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。

Can LLMs extract knowledge graphs from unstructured text? Introducing GraphGPT! Pass in any text (summary of a movie, passage from Wikipedia, etc.) to generate a visualization of entities and their relationships. A quick example:

Varun Shenoy

7,162 subscribers

578,676 次观看 • 3 年前 •via X (Twitter)

科学技术艺术教育

Anya Rossi• Live Now

Private livecam show

10 条评论

Varun Shenoy 的头像

Varun Shenoy3 年前

Here's GraphGPT creating a knowledge graph from the synopsis of Veep:

Varun Shenoy 的头像

Varun Shenoy3 年前

In case you want to play with it yourself, here's the repo. All you need is an OpenAI API key.

Varun Shenoy 的头像

Varun Shenoy3 年前

GraphGPT is on the front page of HN 🎉

Varun Shenoy 的头像

Varun Shenoy3 年前

Play with GraphGPT without having to do any of the dev setup. All you need is an OpenAI API key! Thanks @sfzhu for the idea + PR 🚀

amir 的头像

amir3 年前

is that localhost?

Varun Shenoy 的头像

Varun Shenoy3 年前

🚢 🚢 🚢

Tom Bielecki 的头像

Tom Bielecki3 年前

What!! This is crazy useful. Great that you can append and edit with further Input. It probably wouldn't be hard to extend this to explore any domain/market with web search/summarization @codexeditor

Stratos Kontopoulos 的头像

Stratos Kontopoulos3 年前

Great stuff, especially for generating small & focused visualizations! But the output is simply a graph, not a #KnowledgeGraph, since it's missing #semantics & schema information. Also, it would be great if the output was available in a machine-processible format as well.

Joel Fernandes 的头像

Joel Fernandes3 年前

Nice project. How does one go about building a gpt-like training with custom data (without using openAI) ? For eg I have say a million spreadsheets of unstructured data and I want to chat with my data asking it to draw plots, graphs , asking questions to my data in English ..

verumlotus 的头像

verumlotus3 年前

man's shipping velocity crazy 🫡

相关视频

New package + paper drop 📄 - Introducing KGGen – a simple library to transform unstructured text into knowledge graphs. Text is abundant, but good knowledge graphs are scarce. Feed it raw text, and KGGen generates a structured network of entities and relationships. (1/7)

New package + paper drop 📄 - Introducing KGGen – a simple library to transform unstructured text into knowledge graphs. Text is abundant, but good knowledge graphs are scarce. Feed it raw text, and KGGen generates a structured network of entities and relationships. (1/7)

Belinda

11,097 次观看 • 1 年前

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

244,284 次观看 • 2 年前

🥁🥁 Introducing SlidesAI - Create Presentation Slides with AI In Seconds SlidesAI can summarise and create outlines from a large piece of text and generate a beautiful presentation. Here's a quick demo 👀

🥁🥁 Introducing SlidesAI - Create Presentation Slides with AI In Seconds SlidesAI can summarise and create outlines from a large piece of text and generate a beautiful presentation. Here's a quick demo 👀

Anurag Bhagsain

627,975 次观看 • 3 年前

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:

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

167,963 次观看 • 10 个月前

From text to reality: MIT researchers find new ways to use LLMs to help in design & manufacturing. These models can convert text prompts to CAD, generate manufacturing instructions, and search for optimal designs:

From text to reality: MIT researchers find new ways to use LLMs to help in design & manufacturing. These models can convert text prompts to CAD, generate manufacturing instructions, and search for optimal designs:

MIT CSAIL

59,152 次观看 • 3 年前

Introducing Text-to-Video on ChatGPT 🤯 I built a plugin that allows you to generate videos from just text! Built on Replit ⠕ and powered by Replicate 🔥

Introducing Text-to-Video on ChatGPT 🤯 I built a plugin that allows you to generate videos from just text! Built on Replit ⠕ and powered by Replicate 🔥

Zahid Khawaja

228,024 次观看 • 3 年前

Introducing a Text-to-API AI ⚙️ Turn any website into an API with 's /extract. Just describe your API in plain text and get an endpoint you can hit. Another great open-source project by !

Introducing a Text-to-API AI ⚙️ Turn any website into an API with 's /extract. Just describe your API in plain text and get an endpoint you can hit. Another great open-source project by !

Caleb Peffer (Hiring!)

262,812 次观看 • 1 年前

Introducing `YouTube Summary with ChatGPT` - a free Chrome extension developed by Glasp that uses OpenAI's #ChatGPT to generate text transcripts and summaries of any YouTube video! 🤯 See my demo below 👇 and install it here: 🔗

Introducing `YouTube Summary with ChatGPT` - a free Chrome extension developed by Glasp that uses OpenAI's #ChatGPT to generate text transcripts and summaries of any YouTube video! 🤯 See my demo below 👇 and install it here: 🔗

Charly Wargnier

743,855 次观看 • 3 年前

adobe just released a method that can generate transparent videos from text and images 👀

adobe just released a method that can generate transparent videos from text and images 👀

Dreaming Tulpa 🥓👑

77,051 次观看 • 1 年前

Quickly turn a GitHub repository into text for LLMs with Gitingest ⚡️ Replace "hub" with "ingest" in any GitHub URL for a text version of the codebase.

