Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

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

83,377 subscribers

181,829 Aufrufe • vor 3 Jahren •via X (Twitter)

Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Training Wan 2.1-1.3B to use Qwen3-VL-2B text encoder. Doing 33% text only, 33% VL only, and 33% both. Just pretraining the two text input linear layers for now. It is amazing how quickly a model can adapt to a different text encoder. This is 25,750 steps, BS of 10.

Training Wan 2.1-1.3B to use Qwen3-VL-2B text encoder. Doing 33% text only, 33% VL only, and 33% both. Just pretraining the two text input linear layers for now. It is amazing how quickly a model can adapt to a different text encoder. This is 25,750 steps, BS of 10.

Ostris

26,469 Aufrufe • vor 2 Monaten

Fireworks blazing fast LLM inference is now available on Poe! Today, we’re excited to bring the power of the new Mistral 7B Instruct model to the Poe powered by our lightning-fast Fireworks inference platform. You can now have conversations with the Mistral 7B bot and even build your own bots on top of it. Try it here:

Fireworks blazing fast LLM inference is now available on Poe! Today, we’re excited to bring the power of the new Mistral 7B Instruct model to the Poe powered by our lightning-fast Fireworks inference platform. You can now have conversations with the Mistral 7B bot and even build your own bots on top of it. Try it here:

Fireworks AI

93,334 Aufrufe • vor 3 Jahren

this is over.. for traditional film studios Higgsfield just dropped Product-to-Video, you can now drop any product into any environment and.. the actor can even interact with it this is best way to do product commercial with AI.. for free here's how:

this is over.. for traditional film studios Higgsfield just dropped Product-to-Video, you can now drop any product into any environment and.. the actor can even interact with it this is best way to do product commercial with AI.. for free here's how:

el.cine

376,627 Aufrufe • vor 1 Jahr

I finally sat down and rewrote Displace for Figma from the ground up. It’s super fast, with a completely new set of effects, and now it can export filter code you can paste right into your site! Sooooon

I finally sat down and rewrote Displace for Figma from the ground up. It’s super fast, with a completely new set of effects, and now it can export filter code you can paste right into your site! Sooooon

Mike Bespalov

95,229 Aufrufe • vor 1 Jahr

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

OpenAI's Deep Research is getting a run for its money. Deep Lake was just released, and it's a different take on an AI system that can do deep research on your own data. You can use Deep Lake to build AI search with reasoning on your private and public data. (Look at the attached videos to get an idea of how it works.) If you want to research proprietary and sensitive data, Deep Research won't help you because it's limited to public data. Deep Lake, however, will allow you to use your private data. On top of that, Deep Lake supports multi-modal retrieval from the ground up. It uses vision language models for data ingestion and retrieval so that you can connect any data (PDFs, images, videos, structured data, etc.) You can even use mixed-data queries! Deep Lake can search your data from S3, Dropbox, and GCP. It learns from your queries over time, making the results as relevant to your work as possible!

Santiago

171,340 Aufrufe • vor 1 Jahr

you can now use mintlify to automatically build docs for arbitrary github repos (e.g. n8n here) with an agent powered by a skill reflecting everything we know about quality docs simply swap "github" with "mintlify" in the URL for any repo

you can now use mintlify to automatically build docs for arbitrary github repos (e.g. n8n here) with an agent powered by a skill reflecting everything we know about quality docs simply swap "github" with "mintlify" in the URL for any repo

Nick Khami

74,522 Aufrufe • vor 6 Monaten

I one-shotted a full slide deck in Lovable 🔥 A lot of founders still build slides in PowerPoint. But with AI, that feels super outdated tbh. Why would you build a powerpoint deck if you can build an interactive app that’s responsive, smart, and adaptable. If you use AI: → Everything is automatically animated + feels premium → You can get a full deck with one prompt. → Works on all screen sizes and is super dynamic. → You can share a link instead of sending files → See who viewed it, and measure analytics. I created a guide with all my prompt templates for building slides with AI. Want access? Comment “AI Deck” and I’ll share it with you.

I one-shotted a full slide deck in Lovable 🔥 A lot of founders still build slides in PowerPoint. But with AI, that feels super outdated tbh. Why would you build a powerpoint deck if you can build an interactive app that’s responsive, smart, and adaptable. If you use AI: → Everything is automatically animated + feels premium → You can get a full deck with one prompt. → Works on all screen sizes and is super dynamic. → You can share a link instead of sending files → See who viewed it, and measure analytics. I created a guide with all my prompt templates for building slides with AI. Want access? Comment “AI Deck” and I’ll share it with you.

