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.

Agentic Document Extraction just got much faster! From previous 135sec median processing time down to 8sec. Extracts not just text but diagrams, charts, and form fields from PDFs to give LLM-ready output. Please see the video for details and some application ideas.

Andrew Ng

1,758,043 subscribers

290,723 Aufrufe • vor 1 Jahr •via X (Twitter)

Wissenschaft & Technologie Bildung

Anya Rossi• Live Now

Private livecam show

11 Kommentare

Profilbild von ⟁ndrew V

⟁ndrew Vvor 1 Jahr

I challenge you to prove that this can accurately and precisely extract typed hierarchy JSON output from 25 PDFs and not miss a beat I don’t care if it takes an hour. And I don’t want to have to predefine the schema. It should iteratively learn, using any reasonable language model, NLP, NER processes and functions to develop the appropriate REGEX and Pydantic models to accomplish perfect fidelity of data extraction. Do you think this is possible?

Profilbild von Matt Figdore

Matt Figdorevor 2 Jahren

This is the biggest productivity cheat code right now. Kiss reading documents goodbye. You can get an instant summary of any document with this tool.

Profilbild von Awan Farz

Awan Farzvor 1 Jahr

I was building this with agentic document advance extraction, which is useful.

Profilbild von Vincent Valentine (CEO of UnOpen.ai)

Vincent Valentine (CEO of UnOpen.ai)vor 1 Jahr

incredible progress. this will definitely streamline the workflow.

Profilbild von Robert Rizk

Robert Rizkvor 1 Jahr

KEEP BUILDING!

Profilbild von Reverend Christian Moore

Reverend Christian Moorevor 1 Jahr

عشق منی اندرو جان دلم میخواد بوست کنم ❤️😘

Profilbild von Shine Gupta

Shine Guptavor 1 Jahr

That's an insane speed-up! From 135s to just 8s?🔥 Total game-changer for document pipelines. I was working on a similar project recently but used PaddleOCR for extraction.

Profilbild von Mohammed Lubbad, PhD

Mohammed Lubbad, PhDvor 1 Jahr

The reduction in processing time is impressive. Efficiency allows more room for innovation. How do we leverage this technology for broader applications? 🚀 #InnovationInsights

Profilbild von Tony Sousan

Tony Sousanvor 1 Jahr

@AndrewYNg, how does this breakthrough change your workflow? Speed is crucial, but what about accuracy? #InnovationPotential

Profilbild von ash prasad

ash prasadvor 1 Jahr

Amazing, will look to experiment and integrate.

Profilbild von Richy Hashmore

Richy Hashmorevor 1 Jahr

The improvement drastically cuts down on waiting time.

Ähnliche Videos

Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.

Announcing: Agentic Document Extraction! PDF files represent information visually - via layout, charts, graphs, etc. - and are more than just text. Unlike traditional OCR and most PDF-to-text approaches, which focus on extracting the text, an agentic approach lets us break a document down into components and reason about them, resulting in more accurate extraction of the underlying meaning for RAG and other applications. Watch the video for details.

Andrew Ng

689,441 Aufrufe • vor 1 Jahr

Announcing a significant upgrade to Agentic Document Extraction! LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a new SDK makes using it require only 3 simple lines of code. Please see the video for technical details. I hope this unlocks a lot of value from the "dark data" currently stuck in PDF files, and that you'll build something cool with this!

Announcing a significant upgrade to Agentic Document Extraction! LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a new SDK makes using it require only 3 simple lines of code. Please see the video for technical details. I hope this unlocks a lot of value from the "dark data" currently stuck in PDF files, and that you'll build something cool with this!

Andrew Ng

299,462 Aufrufe • vor 10 Monaten

Agentic Document Extraction now supports field extraction! Many doc extraction use cases extract specific fields from forms and other structured documents. You can now input a picture or PDF of an invoice, request the vendor name, item list, and prices, and get back the extracted fields. Or input a medical form and specify a schema to extract patient name, patient ID, insurance number, etc. One cool feature: If you don't feel like writing a schema (json specification of what fields to extract) yourself, upload one sample document and write a natural language prompt saying what you want, and we automatically generate a schema for you. See the video for details!

