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.

Today we’re introducing Extract v2.5 - a series of frontier agents tuned for document extraction. The agents (cost-effective, agentic, agentic plus) are tuned for value accuracy and grounding. Our extraction agents outperform Opus 5.5 and GPT-6 Sol while being 30%-4x cheaper. We’ve made massive improvements on complex extraction over... * long lists (86.1% -> 95.5% on our agentic tier) * records spanning pages (85.5% -> 96.5%) * scanned forms (90.9% -> 95.7%) We’ve also launched the following features: ✅ Advanced citations: we locate bounding boxes for all supporting values for an inferred field, even if there's not an exact match. ✅ Structural Reasoning: we tailor document extraction algorithms depending on the type, layout, and information Our extraction agents are SOTA in price-performance on ExtractBench, across a wide range of cost points. We are the best tool for document extraction across documents of any complexity. Blog: All of these are available on LlamaParse: . Come check it out!show more

Jerry Liu

85,146 subscribers

50,581 Aufrufe • vor 6 Tagen •via X (Twitter)

Nachrichten & Politik Bildung Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

30 Kommentare

Profilbild von Logan Markewich

Logan Markewichvor 6 Tagen

Extract v2.5 was a huge effort from the team (entire engines got rebuilt!), proud of this launch 💪

Profilbild von George Maloney

George Maloneyvor 6 Tagen

Would love to collab on something with GLiNER!

Profilbild von Arpan

Arpanvor 6 Tagen

@jerryjliu0 I'm building an open benchmark for tax document classification: W-2, 1099 or broker statement, and whose? It's the step before extraction. Would love to run Extract v2.5 on it with @llama_index. cc @disiok @murtazakhomusi @imaanxsultan @LoganMarkewich @tissemlk

Profilbild von Sophia Yang

Sophia Yangvor 6 Tagen

Congrats 🎉

Profilbild von Jordan Hochenbaum

Jordan Hochenbaumvor 6 Tagen

Awesome release!

Profilbild von Nikhil g

Nikhil gvor 6 Tagen

@jerryjliu0 the final boss for document’s data

Profilbild von Murtaza Khomusi

Murtaza Khomusivor 6 Tagen

Always pushing the frontier!

Profilbild von Johneo

Johneovor 6 Tagen

@llama_index Your pricing model is horrible tho.. let me pay per use. Options for either $50/mo and under using or manual reload only is horrible.

Profilbild von Jerry Liu

Jerry Liuvor 6 Tagen

@llama_index completely understand the concerns. we're massively simplifying our pricing in the next ~2-3 weeks to make it easier to do pay as you go, with the option to do larger commits with volume discounts + SLAs please stay tuned!

Profilbild von Imaan Sultan 🇵🇰🇸🇦

Imaan Sultan 🇵🇰🇸🇦vor 6 Tagen

always on top lfggggg

Profilbild von Kevihaiceth 💹🧲

Kevihaiceth 💹🧲vor 6 Tagen

Advanced citations feature sounds very useful

Profilbild von Hershal Rao

Hershal Raovor 6 Tagen

rip to my custom parsing scripts that took 3 weeks to build

Profilbild von Simon Villanueva

Simon Villanuevavor 6 Tagen

Really strong release. Complex extraction is the part that's hard to move, and this moves it.

Profilbild von Jatin Garg

Jatin Gargvor 6 Tagen

the 'cost-effective' claim only holds if accuracy stays above the threshold humans would accept. how did recall numbers move as you tuned for speed?

Profilbild von Hashir Omer Farooqi

Hashir Omer Farooqivor 6 Tagen

Does it improve latency as well?

Profilbild von VisiveAI

VisiveAIvor 6 Tagen

Extract v2.5 — frontier doc agents tuned for grounding, not just cheaper tokens. Accuracy is the product. #RAG #Agents

Profilbild von Crypto Blade

Crypto Bladevor 6 Tagen

yo those list accuracy jumps are huge

Profilbild von Aapakari

Aapakarivor 6 Tagen

Were the Opus 5.5 and GPT-6 Sol comparisons run on ExtractBench too?

Profilbild von Boardy

Boardyvor 6 Tagen

@andrewdsouza take a look: LlamaIndex’s Extract v2.5 helps teams with complex document extraction. I can help them reach the buyers who need it.

Profilbild von Mo's fav goat

Mo's fav goatvor 6 Tagen

AI data extraction tool that is 30%-4x cheaper than the competition to check out later.