Quickly turn a GitHub repository into text for LLMs with Gitingest ⚡️ Replace "hub" with "ingest" in any GitHub URL for a text version of the codebase.

Addy Osmani

285,910 次观看 • 1 年前

Gemini 3.0 Pro is at great 3D design and front-end. It can generate complex 3D scenes and Three.js objects from text prompts. Here's a nice retro-future example from cris.

Gemini 3.0 Pro is at great 3D design and front-end. It can generate complex 3D scenes and Three.js objects from text prompts. Here's a nice retro-future example from cris.

Addy Osmani

90,189 次观看 • 7 个月前

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.

Google announces MusicLM: a model to generate music from text. Here are some crazy things it can do: 1. Given audio of a melody, it can generate new music inspired by that melody customized by prompts! Here's someone humming bella ciao turned into a cappella chorus, EDM, etc.

bleedingedge.ai

379,914 次观看 • 3 年前

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵

Speech-native models like Moshi sound great and answer fast, but aren’t as smart as text LLMs. In our new paper, MoshiRAG, we show how Moshi can ask for advice from a text LLM or a knowledge base. The tricky part is how to do this in real time without adding latency. 🧵

kyutai

52,598 次观看 • 2 个月前

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

Standard Intelligence's devansh responds to roon's tweet that "text is the universal interface," and explains why their new foundation model is trained on video: "At some point in the arbitrarily long future, if we only use text models, we could force most things to be text. But I think there are just a lot of things that are much more native when done from a computer-use [perspective]." "GUIs are designed for humans to use. We have this massive long tail of things on the internet that are entirely undoable by LLMs." "For example, when I do ML engineering most of my time is spent doing the grunt work of engineering. It's a lot of looking at graphs, analyzing, and comparing loss curves. You can do this in text, but it's a much larger pain than doing it in the native interface." "There's a reason humans don't interact with a computer purely through text, it would kind of suck."

TBPN

64,434 次观看 • 4 个月前

You can now generate smart personal podcasts from any of your PDFs, articles, eBooks, links or text in 32 languages with our ElevenReader iOS app.

You can now generate smart personal podcasts from any of your PDFs, articles, eBooks, links or text in 32 languages with our ElevenReader iOS app.

ElevenLabs

232,703 次观看 • 1 年前

Made a simple toy to morph any text with Fourier transforms. Just enter any from/to text in any language and see it morphs: Bonus: Can share link with friends to send the exact message morph to them

Made a simple toy to morph any text with Fourier transforms. Just enter any from/to text in any language and see it morphs: Bonus: Can share link with friends to send the exact message morph to them

Andrei Kashcha

39,706 次观看 • 3 个月前

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

🎥 Today we’re premiering Meta Movie Gen: the most advanced media foundation models to-date. Developed by AI research teams at Meta, Movie Gen delivers state-of-the-art results across a range of capabilities. We’re excited for the potential of this line of research to usher in entirely new possibilities for casual creators and creative professionals alike. More details and examples of what Movie Gen can do ➡️ 🛠️ Movie Gen models and capabilities Movie Gen Video: 30B parameter transformer model that can generate high-quality and high-definition images and videos from a single text prompt. Movie Gen Audio: A 13B parameter transformer model that can take a video input along with optional text prompts for controllability to generate high-fidelity audio synced to the video. It can generate ambient sound, instrumental background music and foley sound — delivering state-of-the-art results in audio quality, video-to-audio alignment and text-to-audio alignment. Precise video editing: Using a generated or existing video and accompanying text instructions as an input it can perform localized edits such as adding, removing or replacing elements — or global changes like background or style changes. Personalized videos: Using an image of a person and a text prompt, the model can generate a video with state-of-the-art results on character preservation and natural movement in video. We’re continuing to work closely with creative professionals from across the field to integrate their feedback as we work towards a potential release. We look forward to sharing more on this work and the creative possibilities it will enable in the future.

AI at Meta

2,264,864 次观看 • 1 年前

"Quick" Summary of LS bible text Ryze should naturally be ahead of Taliyah due to better access to plays, camps, turrets, therefore taliyah plays from behind Tali sivir comp on 2 items doesnt have as much dmg as tri muramana corki, and roa seraph ( tanky and damage, ryze ) etc etc

"Quick" Summary of LS bible text Ryze should naturally be ahead of Taliyah due to better access to plays, camps, turrets, therefore taliyah plays from behind Tali sivir comp on 2 items doesnt have as much dmg as tri muramana corki, and roa seraph ( tanky and damage, ryze ) etc etc

Veigarv2

171,029 次观看 • 9 个月前

[1/9] 🚀 We introduce 4Real-Video-V2, a method that can generate 4D scenes from a simple text prompt, viewable from any angle at any moment in time. It’s fast, photorealistic, and works on full scenes. Here's how it works and why it matters. 👇

[1/9] 🚀 We introduce 4Real-Video-V2, a method that can generate 4D scenes from a simple text prompt, viewable from any angle at any moment in time. It’s fast, photorealistic, and works on full scenes. Here's how it works and why it matters. 👇

Ashkan Mirzaei

10,036 次观看 • 1 年前