Felix Haas

102,413 Aufrufe • vor 8 Monaten

⚡️Vercel dropped AI SDK 3.0 with Generative UI support. And It's amazing! You can transform text & image prompts into React UI in seconds. This is a paradigm shift in how we interact with AI, making it more accessible & engaging for everyone. 7 examples:

⚡️Vercel dropped AI SDK 3.0 with Generative UI support. And It's amazing! You can transform text & image prompts into React UI in seconds. This is a paradigm shift in how we interact with AI, making it more accessible & engaging for everyone. 7 examples:

Min Choi

84,531 Aufrufe • vor 2 Jahren

You can now add custom cover art and descriptions to any of your notebooks 🥳 This is perfect for curating an aesthetic grid or putting a personalized touch on your notebook before sharing it with the world. (We recommend uploading a 16x9 image, specifically of your hero)

You can now add custom cover art and descriptions to any of your notebooks 🥳 This is perfect for curating an aesthetic grid or putting a personalized touch on your notebook before sharing it with the world. (We recommend uploading a 16x9 image, specifically of your hero)

Gemini Notebook

185,395 Aufrufe • vor 5 Monaten

In flow matching, a coupling determines how noise and data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.

In flow matching, a coupling determines how noise and data samples are paired during training. The choice of coupling is important because it influences the geometry of trajectories at inference time. The simplest choice is the independent coupling, where noise and data points are paired arbitrarily. This can lead to curved trajectories as the model averages over many conflicting pairings. However, if we use optimal transport on batches of pairs, this leads to fewer ambiguous intersections that the model must resolve, leading to straighter trajectories at inference time.

Alec Helbling

65,484 Aufrufe • vor 4 Monaten

Build AI agents on a time-aware knowledge graph! Utopia is an open-source knowledge system that turns documents, databases, and connected sources into a temporal graph your agents can reason over. Most RAG systems are optimized for one question: what is relevant right now? That works until the underlying knowledge changes. A customer contract gets updated. A project owner changes. A policy is revised. A previous fact may no longer be true, but simply overwriting it means the system loses the history behind that change. Utopia handles this with a bitemporal knowledge graph. Each fact can track both when it was true in the real world and when the system learned about it. When something changes, the old fact is preserved instead of silently disappearing. That means an agent can reason about questions like: • What is true now? • What was true three months ago? • When did this information change? • What evidence was the conclusion based on? The graph is also ontology-aware, so documents are represented as entities, facts, and relationships instead of only chunks and embeddings. That gives the system more structure for reasoning across relationships, resolving entities, detecting conflicting facts, and deriving new information through explicit rules. Key capabilities: • Bitemporal knowledge graph for tracking how facts change over time • Provenance on facts so agents can trace where information came from • Conflict detection instead of silently overwriting contradictory information • Ontology-based reasoning across entities, relationships, and derived facts • Hybrid retrieval across full-text search, vector search, and graph traversal • MCP and agentic RAG support for exposing the knowledge layer directly to agents The interesting part is that this turns the knowledge base into more than a retrieval system. Instead of only finding relevant information, an agent can reason over what changed, what is still valid, how facts are connected, and where each conclusion came from. 100% open source. I've shared the GitHub repo in the comments!

Build AI agents on a time-aware knowledge graph! Utopia is an open-source knowledge system that turns documents, databases, and connected sources into a temporal graph your agents can reason over. Most RAG systems are optimized for one question: what is relevant right now? That works until the underlying knowledge changes. A customer contract gets updated. A project owner changes. A policy is revised. A previous fact may no longer be true, but simply overwriting it means the system loses the history behind that change. Utopia handles this with a bitemporal knowledge graph. Each fact can track both when it was true in the real world and when the system learned about it. When something changes, the old fact is preserved instead of silently disappearing. That means an agent can reason about questions like: • What is true now? • What was true three months ago? • When did this information change? • What evidence was the conclusion based on? The graph is also ontology-aware, so documents are represented as entities, facts, and relationships instead of only chunks and embeddings. That gives the system more structure for reasoning across relationships, resolving entities, detecting conflicting facts, and deriving new information through explicit rules. Key capabilities: • Bitemporal knowledge graph for tracking how facts change over time • Provenance on facts so agents can trace where information came from • Conflict detection instead of silently overwriting contradictory information • Ontology-based reasoning across entities, relationships, and derived facts • Hybrid retrieval across full-text search, vector search, and graph traversal • MCP and agentic RAG support for exposing the knowledge layer directly to agents The interesting part is that this turns the knowledge base into more than a retrieval system. Instead of only finding relevant information, an agent can reason over what changed, what is still valid, how facts are connected, and where each conclusion came from. 100% open source. I've shared the GitHub repo in the comments!