Agentic Document Extraction now supports field extraction! Many doc extraction use cases extract specific fields from forms and other structured documents. You can now input a picture or PDF of an invoice, request the vendor name, item list, and prices, and get back the extracted fields. Or input a medical form and specify a schema to extract patient name, patient ID, insurance number, etc. One cool feature: If you don't feel like writing a schema (json specification of what fields to extract) yourself, upload one sample document and write a natural language prompt saying what you want, and we automatically generate a schema for you. See the video for details!

Andrew Ng

193,053 Aufrufe • vor 1 Jahr

New course: Document AI: From OCR to Agentic Doc Extraction, built with LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp. Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic workflows that process documents accurately: breaking them into parts, examining each piece carefully, and extracting information through multiple iterations. Traditional Optical Character Recognition (OCR) captures text but loses context from table headers, chart captions, or reading order of columns. After exploring OCR's limitations, you’ll use LandingAI's Agentic Document Extraction (ADE) framework to process documents. ADE treats pages as visually -- as images -- to parse information and extract fields. Skills you'll gain: - Build agents to convert unstructured files into structured Markdown/HTML and JSON - Use ADE to parse complex data like forms, handwriting, or equations - Map extracted information to named fields using a specified schema, with bounding boxes for grounding and validation - Deploy RAG applications with event-driven document processing Come learn about the best tools for processing documents like financial invoices, medical records, or academic papers intelligently:

New course: Document AI: From OCR to Agentic Doc Extraction, built with LandingAI, where I'm executive chairman, and taught by David Park and Andrea Kropp. Much of the world's data is locked in PDFs, JPEGs, and other documents. This short course shows you how to build agentic workflows that process documents accurately: breaking them into parts, examining each piece carefully, and extracting information through multiple iterations. Traditional Optical Character Recognition (OCR) captures text but loses context from table headers, chart captions, or reading order of columns. After exploring OCR's limitations, you’ll use LandingAI's Agentic Document Extraction (ADE) framework to process documents. ADE treats pages as visually -- as images -- to parse information and extract fields. Skills you'll gain: - Build agents to convert unstructured files into structured Markdown/HTML and JSON - Use ADE to parse complex data like forms, handwriting, or equations - Map extracted information to named fields using a specified schema, with bounding boxes for grounding and validation - Deploy RAG applications with event-driven document processing Come learn about the best tools for processing documents like financial invoices, medical records, or academic papers intelligently:

Andrew Ng

200,575 Aufrufe • vor 7 Monaten

PDFs suck. We just raised $17,000,000 in funding to fix this problem once and for all. Extend is building the modern document processing cloud. See how Brex, Square, Checkr, and Fortune 500s use it to process millions of documents:

PDFs suck. We just raised $17,000,000 in funding to fix this problem once and for all. Extend is building the modern document processing cloud. See how Brex, Square, Checkr, and Fortune 500s use it to process millions of documents:

Kushal Byatnal

210,985 Aufrufe • vor 1 Jahr

Agent Fill (our agentic PDF filler) just got smarter: - Hover to see exactly why each field was filled - Review and complete missing fields directly in the editor We've been working with finance and ops teams to save hours every week - thank you all for the feedback. Try it out today and automate PDFs.

Agent Fill (our agentic PDF filler) just got smarter: - Hover to see exactly why each field was filled - Review and complete missing fields directly in the editor We've been working with finance and ops teams to save hours every week - thank you all for the feedback. Try it out today and automate PDFs.

Ramp Labs

13,513 Aufrufe • vor 11 Monaten

PLEASE give me some direction… …but more importantly some time to recover after watching Caroline Bowman perform “They Just Keep Moving The Line” from #SmashBway.

