正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Continued experiments with an autonomous CRM that slowly creates a massive knowledge graph. This time, I'm testing specific edge types, which loses flexibility, but also makes the output easier to query and understand.* *I'm using function call to get JSON, and the "enum" feature to specify edge types

Yohei

125,015 subscribers

72,501 次观看 • 2 年前 •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

10 条评论

Yohei 的头像

Yohei2 年前

Found and fixed an error! Starting to work more consistently with complicated inputs.

Yohei 的头像

Yohei2 年前

Not perfect, but it’s getting somewhere! Pictured: PayPal mafia and related cos (By the way, you can make your own at

Yohei 的头像

Yohei2 年前

How it’s working:

Yohei 的头像

Yohei2 年前

combining the wikipedia entries of OpenAI cofounders starts to look like this

Yohei 的头像

Yohei2 年前

hahahaha let's keep going

Yohei 的头像

Yohei2 年前

phew, took longer than i'd like to admit - but finally got this to be node type agnostic previously it was set to three node types (people, orgs, events), but now I can flexibly create new node types pictured: first few pages of langchain documentation (blue highlight showcases 'search' feature)

Yohei 的头像

Yohei2 年前

Now that the day is over, back to feeding in Wikipedia articles (mapping NVIDIA founders here) Next, going to set it up so I can try feeding in a csv of URLs

Yohei 的头像

Yohei2 年前

huzzah, got csv upload working! uploaded a few wikipedia articles via csv and just watched the knowledge graph grow. (15 min > 30 sec)

Yohei 的头像

Yohei2 年前

hindu dieties

Yohei 的头像

Yohei2 年前

okay, so for testing purposes i made a "latent input" endpoint that generates the graph based on a simple input (the core architecture is designed for easy "extensions", so this one just feeds an openai output into the same endpoint that receives scraped web content from the url_input endpoint)

相关视频

Writing and deploying Supabase edge functions can be time-consuming, but Lovable can help you a lot! Just connect it to Supabase and ask it to create an edge function with the feature that you need! It does a great job of understanding what exactly you need and implementing it!

Writing and deploying Supabase edge functions can be time-consuming, but Lovable can help you a lot! Just connect it to Supabase and ask it to create an edge function with the feature that you need! It does a great job of understanding what exactly you need and implementing it!

Tyler Shukert

15,530 次观看 • 1 年前

As Larry Ellison explains, there are two types of AI models: real-time models, also called AI on the edge, where you need ultra-low latency decisions (think autonomous driving or robotics), and models that don’t need an immediate response, like ChatGPT, where the system has time to reason. Real-time models require local compute inside the device, and these chips have nothing to do with the GPUs running in data centers. The AI-on-the-edge market is still largely untapped — and it’s going to be a multi-trillion-dollar opportunity. I believe $AMD will be one of the biggest beneficiaries

As Larry Ellison explains, there are two types of AI models: real-time models, also called AI on the edge, where you need ultra-low latency decisions (think autonomous driving or robotics), and models that don’t need an immediate response, like ChatGPT, where the system has time to reason. Real-time models require local compute inside the device, and these chips have nothing to do with the GPUs running in data centers. The AI-on-the-edge market is still largely untapped — and it’s going to be a multi-trillion-dollar opportunity. I believe $AMD will be one of the biggest beneficiaries

Daniel

151,698 次观看 • 7 个月前

WIP Just want to say that the video isn't for tomorrow because being "late" is part of the idea (for a joke, kinda :b) Also i'm using a different workflow this time, it's faster and better but I need to get used to it :/

WIP Just want to say that the video isn't for tomorrow because being "late" is part of the idea (for a joke, kinda :b) Also i'm using a different workflow this time, it's faster and better but I need to get used to it :/

Aguito V2

27,871 次观看 • 5 个月前

Transforming Invoice Data into JSON: Local LLM with LlamaIndex & Pydantic 🚀 Complete video: Code: I explain how to get structured JSON output with LlamaIndex and dynamic Pydantic class. This helps to implement the use case of data extraction from invoice documents. The solution runs on the local machine, thanks to Ollama. I'm using a MacBook Air M1 with 8GB RAM. LlamaIndex 🦙 Pydantic ollama #Python #LLM #RAG

Transforming Invoice Data into JSON: Local LLM with LlamaIndex & Pydantic 🚀 Complete video: Code: I explain how to get structured JSON output with LlamaIndex and dynamic Pydantic class. This helps to implement the use case of data extraction from invoice documents. The solution runs on the local machine, thanks to Ollama. I'm using a MacBook Air M1 with 8GB RAM. LlamaIndex 🦙 Pydantic ollama #Python #LLM #RAG

Andrej Baranovskij

147,949 次观看 • 2 年前

“I think my fans are they happy that I'm able to express and share my personal stories. they understand more about me, and but also at the same time like "You you got to stop with this magic man.. it's been too dark, so I'm prepping the next album”

“I think my fans are they happy that I'm able to express and share my personal stories. they understand more about me, and but also at the same time like "You you got to stop with this magic man.. it's been too dark, so I'm prepping the next album”

jackson loops

19,060 次观看 • 8 个月前

Brooks Koepka has sat and waited to get into the last two signature events as an alternate only to head home Thursday after not getting into the events. It's not the first time in his career it happened, but he also is understanding of the position he is in. Koepka is playing in Myrtle Beach this week. "The way I look at it is I'm itching to get in, but I'm accepting of where I'm at, and I understand that there's prices to pay for coming back, and I'm willing to accept those and whatever I have to do. "I knew this year was going to be challenging to even get in them. I kind of thought maybe by around U.S. Open, but to know that I'm kind of knocking on the door already is a good thing. Just the answer to everything is play better, and you're in."

