Knowledge catalogue
I’m excited to announce that @llama_index is on the @CBInsights AI 100 list for 2026 🔥 We’re on a mission to parse all of the world’s PDFs, and make them accessible to both humans and AI agents. List:
May the 4th be with you!✨ Celebrate with us, you must. Join our Start Up Party Up this Thursday before SF's free 2nd St Fest 🎵 Calling all #AI Jedis - leave your agents at home and sign up for our nex
Run an entire company with agents 🔥 It's always awesome to see companies continuing to innovate on AI-native UI/UX, particularly around multi-agent coordination, to solve deeply complex tasks beyond w
Jerry Liu advocates for modular architecture as a strategy to avoid vendor lock-in with AI providers like Anthropic during the emergence of AI agents. He argues that building flexible, interchangeable
Parsing PDFs is hard This past week I gave a few talks (at both AI Dev '26 by @DeepLearningAI and @Capgemini ) on why this is still such an open problem, and it’s even more important as agents become
A lot of work around AI in 2023 was spent on building picks and shovels. I would know this because that was basically the core goal of the original @llama_index framework. Today, a lot of that is no l
The article discusses how the AI scaffolding layer—infrastructure tools and frameworks built around large language models—is experiencing consolidation and collapse, with LlamaIndex CEO explaining whi
Jerry Liu predicts that genuinely useful long-running AI agents will become a reality by 2026, viewing this development as simultaneously inevitable and remarkable. The post reflects on how advances i
Jerry Liu discusses how AI now generates approximately 95% of code, arguing that the era of orchestration frameworks has ended and been replaced by newer approaches to AI development and integration.
Jerry Liu considers whether llama_index should rebrand to 'applied automation co,' suggesting potential strategic discussions about the project's direction and positioning. This appears to be a casual
Our CEO @jerryjliu0 in @VentureBeat , on what's actually changing in the LLM stack: 'We've really identified that there's a core set of data that has been locked up in all these file format containers
Building a document processing pipeline at scale is hard, and is one of the reasons that it's hard to DIY your own document OCR solution by relying on LLM APIs. Your orchestration pipeline needs to ha
Building scalable, distributed document processing pipelines isn’t easy. That’s why we teamed up with @render to build a system that: 📝 Leverages the LlamaParse platform to parse, classify, extract, a
Frameworks are dead. @jerryjliu0 of LlamaIndex called it — and then rebuilt the company around what actually matters: context. New episode of Beyond the Pilot: https://www.youtube.com/watch?v=HbXvX-Kt
Jerry Liu expresses gratitude to DeepLearning.AI for hosting an engaging event and humorously requests a laptop sticker as a memento. The post suggests Liu attended or participated in a DeepLearning.A
Jerry Liu discusses a key limitation of state-of-the-art large language models at AI Dev Day '26, highlighting that while modern LLMs excel at building applications, they struggle with fundamental tas
This is really well thought out. Filesystems are the new default abstraction for agents to interact with documents (the new RAG stack in 2026). The issue is actually figuring out how to productize thi
We shipped a LlamaParse MCP server to let you parse, classify, split, and generally operate over your hardest documents with your favorite AI agent 📄🤖 Check out the MCP server: http://mcp.llamaindex.a
Parsing documents with AI agents just got a lot more seamless🚀 We've rebuilt the LlamaParse MCP server to handle your document processing workflows, and you can connect it today to any MCP-compatible
The LlamaParse MCP got a new face, and it is now easier than ever to run document processing workflows from your agents🚀 We refactored our MCP to have: - Direct integration with our Parse, Classify an
Let's talk document formatting. Bold. Italics. Superscripts. Strikethroughs. The visual cues humans rely on every time we read a doc, and ones existing OCR benchmarks completely ignore. 😱'199' struck
Want to see which frontier models do the best on document understanding? Check out our ParseBench leaderboard on @kaggle! https://www.kaggle.com/benchmarks/llamaindex-org/parsebench For more details o
Loan processors spend 40–60% of their time reconciling income across tax returns, pay stubs, W-2s, and bank statements. We built an end-to-end pipeline that automates it with LlamaParse + the Claude A
ParseBench: A benchmark for document parsing agents @llama_index just shipped a benchmark with 2k verified pages for real enterprise documents. Benchmarks are the major underrated component in the ML
Processing loan applications traditionally takes a staggering amount of time going through paperwork - ~dozens of hours every month looking at the loan application and cross-checking it with user-subm
We need more evals for document understanding. ParseBench is a really great start. I respect @llama_index ‘s work on this. 📈 We benchmarked GPT-5.5 on document understanding 📄📊 We ran it through Parse
Jerry Liu observes the proliferation of AI-related advertisements throughout New York City, likely reflecting the rapid commercialization and mainstream adoption of AI technologies in urban markets. T
As a point of comparison, our commercial document OCR solution LlamaParse wins on all relevant dimensions (except content faithfulness against Opus) and is 1.25c / page prior to an enterprise plan. Co
Grateful to @Wing_VC to be a part of ET30 and @Nasdaq for the event 🔥 Hope to be back to ring the bell for real 🙂 (I am in the photo! In the bottom right) Congrats to the ET30 Class of 2026 who just r