PLEASE give me some direction… …but more importantly some time to recover after watching Caroline Bowman perform “They Just Keep Moving The Line” from #SmashBway.

SmashBway

11,960 Aufrufe • vor 1 Jahr

I just built a Voice AI Agent for insurance claims using Gemini 3.1 Flash Live and Google ADK. Talk to it. It fills the intake form, extracts claim details, and routes to an adjuster in real-time. 100% Opensource.

I just built a Voice AI Agent for insurance claims using Gemini 3.1 Flash Live and Google ADK. Talk to it. It fills the intake form, extracts claim details, and routes to an adjuster in real-time. 100% Opensource.

Shubham Saboo

73,073 Aufrufe • vor 3 Monaten

Got questions about NELFUND student loans? You’re not alone From application status to disbursement details, we’ve sorted out some of the most frequently asked questions from students just like you Still need help? Visit or check your student dashboard for updates #NELFUNDStudentLoan

Got questions about NELFUND student loans? You’re not alone From application status to disbursement details, we’ve sorted out some of the most frequently asked questions from students just like you Still need help? Visit or check your student dashboard for updates #NELFUNDStudentLoan

NELFUND

13,004 Aufrufe • vor 1 Jahr

Our Compute Agent (Operator) Got Much Faster!! It's about 3- 4x faster. In this example, it finds the cheapest flights from London to NYC and emails you the details. In all fairness, we are still 2x slower than OpenAI. We will continue to make it faster and more agentic. The next update will be later this week.

Our Compute Agent (Operator) Got Much Faster!! It's about 3- 4x faster. In this example, it finds the cheapest flights from London to NYC and emails you the details. In all fairness, we are still 2x slower than OpenAI. We will continue to make it faster and more agentic. The next update will be later this week.

Bindu Reddy

20,716 Aufrufe • vor 1 Jahr

Get ready for lots of silly Subverse clips from the latest stream~ I wanted to give some thanks and gratitude in light of Christmas time but the kloi were not having it!

Get ready for lots of silly Subverse clips from the latest stream~ I wanted to give some thanks and gratitude in light of Christmas time but the kloi were not having it!

SingingSamine🎵

77,271 Aufrufe • vor 1 Jahr

please give him more screen time… the screen time of him we got in these two episodes was this much, and it’s just not enough for us 😭😭 #StudyGroup

please give him more screen time… the screen time of him we got in these two episodes was this much, and it’s just not enough for us 😭😭 #StudyGroup

kdrama diary

26,085 Aufrufe • vor 1 Jahr

The median home-buyer just hit 59 years old. Up from 39. Meanwhile, first time homebuyers just hit 40 — a little late to be starting a family. Home prices were supposed to come down after rate hikes and Bidenflation. They did not.

The median home-buyer just hit 59 years old. Up from 39. Meanwhile, first time homebuyers just hit 40 — a little late to be starting a family. Home prices were supposed to come down after rate hikes and Bidenflation. They did not.

Peter St Onge, Ph.D.

227,035 Aufrufe • vor 8 Monaten

Open-weight MiniMax M3 filled out a US customs form from a driver's license photo For this test we deployed MiniMax M3 Q4 using MLX-VLM on a Mac Studio M3 Ultra 512GB RAM. The model was tasked with reading a scanned document and an ID card photo, then completing a declaration form Output: 736 tokens · Input: 1,847 tokens · Time: ~31s The model analyzed both inputs, streamed its reasoning, and then called three tools: write_field for text fields, mark for Yes/No checkboxes, and sign for the signature and date. It extracted the required information, mapped it to the correct fields and completed the form without any manual input

Open-weight MiniMax M3 filled out a US customs form from a driver's license photo For this test we deployed MiniMax M3 Q4 using MLX-VLM on a Mac Studio M3 Ultra 512GB RAM. The model was tasked with reading a scanned document and an ID card photo, then completing a declaration form Output: 736 tokens · Input: 1,847 tokens · Time: ~31s The model analyzed both inputs, streamed its reasoning, and then called three tools: write_field for text fields, mark for Yes/No checkboxes, and sign for the signature and date. It extracted the required information, mapped it to the correct fields and completed the form without any manual input

atomic.chat

109,369 Aufrufe • vor 1 Monat

Typing is great, but speaking is faster. Bring Gemini directly into your desktop workflow to seamlessly reformat text between apps using just your voice. Watch it pull raw details from a plain document and transform them into a festive, emoji-filled email invite exactly where you need it.