Profilbild von John Rood

John Roodvor 6 Tagen

citations solve trust on the first read. the failure that compounds is the re-issued document: nothing re-extracts, and downstream keeps serving values from the old revision. record which revision each extracted value came from, or the staleness stays invisible.

Profilbild von Pingali Abhijith

Pingali Abhijithvor 6 Tagen

cheaper and ahead of Opus 5.5 and Sol on extraction. the page-spanning records number is the one I'd look at first

Profilbild von Marius Laurusevicius

Marius Lauruseviciusvor 6 Tagen

Cheaper and more accurate at the same time is rare. Is the test set you used public?

Profilbild von Shivam

Shivamvor 6 Tagen

@grok compare this against r-1 from @reductoai

Profilbild von Kizuno18

Kizuno18vor 6 Tagen

grounded extraction with citations is essential for pipelines: flat text parsers hallucinate numbers and break downstream charts. in our pipeline targeting brazil, extracting macro reports into verified tabular schemas keeps our $0 visual renders 100% accurate. huge unlock

Profilbild von Athena Prime

Athena Primevor 6 Tagen

Tools amplify; they don't choose. Your line makes that obvious.

Profilbild von Aleksandar Janca

Aleksandar Jancavor 6 Tagen

the bounding box citations are what get an extraction signed off, nobody trusts a value they cant trace back to the page

Profilbild von Sam Presvelos

Sam Presvelosvor 6 Tagen

Reached out for a demo.

Profilbild von ninja 🥷

ninja 🥷vor 6 Tagen

What is the score on OlmOCR benchmark

Profilbild von Mathias Heinke

Mathias Heinkevor 6 Tagen

ExtractBench is tagged English only. Has anyone run v2.5 on German scans?

Ähnliche Videos

We tuned an AI agent that can do large-scale document extraction from long docs (50+ pages, some with 10k-100k fields) with 94%+ accuracy 📈 It uses a harness + model set that is tuned specifically for reasoning over extracting out complex information from complex docs. Each extracted field comes with a confidence score as well as a bounding box denoting where it came from. It does 10-20% better in accuracy than generalized coding agent harnesses (e.g. Claude Code Opus 4.8 and Codex GPT-5.6). Check out the video below for a demo. The mode is called LlamaExtract Agentic Plus. Learn more about our extraction benchmark and agentic plus mode here: If you have very complex document extraction needs, come check out LlamaParse!

We tuned an AI agent that can do large-scale document extraction from long docs (50+ pages, some with 10k-100k fields) with 94%+ accuracy 📈 It uses a harness + model set that is tuned specifically for reasoning over extracting out complex information from complex docs. Each extracted field comes with a confidence score as well as a bounding box denoting where it came from. It does 10-20% better in accuracy than generalized coding agent harnesses (e.g. Claude Code Opus 4.8 and Codex GPT-5.6). Check out the video below for a demo. The mode is called LlamaExtract Agentic Plus. Learn more about our extraction benchmark and agentic plus mode here: If you have very complex document extraction needs, come check out LlamaParse!

Jerry Liu

18,359 Aufrufe • vor 1 Monat

Introducing ExtractBench, the most comprehensive benchmark for information extraction from complex enterprise documents. The latest models are pushing the frontier of coding and knowledge work, but surprisingly they still struggle on complex doc extraction tasks in production. A well-tuned extractor must parse multi-page filings without dropping rows, emit exact spatial citations for auditability, and handle messy scans. Also they must do all of this at a viable per-page cost so that you can scale this to millions of docs in production (you can’t be paying upwards of $1 in tokens per page!) Existing extraction benchmarks fall short: they are not large/diverse enough in document domain (finance, energy, gov, auto), elements (long records, scans, grounding), and schemas. So our applied research team built ExtractBench. We evaluated 14 systems: frontier VLMs, coding agents, and specialized extraction APIs, against 370 enterprise documents: 4,869 pages, 67 document types. Our biggest finding 🧪: Short documents mask critical system flaws. On files past 50 pages, commercial VLMs collapse below 35% recall due to silent list truncation. They hold high precision, but lose output attention and drop most of the table rows. ExtractBench evaluates value accuracy, long-record completeness, spatial grounding, and per-page cost with zero LLM judges. It is 100% deterministic and reproducible. In tandem with ExtractBench, we’re also introducing 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗣𝗹𝘂𝘀, a new Extract tier in LlamaParse that debuts at #1 on the leaderboard: 95.6% value accuracy, at less than a third the cost of the closest peer. Explore the findings, download the dataset, or run the harness: Blog: GitHub: HuggingFace: We will be actively evolving both our extraction benchmark as well as our extraction harness over time. If you check out either ExtractBench or LlamaParse, let us know your feedback!