Brooks Koepka has sat and waited to get into the last two signature events as an alternate only to head home Thursday after not getting into the events. It's not the first time in his career it happened, but he also is understanding of the position he is in. Koepka is playing in Myrtle Beach this week. "The way I look at it is I'm itching to get in, but I'm accepting of where I'm at, and I understand that there's prices to pay for coming back, and I'm willing to accept those and whatever I have to do. "I knew this year was going to be challenging to even get in them. I kind of thought maybe by around U.S. Open, but to know that I'm kind of knocking on the door already is a good thing. Just the answer to everything is play better, and you're in."

Cameron Jourdan

964,141 次观看 • 3 个月前

Today I’m incredibly excited to announce Wendy. Wendy is an operating system and developer platform for Physical AI — built to make it dramatically easier to build and deploy on NVIDIA Jetson, Raspberry Pi, and other edge devices. We think robotics, edge AI, industrial systems, autonomous machines, and smart cameras should be far simpler to create. Less setup. Less infrastructure pain. Faster time to first demo. This is the start of something big. Get started at

Today I’m incredibly excited to announce Wendy. Wendy is an operating system and developer platform for Physical AI — built to make it dramatically easier to build and deploy on NVIDIA Jetson, Raspberry Pi, and other edge devices. We think robotics, edge AI, industrial systems, autonomous machines, and smart cameras should be far simpler to create. Less setup. Less infrastructure pain. Faster time to first demo. This is the start of something big. Get started at

Maximilian Alexander

138,257 次观看 • 3 个月前

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!

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

244,365 次观看 • 2 年前

JSON columns in Postgres can be flexible, but too much flexibility can be risky as you might accidentally end up with malformed data. You can prevent this using the pg_jsonschema extension to easily define a schema for your JSON and JSONB columns!

JSON columns in Postgres can be flexible, but too much flexibility can be risky as you might accidentally end up with malformed data. You can prevent this using the pg_jsonschema extension to easily define a schema for your JSON and JSONB columns!

Tyler Shukert

17,480 次观看 • 1 年前

#Browns aren’t that far off IMO, which definitely makes the HC job an attractive one. But I think it’s also tailor made for a specific candidate to step right in and thrive 👇🏾

#Browns aren’t that far off IMO, which definitely makes the HC job an attractive one. But I think it’s also tailor made for a specific candidate to step right in and thrive 👇🏾

Emory Hunt

31,373 次观看 • 6 个月前

"I'm sick of chasing sick buildings." Have a quick listen to this one part of my TEDx talk where I list the types of calls I get *every single day* (and why, for the first time in my career, I'm optimistic about the beginning of the end of the sick building era.)

"I'm sick of chasing sick buildings." Have a quick listen to this one part of my TEDx talk where I list the types of calls I get every single day (and why, for the first time in my career, I'm optimistic about the beginning of the end of the sick building era.)

Joseph Allen

11,823 次观看 • 1 年前

Excited to announce that I'm going to begin working on a new podcast series (I know, I know) entitled Reports from the Edge. I will be interviewing people much smarter than myself in an attempt to understand our collapsing world. Have a look at the trailer and subscribe below!

Excited to announce that I'm going to begin working on a new podcast series (I know, I know) entitled Reports from the Edge. I will be interviewing people much smarter than myself in an attempt to understand our collapsing world. Have a look at the trailer and subscribe below!

Alex 🇵🇸

18,072 次观看 • 1 年前

Raw kicks off with Mick Foley calling out Edge before their Hardcore match this Sunday at WrestleMania. Mick has a gift for Edge, which is something that he'll be able to use as weapon. Edge opens up the box and pulls out a baseball bat, then heads to the ring to attack Foley, but The Hardcore Legend has a weapon of his own... a Barbed Wire Baseball Bat! Foley chases Edge & Lita off with the bat!

Raw kicks off with Mick Foley calling out Edge before their Hardcore match this Sunday at WrestleMania. Mick has a gift for Edge, which is something that he'll be able to use as weapon. Edge opens up the box and pulls out a baseball bat, then heads to the ring to attack Foley, but The Hardcore Legend has a weapon of his own... a Barbed Wire Baseball Bat! Foley chases Edge & Lita off with the bat!

OSJ

16,791 次观看 • 4 个月前

All heart! Down 16 players.. Desert Edge down 42-13 w/ 4:19 to go in the 3rd… they comeback and score a TD with no time left 42-41. They go for 2 and the win, get it — but a holding call brings it back. They decided to go for 2 again and can’t convert. Ballgame. Desert Edge Football

All heart! Down 16 players.. Desert Edge down 42-13 w/ 4:19 to go in the 3rd… they comeback and score a TD with no time left 42-41. They go for 2 and the win, get it — but a holding call brings it back. They decided to go for 2 again and can’t convert. Ballgame. Desert Edge Football

Cameron Cox

34,714 次观看 • 2 年前

claude just hit 54,000% returns running this auto-trading script and i'm showing you the exact process on stream. it's literally just taking liquidations data and testing to find an edge while we sleep. if you're still manually trading you need to watch this before your next liquidation

claude just hit 54,000% returns running this auto-trading script and i'm showing you the exact process on stream. it's literally just taking liquidations data and testing to find an edge while we sleep. if you're still manually trading you need to watch this before your next liquidation

Moon Dev

18,484 次观看 • 3 个月前