Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

Knowledge graphs are really cool 🧠 What’s even cooler is LLMs + knowledge graphs backed by a graph db (NebulaGraph) 🔥 This presents an entirely new stack for retrieval-augmented generation (separate from vector db + top-k)! Now possible with LlamaIndex 🦙 👇

jerryjliu0's profile picture

Jerry Liu

71,459 subscribers

113,738 görüntüleme • 3 yıl önce •via X (Twitter)

LIVE

Anya Rossi• Live Now

Private livecam show

0 Yorum

Yorum bulunmuyor

Orijinal gönderinin yorumları burada görünecek

Benzer Videolar

In Knowledge Graphs for RAG, our latest short course, you’ll explore how knowledge graphs work, how to build with them, and create better retrieval augmented generation applications. Start today for free:
0:16

In Knowledge Graphs for RAG, our latest short course, you’ll explore how knowledge graphs work, how to build with them, and create better retrieval augmented generation applications. Start today for free:

DeepLearning.AI

13,987 görüntüleme • 2 yıl önce

Today SciPhi is open-sourcing Triplex, a SOTA LLM for knowledge graph construction. Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop. Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost.
0:11

Today SciPhi is open-sourcing Triplex, a SOTA LLM for knowledge graph construction. Triplex is so small that it can be used with SciPhi's R2R to build knowledge graphs directly from your laptop. Triplex outperforms few-shot prompted gpt-4o at 1/60th the inference cost.

Owen Colegrove

42,871 görüntüleme • 1 yıl önce

The `rebel-large` model is awesome for relation extraction 🔗 Paired with CUDA, it’s blazing fast ⚡️. With LlamaIndex 🦙 🦙, we can now build a knowledge graph over any text data super quickly! 🕸️ Full Colab notebook showing how you can use it:
0:14

The `rebel-large` model is awesome for relation extraction 🔗 Paired with CUDA, it’s blazing fast ⚡️. With LlamaIndex 🦙 🦙, we can now build a knowledge graph over any text data super quickly! 🕸️ Full Colab notebook showing how you can use it:

Jerry Liu

181,780 görüntüleme • 2 yıl önce

railway is so good – just deployed a node.js app w/ db in 10 minutes with no prior knowledge is this what great software looks like?
0:15

railway is so good – just deployed a node.js app w/ db in 10 minutes with no prior knowledge is this what great software looks like?

Aiden Bai

226,864 görüntüleme • 1 yıl önce

"Graphs are cool and modern! Text is for boring coders!" - continues to perform Undo for a single node movement for ~11 seconds in a simple graph after being for ~6 years in development 🤔 (pls deprecate it all already)
0:12

"Graphs are cool and modern! Text is for boring coders!" - continues to perform Undo for a single node movement for ~11 seconds in a simple graph after being for ~6 years in development 🤔 (pls deprecate it all already)

Mr F

61,296 görüntüleme • 2 yıl önce

Brilliant open-source tool from Anthropic Visualize internal LLM pathways through open attribution graphs. → Attribution graphs reveal which neurons and features drive each output token, turning the LLM’s black box into a clear map. They open-sourced a library that generates attribution graphs to trace how LLMs arrive at outputs. These graphs reveal internal activation flows and feature influences in popular open-weights models. 🧠 Attribution Graphs Graphs link model activations to output tokens. Nodes represent neurons or features. Edges show influence strength. Researchers inspect paths to see which components drive each decision. 🛠️ Toolchain and Frontend Circuit-tracer library works with models like Gemma-2-2b and Llama-3.2-1b. Demo notebooks illustrate multi-step reasoning examples. Neuronpedia hosts an interactive UI for graph exploration, annotation, and sharing. 🔍 Hypothesis Testing Users tweak feature values in graphs, regenerate outputs, and observe changes. This lets researchers validate whether specific circuits control behaviors like language translation or reasoning chains.
0:17

Brilliant open-source tool from Anthropic Visualize internal LLM pathways through open attribution graphs. → Attribution graphs reveal which neurons and features drive each output token, turning the LLM’s black box into a clear map. They open-sourced a library that generates attribution graphs to trace how LLMs arrive at outputs. These graphs reveal internal activation flows and feature influences in popular open-weights models. 🧠 Attribution Graphs Graphs link model activations to output tokens. Nodes represent neurons or features. Edges show influence strength. Researchers inspect paths to see which components drive each decision. 🛠️ Toolchain and Frontend Circuit-tracer library works with models like Gemma-2-2b and Llama-3.2-1b. Demo notebooks illustrate multi-step reasoning examples. Neuronpedia hosts an interactive UI for graph exploration, annotation, and sharing. 🔍 Hypothesis Testing Users tweak feature values in graphs, regenerate outputs, and observe changes. This lets researchers validate whether specific circuits control behaviors like language translation or reasoning chains.