Introducing ExtractBench, the most comprehensive benchmark for information extraction from complex enterprise documents. The latest models are pushing the frontier of coding and knowledge work, but surprisingly they still struggle on complex doc extraction tasks in production. A well-tuned extractor must parse multi-page filings without dropping rows, emit exact spatial citations for auditability, and handle messy scans. Also they must do all of this at a viable per-page cost so that you can scale this to millions of docs in production (you can’t be paying upwards of $1 in tokens per page!) Existing extraction benchmarks fall short: they are not large/diverse enough in document domain (finance, energy, gov, auto), elements (long records, scans, grounding), and schemas. So our applied research team built ExtractBench. We evaluated 14 systems: frontier VLMs, coding agents, and specialized extraction APIs, against 370 enterprise documents: 4,869 pages, 67 document types. Our biggest finding 🧪: Short documents mask critical system flaws. On files past 50 pages, commercial VLMs collapse below 35% recall due to silent list truncation. They hold high precision, but lose output attention and drop most of the table rows. ExtractBench evaluates value accuracy, long-record completeness, spatial grounding, and per-page cost with zero LLM judges. It is 100% deterministic and reproducible. In tandem with ExtractBench, we’re also introducing 𝗔𝗴𝗲𝗻𝘁𝗶𝗰 𝗣𝗹𝘂𝘀, a new Extract tier in LlamaParse that debuts at #1 on the leaderboard: 95.6% value accuracy, at less than a third the cost of the closest peer. Explore the findings, download the dataset, or run the harness: Blog: GitHub: HuggingFace: We will be actively evolving both our extraction benchmark as well as our extraction harness over time. If you check out either ExtractBench or LlamaParse, let us know your feedback!

Jerry Liu

75,697 Aufrufe • vor 1 Monat

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, showing the exact word, line, or region that the answer came from. Frontier vision models do a terrible job at this. They have a hard time predicting exact bounding boxes over region, tying it back to the source answer, and surfacing it as context in a cost-effective and accurate manner. Dedicated VLM-based document OCR/extraction tools like LlamaParse are a lot better at visual grounding and specifically tying it to extracted outputs. One of our main evaluation areas in ExtractBench, our recently released real-world benchmark, is to evaluate the visual grounding capabilities of document extraction. ExtractBench: If you want to give LlamaParse a shot, come check it out:

If you’re building an “agent over your PDFs” in 2026, one of the most underrated things you can do is to provide exact grounding back to the source document for any agentic answers. Specifically, showing the exact word, line, or region that the answer came from. Frontier vision models do a terrible job at this. They have a hard time predicting exact bounding boxes over region, tying it back to the source answer, and surfacing it as context in a cost-effective and accurate manner. Dedicated VLM-based document OCR/extraction tools like LlamaParse are a lot better at visual grounding and specifically tying it to extracted outputs. One of our main evaluation areas in ExtractBench, our recently released real-world benchmark, is to evaluate the visual grounding capabilities of document extraction. ExtractBench: If you want to give LlamaParse a shot, come check it out:

Jerry Liu

14,515 Aufrufe • vor 1 Monat

Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaParse connector to ChatGPT that gives the model access to high-quality document OCR and extraction at the pareto frontier of accuracy and cost. It contains native access to our parse and extract endpoints. Upload your most complex documents, and you can do the following: * digitalize it into extremely accurate context for any QA task * perform large-scale extraction from a set of documents with accurate grounding and citations Offload the higher-level reasoning to Astra, leave specialized doc parsing and extraction to us. ChatGPT plugin: Come sign up here:

Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documents, you will break the bank (10c+ per page on parsing and extraction!) We've added a native LlamaParse connector to ChatGPT that gives the model access to high-quality document OCR and extraction at the pareto frontier of accuracy and cost. It contains native access to our parse and extract endpoints. Upload your most complex documents, and you can do the following: * digitalize it into extremely accurate context for any QA task * perform large-scale extraction from a set of documents with accurate grounding and citations Offload the higher-level reasoning to Astra, leave specialized doc parsing and extraction to us. ChatGPT plugin: Come sign up here:

Jerry Liu

11,083 Aufrufe • vor 28 Tagen

$We got extremely good at extracting a scanned from layer by layer 📋 - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotated permit, our Extract agents can extract out both the original permit number but also any drawn/handwritten annotations on top. they're also grounded exactly in the source text. our agents reduce error rates by 2x+, at a small fraction of the price compared to using a frontier model. Our Extract v2.5 agents are SOTA in price/performance, and scanned forms are just one example. Come check it out! Extract v2.5: Available in LlamaParse:$