We benchmarked GPT-5.5 on document understanding 📄📊 We ran it through ParseBench, our comprehensive OCR benchmark over enterprise documents. We evaluated metrics across various dimensions: visual grou
Jerry Liu congratulated the ET30 Class of 2026 for ringing the Nasdaq closing bell, celebrating what appears to be an achievement by members of an executive or entrepreneurial cohort. The ET30 is like
If you want to stack rank LLMs/VLMs on document understanding 📄, you can through ParseBench, now live on @kaggle 📊 ParseBench is the most comprehensive document OCR benchmark over real enterprise docu
LlamaParse is a document parsing tool offered by LlamaIndex that specializes in extracting and processing information from production documents. The tool appears designed to handle complex document fo
Our own team was trying to figure out how to get LiteParse working in the browser 😂 Shouldn't have doubted Claude. Claude knows best. LiteParse is really neat! It does a great job of extracting text f
ParseBench is now live on @Kaggle. The first document OCR benchmark built for AI agents — 2,000 enterprise pages, 167K+ test rules, 5 dimensions that actually break downstream agents. Benchmark your p
This post shows the #ET30 Class of 2026 (likely a cohort of emerging entrepreneurs or innovators) at the Nasdaq in Times Square, with Jerry Liu inviting followers to identify who in the photo inspires
LiteParse: our open-source, layout-aware PDF parser for AI agents. The secret? Grid projection. Instead of heavy ML layout models or flat text extraction, it projects text onto a monospace grid so ali
LiteParse, our OSS document parser, is really good at parsing complex PDF layouts, text, and tables into a clean spatial grid. The best part is it doesn't use VLMs or any ML models at all. It's entire
Let's talk parsing charts 📊📈. Last week we released ParseBench, the first document OCR benchmark for AI agents. New in ParseBench: ChartDataPointMatch. Most document look at a chart and OCR the captio
Our core mission today is using AI to solve document OCR. All of our product offerings, from commercial (LlamaParse) to open-source (LiteParse, ParseBench), are fully aligned towards solving this prob
ParseBench is the first benchmark to include VLM chart understanding 📊📈📉 over enterprise documents. 🟠 Existing benchmarks (ChartQA, ChartXiv) test over charts specifically and not the chart's inclusio
NYC FinTech Week just got an AI track 🗽 Next week we're co-hosting the AI Builders Rooftop Happy Hour with @LinkupAPI — for the people shipping fintech agents, document intelligence, and agentic workf
LiteParse is the best model-free, open-source document parser for AI agents. It now gets a first-class landing page on our website 💫 Our company mission is building the world's best agentic document p
Source tweet is here: https://x.com/jerryjliu0/status/2044902620746363016?s=20 We comprehensively benchmarked Opus 4.7 on document understanding. We evaluated it through ParseBench - our comprehensive
Thanks for the shoutout re: ParseBench! 📑 🙂 Opus 4.7 is definitely a step up from Opus 4.6 on document understanding capabilities. Great to see labs start to push a bit more on this front. [16 Apr 202
A downside with using VLMs to parse PDFs is guaranteeing that the output text is *correct* and output in the correct reading order. 1️⃣ Text correctness: making sure that digits, words, sentences are
Let's talk content faithfulness. Four days ago, we launched ParseBench, the first document OCR benchmark for AI agents. Its most fundamental metric asks: did the parser capture all the text, in order,
Anthropic says Opus 4.7 hits 80.6% on Document Reasoning — up from 57.1%. But 'reasoning about documents' ≠ 'parsing documents for agents.' We ran it on ParseBench. → Charts: 13.5% → 55.8% (+42.3) — h
LiteParse should be the default document parser you use with any AI agent (Claude Code, Claude Cowork, OpenClaw, Codex, and more) The core is extremely fast text and accurate parsing from any document
We comprehensively benchmarked Opus 4.7 on document understanding. We evaluated it through ParseBench - our comprehensive OCR benchmark for enterprise documents where we evaluate tables, text, charts,
Document OCR benchmarks are still an open problem Existing document OCR benchmarks are either too narrowly focused on a specific type (e.g. FinTabNet, ChartQA), or on documents that aren’t reflective
If it can’t parse, it can’t perform. ❌ Reliable document understanding is fundamental to enterprise-grade #AgenticAutomation. We're excited to see the release of ParseBench, a new open-source benchmar
Let's talk parsing tables. Two days ago we launched ParseBench,the first document OCR benchmark built for AI agents. This deep dive breaks down TableRecordMatch (GTRM), our metric for evaluating compl
Parsing complex tables in PDFs is extremely challenging. Existing metrics for measuring table accuracy, like TEDS (tree edit distance similarity), overweight exact table structure and underweight sema
Jerry Liu, co-founder of LlamaIndex, shared a post on X (formerly Twitter) expressing enthusiasm about a notable development, likely related to AI, large language models, or the LlamaIndex ecosystem.
ParseBench is the most comprehensive OCR benchmark for real-world enterprise documents: financial filings, contracts, insurance documents, and more. We evaluate across 5 dimensions that are present am
This is why we released liteparse :) Free, open-source, designed for agents. Natively supports OCR / screenshotting for deeper visual understanding in a document when needed. @kepano I just tried it t
Everyone who think vision is solved should look at some enterprise documents We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of
great to see more open evals for an important problem We’re open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that wo
Ocr benchmark 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