Typing is great, but speaking is faster. Bring Gemini directly into your desktop workflow to seamlessly reformat text between apps using just your voice. Watch it pull raw details from a plain document and transform them into a festive, emoji-filled email invite exactly where you need it.

Google Gemini

179,801 Aufrufe • vor 2 Monaten

OpenAI just dropped GPT-4.1. It’s a huge jump over GPT-4o on basically every metric, and importantly document processing and data extraction from enterprise content. Box is now offering it in beta in the Box AI Studio, and will be rolling out to everyone shortly.

OpenAI just dropped GPT-4.1. It’s a huge jump over GPT-4o on basically every metric, and importantly document processing and data extraction from enterprise content. Box is now offering it in beta in the Box AI Studio, and will be rolling out to everyone shortly.

Aaron Levie

108,961 Aufrufe • vor 1 Jahr

Most organizations run on unstructured content, but it’s the data locked within that content moves business forward. Box Extract is now generally available, delivering agentic data extraction at scale for smart process automation. Combining the latest AI models with advanced OCR capabilities, and agentic approaches that understand document structure and meaning, Box Extract automatically and accurately extracts high quality data from a variety of content to automate workflows, speed content discovery, and drive smarter business decisions.

Most organizations run on unstructured content, but it’s the data locked within that content moves business forward. Box Extract is now generally available, delivering agentic data extraction at scale for smart process automation. Combining the latest AI models with advanced OCR capabilities, and agentic approaches that understand document structure and meaning, Box Extract automatically and accurately extracts high quality data from a variety of content to automate workflows, speed content discovery, and drive smarter business decisions.

Box

759,033 Aufrufe • vor 6 Monaten

LlamaParse now has an official Agent Skill you can use across 40+ agents. With built-in instructions for parsing complex documents, including different formats, tables, charts, and images, your agents gain access to deeper document understanding, not just raw text extraction. 👇 Watch the demo 📖 Read the docs: 🚀 Get started with LlamaCloud:

LlamaParse now has an official Agent Skill you can use across 40+ agents. With built-in instructions for parsing complex documents, including different formats, tables, charts, and images, your agents gain access to deeper document understanding, not just raw text extraction. 👇 Watch the demo 📖 Read the docs: 🚀 Get started with LlamaCloud:

LlamaIndex 🦙

51,845 Aufrufe • vor 4 Monaten

I wanted storytelling — not just output. So I tried Pai by Utopai — the first long-form video generation model built for narrative continuity. I created an original animated short where the story actually flows from scene to scene. See it here: #UtopaiPartners

I wanted storytelling — not just output. So I tried Pai by Utopai — the first long-form video generation model built for narrative continuity. I created an original animated short where the story actually flows from scene to scene. See it here: #UtopaiPartners

Erina | AI Tools & News

11,511 Aufrufe • vor 5 Monaten

Claude Sonnet 4.6 just released, and it's incredible It's just as good as Opus for most agentic tasks, but faster and a fifth of the price In this video I show you all the key differences, how to hook this up to OpenClaw, and give you 2 mind blowing use cases you can use NOW:

Claude Sonnet 4.6 just released, and it's incredible It's just as good as Opus for most agentic tasks, but faster and a fifth of the price In this video I show you all the key differences, how to hook this up to OpenClaw, and give you 2 mind blowing use cases you can use NOW:

Alex Finn

101,167 Aufrufe • vor 5 Monaten