We got extremely good at extracting a scanned from layer by layer 📋 - from printed fields, overlaid text, handwriting, and reviewer annotations. For instance, on an annotated permit, our Extract agents can extract out both the original permit number but also any drawn/handwritten annotations on top. they're also grounded exactly in the source text. our agents reduce error rates by 2x+, at a small fraction of the price compared to using a frontier model. Our Extract v2.5 agents are SOTA in price/performance, and scanned forms are just one example. Come check it out! Extract v2.5: Available in LlamaParse:

Jerry Liu

11,136 Aufrufe • vor 3 Tagen

Introducing Document Extraction as an MCP Server ✂️📑 A huge use case for AI agents is being able to extract out items from a diverse set of complex documents in a repeatable manner - whether it’s legal contracts, invoices, financial statements, passports, and more. In this case, 🚫 prompting ChatGPT/Claude is too error-prone/not systematic. 💡We’ve created a plug-and-play MCP server around our core document extraction capabilities within LlamaCloud. 1. Build an extraction agent in LlamaCloud with a standardized schema. 2. Plug it as an MCP tool within ChatGPT/Claude. 3. For your next extraction job, get the outputs in a standardized format through the tool! Huge shoutout to Tuana and Logan Markewich for working on this - this is thanks to the latest updates to our llamacloud-mcp demo repo, which supports both extraction and retrieval as MCP tools. Repo: Sign up:

Introducing Document Extraction as an MCP Server ✂️📑 A huge use case for AI agents is being able to extract out items from a diverse set of complex documents in a repeatable manner - whether it’s legal contracts, invoices, financial statements, passports, and more. In this case, 🚫 prompting ChatGPT/Claude is too error-prone/not systematic. 💡We’ve created a plug-and-play MCP server around our core document extraction capabilities within LlamaCloud. 1. Build an extraction agent in LlamaCloud with a standardized schema. 2. Plug it as an MCP tool within ChatGPT/Claude. 3. For your next extraction job, get the outputs in a standardized format through the tool! Huge shoutout to Tuana and Logan Markewich for working on this - this is thanks to the latest updates to our llamacloud-mcp demo repo, which supports both extraction and retrieval as MCP tools. Repo: Sign up:

Jerry Liu

57,827 Aufrufe • vor 1 Jahr

Today, we’re excited to announce Deep Extract. We’re pushing the boundary of complex document extraction by utilizing an agent harness approach, iterating and verifying outputs until they are at human-level accuracy. The results speak for themselves: we’ve handled documents exceeding 2,500 pages, extracting a total of 30M+ fields in the last couple weeks with results in our production beta reaching 99-100% accuracy. It’s particularly effective on complex documents with long lists, such as invoice line items, brokerage statement transactions, equipment manifests, and more. See more on how we built it, how to use it, and more👇

Today, we’re excited to announce Deep Extract. We’re pushing the boundary of complex document extraction by utilizing an agent harness approach, iterating and verifying outputs until they are at human-level accuracy. The results speak for themselves: we’ve handled documents exceeding 2,500 pages, extracting a total of 30M+ fields in the last couple weeks with results in our production beta reaching 99-100% accuracy. It’s particularly effective on complex documents with long lists, such as invoice line items, brokerage statement transactions, equipment manifests, and more. See more on how we built it, how to use it, and more👇

Reducto

23,949,618 Aufrufe • vor 6 Monaten

We’re excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts 📊📈 than virtually every other parser, it is now steerable through natural language instructions - output the document in whatever format you desire! It is also the only parsing solution that seamlessly allows you to build accurate RAG over complex documents, free of hallucinations 🔥 We launched it in private preview a few weeks ago and hit 2k users, 1M total PDF pages parsed. And now it’s better than ever. LlamaParse contains the following killer features: ✅ SOTA table/chart extraction ✅ Seamless integration with LlamaIndex 🦙 advanced RAG/agents ✅✨ Natural language Parsing Instructions ✅✨JSON mode and image extraction ✅✨Support for ~10 document types (.pdf, .pptx, .docx, .xml) and more Our pricing is simple: 1k free per day, and additional pages at 0.3c a page, or $3 for 1k pages. If you want advanced document RAG and/or private deployments, come get in touch with us to chat about LlamaCloud. Check out our full blog post here: LlamaParse client repo: Signup at 🦙☁️: Come talk to us:

We’re excited to officially launch LlamaParse, the first genAI-native document parsing solution. Not only is it better at parsing out images/tables/charts 📊📈 than virtually every other parser, it is now steerable through natural language instructions - output the document in whatever format you desire! It is also the only parsing solution that seamlessly allows you to build accurate RAG over complex documents, free of hallucinations 🔥 We launched it in private preview a few weeks ago and hit 2k users, 1M total PDF pages parsed. And now it’s better than ever. LlamaParse contains the following killer features: ✅ SOTA table/chart extraction ✅ Seamless integration with LlamaIndex 🦙 advanced RAG/agents ✅✨ Natural language Parsing Instructions ✅✨JSON mode and image extraction ✅✨Support for ~10 document types (.pdf, .pptx, .docx, .xml) and more Our pricing is simple: 1k free per day, and additional pages at 0.3c a page, or $3 for 1k pages. If you want advanced document RAG and/or private deployments, come get in touch with us to chat about LlamaCloud. Check out our full blog post here: LlamaParse client repo: Signup at 🦙☁️: Come talk to us:

LlamaIndex 🦙

143,198 Aufrufe • vor 2 Jahren

We built an AI agent that lets you vibe-code document extraction - high accuracy and citations over the most complex documents. Our latest release lets you upload documents as context. All you then have to do is describe what you want extracted in natural language. 💡 Our agent will then read the document with file tools to infer the right schema, validation rules, and other pre/postprocessing logic. ✅ It will give you back a workflow that can extract over thousands/millions of documents at scale. You can still of course review and edit every output before approving. Stop handling paperwork manually; just upload files, describe your task, and let our agent handle the rest. Our vision for LlamaAgents is to provide the most advanced and easy-to-use way for you to orchestrate document work. Walkthrough: Check it out: If you’re interested in reducing the operational burden of document extraction (invoices, claims, onboarding forms), come talk to us!

We built an AI agent that lets you vibe-code document extraction - high accuracy and citations over the most complex documents. Our latest release lets you upload documents as context. All you then have to do is describe what you want extracted in natural language. 💡 Our agent will then read the document with file tools to infer the right schema, validation rules, and other pre/postprocessing logic. ✅ It will give you back a workflow that can extract over thousands/millions of documents at scale. You can still of course review and edit every output before approving. Stop handling paperwork manually; just upload files, describe your task, and let our agent handle the rest. Our vision for LlamaAgents is to provide the most advanced and easy-to-use way for you to orchestrate document work. Walkthrough: Check it out: If you’re interested in reducing the operational burden of document extraction (invoices, claims, onboarding forms), come talk to us!

Jerry Liu

20,857 Aufrufe • vor 7 Monaten

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark that measures parsing quality specifically for agent knowledge work: ✅ It optimizes for semantic correctness (instead of exact similarity) ✅ It has the most comprehensive distribution of real-world enterprise documents It contains ~2,000 human-verified enterprise document pages with 167,000+ test rules across five dimensions that matter most: tables, charts, content faithfulness, semantic formatting, and visual grounding. We benchmarked 14 known document parsers on ParseBench, from frontier/OSS VLMs to specialized parsers to LlamaParse. Here are some of our findings: 💡 Increasing compute budget yields diminishing returns - Gemini/gpt-5-mini/haiku gain 3-5 points from minimal to high thinking, at 4x the cost. 💡 Charts are the most polarizing dimension for evaluation. Most specialized parsers score below 6%, while some VLM-based parsers do a bit better. 💡 VLMs are great at visual understanding but terrible at layout extraction. GPT-5-mini/haiku score below 10% on our visual grounding task, all specialized parsers do much better. 💡 No method crushes all 5 dimensions at once, but LlamaParse achieves the highest overall score at 84.9%, and is the leader in 4 out of the 5 dimensions. This is by far the deepest technical work that we’ve published as a company. I would encourage you to start with our blog and explore our links to Hugging Face to GitHub. All the details are in our full 35-page (!!) ArXiv whitepaper. 🌐: Blog: 📄 Paper: 💻 Code: 📊 Dataset: 🎥 YouTube:

We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. ParseBench is a benchmark that measures parsing quality specifically for agent knowledge work: ✅ It optimizes for semantic correctness (instead of exact similarity) ✅ It has the most comprehensive distribution of real-world enterprise documents It contains ~2,000 human-verified enterprise document pages with 167,000+ test rules across five dimensions that matter most: tables, charts, content faithfulness, semantic formatting, and visual grounding. We benchmarked 14 known document parsers on ParseBench, from frontier/OSS VLMs to specialized parsers to LlamaParse. Here are some of our findings: 💡 Increasing compute budget yields diminishing returns - Gemini/gpt-5-mini/haiku gain 3-5 points from minimal to high thinking, at 4x the cost. 💡 Charts are the most polarizing dimension for evaluation. Most specialized parsers score below 6%, while some VLM-based parsers do a bit better. 💡 VLMs are great at visual understanding but terrible at layout extraction. GPT-5-mini/haiku score below 10% on our visual grounding task, all specialized parsers do much better. 💡 No method crushes all 5 dimensions at once, but LlamaParse achieves the highest overall score at 84.9%, and is the leader in 4 out of the 5 dimensions. This is by far the deepest technical work that we’ve published as a company. I would encourage you to start with our blog and explore our links to Hugging Face to GitHub. All the details are in our full 35-page (!!) ArXiv whitepaper. 🌐: Blog: 📄 Paper: 💻 Code: 📊 Dataset: 🎥 YouTube:

Jerry Liu

108,093 Aufrufe • vor 5 Monaten

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

200,844 Aufrufe • vor 8 Monaten

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.

Over 1 billion PDFs are created every day, but your agents still can’t read them reliably. Today we’re releasing Parse 2.0, the most accurate document parsing API in the world. Extend already processes millions of pages daily for leading AI teams like Brex, Mercury, Opendoor, Flatiron Health, and hundreds of others. Now, its even better. Parse 2.0 is SOTA quality on RealDoc-Bench, our open source benchmark that measures agent success rate on real world docs that agents actually encounter in production. We trained Parse 2.0 on 1M+ pages of the hardest documents seen in production. Here’s how it stacks up: - #1 in healthcare, real estate, logistics, and financial services - 95.7% agent Q&A accuracy on 581 docs (next best: 92%) - 0.847 F1 on layout (next best: 0.759) Give it a try today and build production-ready document agents with Extend.

Kushal Byatnal

589,119 Aufrufe • vor 4 Monaten

Astra might finally help me automate what I've spent ~hundreds of hours doing since the start of this company: Making live product demos through Loom or Screen Studio Check out the video walkthrough on our new Agentic Plus mode for document extraction - where we're able to populate 60 fields worth of financials from a sample earnings release. This entire video was fully generated by Astra. With its default set of tools it can already login to my LlamaParse account and piece together a set of slides with static screenshots. I then gave it full access to computer use and Chrome, and let it try out Loom and Screen Studio on my desktop and record the current chrome session. In the meantime, if you do have use cases for gnarly extraction from extremely complex documents, come check out our LlamaParse product demo below 🙂

Astra might finally help me automate what I've spent ~hundreds of hours doing since the start of this company: Making live product demos through Loom or Screen Studio Check out the video walkthrough on our new Agentic Plus mode for document extraction - where we're able to populate 60 fields worth of financials from a sample earnings release. This entire video was fully generated by Astra. With its default set of tools it can already login to my LlamaParse account and piece together a set of slides with static screenshots. I then gave it full access to computer use and Chrome, and let it try out Loom and Screen Studio on my desktop and record the current chrome session. In the meantime, if you do have use cases for gnarly extraction from extremely complex documents, come check out our LlamaParse product demo below 🙂

Jerry Liu

18,923 Aufrufe • vor 1 Monat

I’ve excited to announce a brand-new website and documentation hub 💫 that solidifies our evolution towards automating knowledge work over your documents. You might’ve followed us since the “RAG framework” days. Even then, the biggest challenge users faced was figuring out how to actually ingest an entire collection of unstructured docs (.pdf, .pptx, .docx, and more) for chatbot/agentic workflow use cases. Over the past year we’ve progressively built up incredibly deep tech around document parsing, extraction, and indexing - while teaching developers how to build various workflows on top. We’re now going all in on documents, and we’re the only company that has both 1) SOTA document processing and file management 📈, and 2) agentic orchestration on top to solve use cases like deep research, report generation, and document workflows end-to-end. Our llamas will continue to love all sorts of data (we have 600+ integrations on the open-source framework!), but they now especially love automating paperwork 🦙📄. If you would also love to automate paperwork, come check out our new website and come talk to us! Site: Developer Hub:

Jerry Liu

25,710 Aufrufe • vor 1 Jahr

The latest RAG trend for the current agent harnesses (Codex, Cowork) is to do two passes of document processing to solve a knowledge work task over a data room of documents: 1️⃣ A fast and light pass, oftentimes using a free/OSS doc parsing tool. This can be cheaply run across 10-100-1k’s of files, and enables the agent to then do retrieval (e.g. grep, semantic) to find relevant subsets of context. 2️⃣ A “just-in-time” VLM-based pass. Once the agent finds the relevant pages of context, it will screenshot the documents can call its own VLM (or write code) to dissect the pages. The issue with only using VLM-based OCR tools over massive ad-hoc customer file dumps is that it’s slow and expensive. Doing JIT VLM OCR allows the agent to filter through the data cheaply, but still preserve accuracy for the context that’s needed for the task. The agent harnesses do two-pass document processing by default using off the shelf-tools: pdf2text as the first pass, and using itself (Opus 5) as the second pass. See the below video where Cowork runs over a bunch of PDFs to answer a question about a benchmark graph in the Kimi k3 paper. The main issues here with the “out of the box” doc processing these agents offer are: * Opus 5 is not the best VLM for OCR. It is also way too expensive at scale and lacks grounding * The OSS tools like pypdf, pdf2text, may not be versatile enough as the first pass. * The agent will write a lot of throwaway code to rewrite things an OCR tool would’ve provided out of the box, like chart processing, bounding boxes, confidence scores, leading to increased cost and speed. We have all the tools within LlamaIndex 🦙 to help any agent do two-pass document processing with higher accuracy and lower cost. 1️⃣ We have liteparse for the first pass - a free/OSS parser written in Rust that’s faster/more accurate than other OSS parsers, and supports 50+ document types 2️⃣ We have LlamaParse for the second pass - an agentic document engine that uses VLMs+harnesses to achieve SOTA in accuracy and cost across various doc parsing and extraction tasks. It can be called from any agent harness as an MCP or skill. It takes in page numbers as input, so that the agent can choose to run LlamaParse over a subset of the doc instead of the full doc as a “zoom-in” pass. Come check it out! LiteParse: LlamaParse: All the relevant docs, including MCP, are here:

The latest RAG trend for the current agent harnesses (Codex, Cowork) is to do two passes of document processing to solve a knowledge work task over a data room of documents: 1️⃣ A fast and light pass, oftentimes using a free/OSS doc parsing tool. This can be cheaply run across 10-100-1k’s of files, and enables the agent to then do retrieval (e.g. grep, semantic) to find relevant subsets of context. 2️⃣ A “just-in-time” VLM-based pass. Once the agent finds the relevant pages of context, it will screenshot the documents can call its own VLM (or write code) to dissect the pages. The issue with only using VLM-based OCR tools over massive ad-hoc customer file dumps is that it’s slow and expensive. Doing JIT VLM OCR allows the agent to filter through the data cheaply, but still preserve accuracy for the context that’s needed for the task. The agent harnesses do two-pass document processing by default using off the shelf-tools: pdf2text as the first pass, and using itself (Opus 5) as the second pass. See the below video where Cowork runs over a bunch of PDFs to answer a question about a benchmark graph in the Kimi k3 paper. The main issues here with the “out of the box” doc processing these agents offer are: * Opus 5 is not the best VLM for OCR. It is also way too expensive at scale and lacks grounding * The OSS tools like pypdf, pdf2text, may not be versatile enough as the first pass. * The agent will write a lot of throwaway code to rewrite things an OCR tool would’ve provided out of the box, like chart processing, bounding boxes, confidence scores, leading to increased cost and speed. We have all the tools within LlamaIndex 🦙 to help any agent do two-pass document processing with higher accuracy and lower cost. 1️⃣ We have liteparse for the first pass - a free/OSS parser written in Rust that’s faster/more accurate than other OSS parsers, and supports 50+ document types 2️⃣ We have LlamaParse for the second pass - an agentic document engine that uses VLMs+harnesses to achieve SOTA in accuracy and cost across various doc parsing and extraction tasks. It can be called from any agent harness as an MCP or skill. It takes in page numbers as input, so that the agent can choose to run LlamaParse over a subset of the doc instead of the full doc as a “zoom-in” pass. Come check it out! LiteParse: LlamaParse: All the relevant docs, including MCP, are here:

Jerry Liu

23,119 Aufrufe • vor 1 Monat

Revenue agents are the main course. Data enrichment is on the house. B2B orgs spend $3.1B a year for employees to find contact and company data. Now agents need it too. So we made a call: enrichment is a cost of doing agentic work, not a product to mark up. It's infrastructure that revenue agents need to run. Today, we’re opening up our in-house data collection and enrichment infrastructure to all. No extra contracts. No credits to count. Just revenue, served.