Sumanth

16,653 Aufrufe • vor 14 Tagen

You can get “deconstructed” drinks at Dutch Bros Dutch Bros had a deal for 4 drinks for $16 This American got them “Deconstructed” so you can drink them whenever This looks like $16 for a couple pumps of syrup at the bottom of a plastic cup Here’s how the deconstructed drink works - It’s for their Rebel energy - You order your Rebel “deconstructed.” - They hand you the unopened can of Rebel - They give you a cup with the flavor syrups When you’re ready you pour the syrup into the Rebel over ice so it stays fizzy Many people make posts like this pretending the drinks only come with the syrups so it causes outraged, but really you get the unopened cans of energy drinks too

You can get “deconstructed” drinks at Dutch Bros Dutch Bros had a deal for 4 drinks for $16 This American got them “Deconstructed” so you can drink them whenever This looks like $16 for a couple pumps of syrup at the bottom of a plastic cup Here’s how the deconstructed drink works - It’s for their Rebel energy - You order your Rebel “deconstructed.” - They hand you the unopened can of Rebel - They give you a cup with the flavor syrups When you’re ready you pour the syrup into the Rebel over ice so it stays fizzy Many people make posts like this pretending the drinks only come with the syrups so it causes outraged, but really you get the unopened cans of energy drinks too

Wall Street Apes

62,398 Aufrufe • vor 4 Monaten

I vibe coded a visual PDF search app with ColQwen2. This is how it works: - Store PDF files as images in a Weaviate AI Database vector database - Embed images and text with a multimodal late-interaction model (ColQwen2) - Generate token-wise (and summed) similarity maps to highlight image patches with high similarity Now I need to refactor the messy vibe-coded project. In the meantime, you can check out the Notebook this demo is based on to try it out yourself:

I vibe coded a visual PDF search app with ColQwen2. This is how it works: - Store PDF files as images in a Weaviate AI Database vector database - Embed images and text with a multimodal late-interaction model (ColQwen2) - Generate token-wise (and summed) similarity maps to highlight image patches with high similarity Now I need to refactor the messy vibe-coded project. In the meantime, you can check out the Notebook this demo is based on to try it out yourself:

Leonie

34,494 Aufrufe • vor 1 Jahr

You can now use GLM-5.3 Flash completely FREE 😱 GLM-5.3 is now officially out and free on No bank card needed. You can also use Qwen3.8, HY3, MiMo-V2.5 and other models for $0. Setup: 2 mins: > Go to > Create a free account > Pick any model showing 0 credits > Use it in chat or create an API key No official end date yet. Grab it before the free access disappears.

You can now use GLM-5.3 Flash completely FREE 😱 GLM-5.3 is now officially out and free on No bank card needed. You can also use Qwen3.8, HY3, MiMo-V2.5 and other models for $0. Setup: 2 mins: > Go to > Create a free account > Pick any model showing 0 credits > Use it in chat or create an API key No official end date yet. Grab it before the free access disappears.

CDG

13,405 Aufrufe • vor 25 Tagen

oh my.. this is over for developers Gemini 3 can create interactive 3D webpage in mins, just a few simple text prompts, it generates all the code you can control millions of particles with your hands and make them form any shape you want tutorial and prompts below:

oh my.. this is over for developers Gemini 3 can create interactive 3D webpage in mins, just a few simple text prompts, it generates all the code you can control millions of particles with your hands and make them form any shape you want tutorial and prompts below:

el.cine

617,324 Aufrufe • vor 9 Monaten

Voicenotes Dictation is now live on iOS. You can now use the Voicenotes keyboard to speak into any app with a text box - Messages, emails, notes, comments, basically anywhere you’d normally type. Just speak, and your words appear instantly. Update Voicenotes from the App Store to try it.

Voicenotes Dictation is now live on iOS. You can now use the Voicenotes keyboard to speak into any app with a text box - Messages, emails, notes, comments, basically anywhere you’d normally type. Just speak, and your words appear instantly. Update Voicenotes from the App Store to try it.

Voicenotes

33,982 Aufrufe • vor 2 Monaten

Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.

Today, we're shipping MLX support for TADA, our open-source text-to-speech model, which means the entire pipeline (LLM, flow-matching, and decoder) can now run locally on any Apple Silicon device. We're seeing a 45% reduction in memory usage and a 10x speed-up when using it quantized. With these improvements, you can use TADA on-device for OpenClaw or any personal chatbot. If you own a MacBook, Mac Mini, or Mac Studio, record a 10-second clip of any voice, type any text, and get high-quality, natural and expressive speech in real-time. Completely offline, completely free.

Hume AI

24,765 Aufrufe • vor 5 Monaten

Your store is slow and ugly because it’s bloated with useless apps. My store is fast because I only use the ready-to-use sections. The result? Higher conversion rates and a $0 monthly app bill. This isn’t magic; it’s just the power of AI. Comment "FAST" below, and I’ll show you how to apply it to your own store. (Must be following so I can DM you)

Your store is slow and ugly because it’s bloated with useless apps. My store is fast because I only use the ready-to-use sections. The result? Higher conversion rates and a $0 monthly app bill. This isn’t magic; it’s just the power of AI. Comment "FAST" below, and I’ll show you how to apply it to your own store. (Must be following so I can DM you)

SectionStore.io

12,072 Aufrufe • vor 8 Monaten