Rohan Paul

27,197 görüntüleme • 1 yıl önce

Higgsfield supercomputer is now powered by Google Gemini More natural text generation, cinematic-quality visuals, precise frame-by-frame editing, and smarter search backed by deep global knowledge
0:10

Higgsfield supercomputer is now powered by Google Gemini More natural text generation, cinematic-quality visuals, precise frame-by-frame editing, and smarter search backed by deep global knowledge

Calira

23,100 görüntüleme • 20 gün önce

Bring your company's top thinking to every project with Rovo, AI powered by your org's collective knowledge. 🧠
0:15

Bring your company's top thinking to every project with Rovo, AI powered by your org's collective knowledge. 🧠

Atlassian

1,759,176 görüntüleme • 3 ay önce

RAG is not Memory for AI Agents. 5 AI memory engines to build agents that maintain long-term context and learn continuously: (Last 2 released just this month) 1. Zep builds and queries temporally-aware knowledge graphs that evolve with every interaction. 100% Opensource.
0:19

RAG is not Memory for AI Agents. 5 AI memory engines to build agents that maintain long-term context and learn continuously: (Last 2 released just this month) 1. Zep builds and queries temporally-aware knowledge graphs that evolve with every interaction. 100% Opensource.

Unwind AI

85,045 görüntüleme • 9 ay önce

Today, we are proud to upgrade our 10 + years journey with a new identity and launching a brand new nOS — the Network Operating System for Verifiable Enterprise AI, powered by OriginTrail's new Decentralized Knowledge Graph. Here's why we built it 🧵
0:10

Today, we are proud to upgrade our 10 + years journey with a new identity and launching a brand new nOS — the Network Operating System for Verifiable Enterprise AI, powered by OriginTrail's new Decentralized Knowledge Graph. Here's why we built it 🧵

Trace Labs - Trusted Context for AI Agents

1,802,021 görüntüleme • 7 gün önce

RAG is not Memory. AI agents need long-term memory to maintain context and learn continuously. 5 frameworks for AI agent memory. 100% opensource. 1. Graphiti builds temporally-aware knowledge graphs for AI agents that change over time with evolving relationships and context.
0:19

RAG is not Memory. AI agents need long-term memory to maintain context and learn continuously. 5 frameworks for AI agent memory. 100% opensource. 1. Graphiti builds temporally-aware knowledge graphs for AI agents that change over time with evolving relationships and context.

Unwind AI

293,513 görüntüleme • 1 yıl önce

This is TEACH TAPE from George Pickens Stack the DB and give the QB space to fade you to the sideline 👌
0:13

This is TEACH TAPE from George Pickens Stack the DB and give the QB space to fade you to the sideline 👌

Coach Dan Casey

379,318 görüntüleme • 7 ay önce

Autoencoder by hand✍️Excel~ I designed this exercise to show how an Encoder-Decoder network convert input to code and reconstruct input from code. It is annotated with equations, PyTorch, and graphs. 👇Join the 'AI Math' community. Download xlsx.
0:15

Autoencoder by hand✍️Excel~ I designed this exercise to show how an Encoder-Decoder network convert input to code and reconstruct input from code. It is annotated with equations, PyTorch, and graphs. 👇Join the 'AI Math' community. Download xlsx.

Tom Yeh

101,555 görüntüleme • 1 yıl önce

V8 DKG Launches Now: A New Dawn for AI in 2025🌟 As 2024 draws to a close, we're excited to announce the immediate launch of V8 Decentralized Knowledge Graph (DKG)! This monumental release is set to redefine AI's capabilities as we step into 2025. What Does V8 Bring to the Table? 🧠Decentralized AI: AI agents can now leverage a 'collective memory' at internet scale, drawing from a shared, yet sovereign, knowledge base. This means AI can provide more contextual, coherent, and accurate interactions without compromising data integrity or privacy. 🚀Unmatched Scalability: With the capability to handle billions of Knowledge Assets, V8 DKG sets the stage for AI to grow and learn in ways we've only imagined, supporting everything from decentralized science to industry 4.0. 🔐Trust and Integrity: With integrated decentralized Retrieval Augmented Generation (dRAG), V8 DKG promotes AI that's more accurate, less biased, and inherently trustworthy. How to V8👇 To update your node from V6 to V8, delegate your TRAC utility tokens, and learn more about creating, connecting and owning your Knowledge Assets, make sure to thoroughly read the following documentation: 👉 With V8 DKG launch, you may now access the new: V8 Explorer👉 AND Staking Dashboard 👉 You may now also participate in V8 Staking Security Bounty by delegating new TRAC stake and report your findings. Read more: 👉 The V8 Staking Security Bounty will importantly contribute to the so-called tuning phase of V8 DKG launch (V8.0 to V8.1). Let's break records, as we usher in a new era of Internet Scale OriginTrail!
0:15

