is struggling because a family member of theirs has cancer, then that particular, maybe tidy, tied-up-in-a-nice-bow answer is not going to speak to them whatsoever. And so that's why that's the hardest question because there are actually very good answers to it, but often it doesn't speak to the person in front of you, because questions have questioners that sit behind them. And one of the pitfalls of my chosen field of ministry apologetics is that sometimes we give answers where we talk at people rather than with people. And there's a danger to that because the Christian faith isn't just an intellectual assent, right? It's a personal relationship. And that should also be played out in the answers that we give..."
3:18

Great balance of showing compassion while sharing truth as Wes Huff responds to the question of why a good God would allow evil: "Well, that is arguably the hardest and most pressing apologetic question there is, because ultimately, the very tidy philosophical and theological answer isn't the right answer sometimes. You know, sometimes the right answer to the wrong question is the wrong answer, because I've encountered situations where someone has brought up a variation of the problem of evil to me, and I've just felt uneasy about maybe the tenor that they're coming at with the question...and asking them, 'You know, that's a great question. Why are you asking that question in particular?' and finding out once again (like the previous question related to it), they're personally hurting. And so, in that sense, I could give a tidy answer about if you're positing that something is good, you're positing that there's an objective good and evil, and if there's an objective good and evil, then you're positing an objective law, and objective law needs an objective lawgiver. So where do we find the groundwork for an objective lawgiver to begin with? Otherwise, you may not like certain things, but to say they ought not to happen is actually an ethical leap to an objective reality that you may or may not have groundwork for. But if that person is struggling because a family member of theirs has cancer, then that particular, maybe tidy, tied-up-in-a-nice-bow answer is not going to speak to them whatsoever. And so that's why that's the hardest question because there are actually very good answers to it, but often it doesn't speak to the person in front of you, because questions have questioners that sit behind them. And one of the pitfalls of my chosen field of ministry apologetics is that sometimes we give answers where we talk at people rather than with people. And there's a danger to that because the Christian faith isn't just an intellectual assent, right? It's a personal relationship. And that should also be played out in the answers that we give..."

Melissa the Hopeful🏠Homemaker

116,060 次观看 • 4 个月前

Google just released a 1-hour course on building agentic knowledge Graphs from scratch: • 00:00 - Introduction to AI agents • 08:09 - Foundations of multi-agent systems • 13:25 - Introduction to Graph engineering • 23:27 - Environment setup for agentic Graphs • 47:43 - Building Graph RAG agents • 1:25:14 - Agent memory bank with graphs Worth more than 10 articles on loop engineering. Watch it today, then read how to become a graph engineer in the article below.
1:43:21

Google just released a 1-hour course on building agentic knowledge Graphs from scratch: • 00:00 - Introduction to AI agents • 08:09 - Foundations of multi-agent systems • 13:25 - Introduction to Graph engineering • 23:27 - Environment setup for agentic Graphs • 47:43 - Building Graph RAG agents • 1:25:14 - Agent memory bank with graphs Worth more than 10 articles on loop engineering. Watch it today, then read how to become a graph engineer in the article below.

Codez

194,869 次观看 • 27 天前