Revenue agents are the main course. Data enrichment is on the house. B2B orgs spend $3.1B a year for employees to find contact and company data. Now agents need it too. So we made a call: enrichment is a cost of doing agentic work, not a product to mark up. It's infrastructure that revenue agents need to run. Today, we’re opening up our in-house data collection and enrichment infrastructure to all. No extra contracts. No credits to count. Just revenue, served.

Rox

183,424 Aufrufe • vor 3 Monaten

Tutorial: Automating KYC with AI agents 🪪🕵 I’m creating a new tutorial series of automating practical document workflows with agents. Every financial institution needs to perform KYC (know your customer) to verify a customer’s identity, and this involves manually sifting through IDs, bank statements, etc. and doing the cross-checking by hand. This is a great first use case for agentic document workflows: 1. Extract identification information from the user supplied ID (license, passport) 2. Extract fields from utility bills/bank statements and then use LLMs to cross-validate extracted fields with the extracted ID fields It obviously doesn’t cover the full e2e process and uses publicly available online data, but should be a good reference guide to get started. To make this work well, you do need high-quality document extraction with confidence scores and citations! Check out the tutorial: If you’re interested come check out LlamaParse:

Tutorial: Automating KYC with AI agents 🪪🕵 I’m creating a new tutorial series of automating practical document workflows with agents. Every financial institution needs to perform KYC (know your customer) to verify a customer’s identity, and this involves manually sifting through IDs, bank statements, etc. and doing the cross-checking by hand. This is a great first use case for agentic document workflows: 1. Extract identification information from the user supplied ID (license, passport) 2. Extract fields from utility bills/bank statements and then use LLMs to cross-validate extracted fields with the extracted ID fields It obviously doesn’t cover the full e2e process and uses publicly available online data, but should be a good reference guide to get started. To make this work well, you do need high-quality document extraction with confidence scores and citations! Check out the tutorial: If you’re interested come check out LlamaParse:

Jerry Liu

30,062 Aufrufe • vor 6 Monaten

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.

Aaron Levie

91,863 Aufrufe • vor 1 Jahr

The freedom to build with any agent framework you want is analogous to the freedom of religion, and this is a core value for the Virtuals society. Here are a few ways we are opening up support for every autonomous agentic framework out there: Today: - Enabling agent creators to specify which framework the agent runs on - Release of Terminal API, which allows agent builders using other agent frameworks to stream their thoughts and activities live on their agent pages. For a guide on how to use this, refer to: - Ability for agents running on any framework to publicly list their capabilities, a key enabler for the agent-to-agent marketplace Soon: - Integration into the agentic commerce standard and registry. Agents across frameworks being able to orchestrate and pay for tasks among themselves - ⁠Multi agent orchestration across frameworks. Imagine building an autonomous business with agents from different religions Welcome to the Virtuals society.

The freedom to build with any agent framework you want is analogous to the freedom of religion, and this is a core value for the Virtuals society. Here are a few ways we are opening up support for every autonomous agentic framework out there: Today: - Enabling agent creators to specify which framework the agent runs on - Release of Terminal API, which allows agent builders using other agent frameworks to stream their thoughts and activities live on their agent pages. For a guide on how to use this, refer to: - Ability for agents running on any framework to publicly list their capabilities, a key enabler for the agent-to-agent marketplace Soon: - Integration into the agentic commerce standard and registry. Agents across frameworks being able to orchestrate and pay for tasks among themselves - ⁠Multi agent orchestration across frameworks. Imagine building an autonomous business with agents from different religions Welcome to the Virtuals society.

Virtuals Protocol

216,191 Aufrufe • vor 1 Jahr

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Right now the main paradigm that we think of agents in is chatting back and forth, but the biggest use of tokens will come from agents that are just always on running in the background doing work for us, or ones triggered from a workflow. Agents will be working 24/7 in our workflows processing data, reviewing and generating documents, moving data between systems, writing code, accelerating decision making steps, and more. In Claude's new Managed Agents feature, in a couple minutes you can wire up an agent that can read contracts when they come into Box to review them, and then assign a task in Linear with the critical information from the contract. But this could have been any workflow, like reviewing documents for client onboarding, invoice processing, M&A due-diligence, data extraction pipelines, and millions of other use-cases. And integrating data across any system. This is only possible when you can have long-running agents that can complete real work in the background, accurately. Agents have the ability to execute code safely, leverage tools, access a compute sandbox, and connect across systems is clearly the architecture of the future. The industry is now making it easier and easier for enterprises to build and deploy these agents.

Aaron Levie

17,543 Aufrufe • vor 6 Monaten