V8 DKG Launches Now: A New Dawn for AI in 2025🌟 As 2024 draws to a close, we're excited to announce the immediate launch of V8 Decentralized Knowledge Graph (DKG)! This monumental release is set to redefine AI's capabilities as we step into 2025. What Does V8 Bring to the Table? 🧠Decentralized AI: AI agents can now leverage a 'collective memory' at internet scale, drawing from a shared, yet sovereign, knowledge base. This means AI can provide more contextual, coherent, and accurate interactions without compromising data integrity or privacy. 🚀Unmatched Scalability: With the capability to handle billions of Knowledge Assets, V8 DKG sets the stage for AI to grow and learn in ways we've only imagined, supporting everything from decentralized science to industry 4.0. 🔐Trust and Integrity: With integrated decentralized Retrieval Augmented Generation (dRAG), V8 DKG promotes AI that's more accurate, less biased, and inherently trustworthy. How to V8👇 To update your node from V6 to V8, delegate your TRAC utility tokens, and learn more about creating, connecting and owning your Knowledge Assets, make sure to thoroughly read the following documentation: 👉 With V8 DKG launch, you may now access the new: V8 Explorer👉 AND Staking Dashboard 👉 You may now also participate in V8 Staking Security Bounty by delegating new TRAC stake and report your findings. Read more: 👉 The V8 Staking Security Bounty will importantly contribute to the so-called tuning phase of V8 DKG launch (V8.0 to V8.1). Let's break records, as we usher in a new era of Internet Scale OriginTrail!

OriginTrail

561,104 görüntüleme • 1 yıl önce

Autoencoder by hand✍️Excel~ I designed this exercise to show how an Encoder-Decoder network convert input to code and reconstruct input from code. It is annotated with equations, PyTorch, and graphs. I also made a medium version.👇Join the 'AI Math' community. Download xlsx.
0:15

Autoencoder by hand✍️Excel~ I designed this exercise to show how an Encoder-Decoder network convert input to code and reconstruct input from code. It is annotated with equations, PyTorch, and graphs. I also made a medium version.👇Join the 'AI Math' community. Download xlsx.

Tom Yeh

54,473 görüntüleme • 1 yıl önce

🚨NEW: Tucker Carlson "REALLY HAPPY" with Trump Admin Epstein Files release🚨 "His administration just released more than 3 million documents ... that's a win for exposure, for transparency, for knowledge. And knowledge is the predicate of change." Daily Caller
0:17

🚨NEW: Tucker Carlson "REALLY HAPPY" with Trump Admin Epstein Files release🚨 "His administration just released more than 3 million documents ... that's a win for exposure, for transparency, for knowledge. And knowledge is the predicate of change." Daily Caller

Jason Cohen 🇺🇸

49,943 görüntüleme • 3 ay önce

New Dolphins’ safety Minkah Fitzpatrick sharpening his DB skills @ All Eyes DB Camp 💪🏾🏈🔥
0:14

New Dolphins’ safety Minkah Fitzpatrick sharpening his DB skills @ All Eyes DB Camp 💪🏾🏈🔥

DB Tips - Chad Wilson

40,609 görüntüleme • 11 ay önce

playing an entirely different sport out here. Dakota Guerrant 6’1 190 Wr/Db/Ath 2027 💪🏽
0:15

playing an entirely different sport out here. Dakota Guerrant 6’1 190 Wr/Db/Ath 2027 💪🏽

SFE

14,092 görüntüleme • 4 ay önce

Finally! A RAG over code solution that actually works (open-source). Naive chunking used in RAG isn't suited for code. This is because codebases have long-range dependencies, cross-file references, etc., that independent text chunks just can't capture. Graph-Code is a graph-driven RAG system that solves this. It analyzes the Python codebase and builds knowledge graphs to enable natural language querying. Key features: - Deep code parsing to extract classes, functions, and relationships. - Uses Memgraph to store the codebase as a graph. - Parses pyproject to understand external dependencies. - Retrieves actual source code snippets for found functions. Find the repo in the replies!
0:15

Finally! A RAG over code solution that actually works (open-source). Naive chunking used in RAG isn't suited for code. This is because codebases have long-range dependencies, cross-file references, etc., that independent text chunks just can't capture. Graph-Code is a graph-driven RAG system that solves this. It analyzes the Python codebase and builds knowledge graphs to enable natural language querying. Key features: - Deep code parsing to extract classes, functions, and relationships. - Uses Memgraph to store the codebase as a graph. - Parses pyproject to understand external dependencies. - Retrieves actual source code snippets for found functions. Find the repo in the replies!

Avi Chawla

121,861 görüntüleme • 11 ay önce

#PortStrike I need someone with more knowledge to tell me what’s really ABout to happen tomorrow
0:10

#PortStrike I need someone with more knowledge to tell me what’s really ABout to happen tomorrow

yaboibunnie

18,218 görüntüleme • 1 yıl önce