Jerry Liu
@jerryjliu0 • 85,807 subscribers
Parsing the world's hardest PDFs @llama_index. cofounder/CEO LlamaParse: https://t.co/XYZmx5TFz8 Enterprise: https://t.co/Ht5jwxSrQB
Shorts
Videos
Introducing DocJev - a lightning-fast OSS library for document classification and splitting with jev ⚡️ Give a document alongside some natural language category rules. Jev will predict the document category (classify) or the boundaries between sub-documents (split). It is 6x faster than gpt-5.6-luna with equivalent accuracy. You can choose between different OCR backends: liteparse: the fastest/most accurate free+OSS text parser out there. Perfect for digitalized documents. The speedups vs. luna above are inclusive of liteparse times. LlamaParse: the most advanced VLM-based solution for complex docs. Using this will of course add latency on document preprocessing. But it’s a good option if you want to cache the digitalized representations of documents for a variety of downstream tasks. Check it out: If you want to dive deeper into liteparse or LlamaParse check the links below: liteparse: LlamaParse:
Jerry Liu217,617 görüntüleme • 27 gün önce
We built the fastest PDF -> markdown parser in the world 🚀⚡️ AND it’s more accurate than any other open-source, model-free parser (pymupdf4llm, opendataloader, pdf-inspector, markitdown) on 3 standardized benchmarks: olmOCR0-bench, opendataloader-bench, ParseBench Introducing LiteParse v2.1. The v2 base version was already the fastest document->text parser on the planet, and with this new release we’ve introduced markdown. It is fully open-source (Apache 2.0) and free, is usable from CLI/Rust/Node/Python/WASM, and is also installable as a one-click agent skill. Check it out: Come check out LiteParse:
Jerry Liu364,389 görüntüleme • 4 ay önce
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!
Jerry Liu52,224 görüntüleme • 16 gün önce
Introducing LiteParse - the best model-free document parsing tool for AI agents 💫 ✅ It’s completely open-source and free. ✅ No GPU required, will process ~500 pages in 2 seconds on commodity hardware ✅ More accurate than PyPDF, PyMuPDF, Markdown. Also way more readable - see below for how we parse tables!! ✅ Supports 50+ file formats, from PDFs to Office docs to images ✅ Is designed to plug and play with Claude Code, OpenClaw, and any other AI agent with a one-line skills install. Supports native screenshotting capabilities. We spent years building up LlamaParse by orchestrating state-of-the-art VLMs over the most complex documents. Along the way we realized that you could get quite far on most docs through fast and cheap text parsing. Take a look at the video below. For really complex tables within PDFs, we output them in a spatial grid that’s both AI and human-interpretable. Any other free/light parser light PyPDF will destroy the representation of this table and output a sequential list. This is not a replacement for a VLM-based OCR tool (it requires 0 GPUs and doesn’t use models), but it is shocking how good it is to parse most documents. Huge shoutout to Logan Markewich and Clelia Bertelli (🦀/acc) for all the work here. Come check it out: Repo:
Jerry Liu257,589 görüntüleme • 7 ay önce
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 Liu75,742 görüntüleme • 2 ay önce
Parse PDFs at lightspeed (this video is at 1x) Absolute cinema
Jerry Liu144,675 görüntüleme • 4 ay önce
Introducing FlyOCR 🪰 - I trained a fly brain to read a PDF It uses the full MaleCNS v1.0 fruit fly connectcome. The architecture is inspired by doomfly by The fly splits a pdf image into individual glyphs, maps pixels into receptor activations, runs simplified current-based dynamics across the 166k neurons and 25m edges in the circuit, applies a compact readout model on the downstream spikes, and concatenates everything into the parsed output. On reading an actual Microsoft 10-k, the fly gets ~86% over the balance sheet heading, but is largely able to read the numeric values correctly. Over 1.7k+ sampled glyphs (chars+digits) it gets 87% accuracy. With enough training it might match some of the latter-generation MNIST models! Maybe eventually we’ll replace our doc parsing VLMs with flies. Full video below. Repo with full code + report:
Jerry Liu38,858 görüntüleme • 1 ay önce
i'm flattered by the shoutout, but there's no free lunch for document parsing Cohere parse starts at $1.50 / 1k pages, which is indeed on the cheaper end of doc OCR solutions, but it scores ~50% when averaged across all 5 ParseBench dimensions: * It lacks high-quality visual grounding, doing coarse segmentation for tables and images, but lacking finer-grained bboxes at the word/cell/line-level. this is quite important for any sensitive AI application that requires precise citations back to the source. * It lacks general visual / chart parsing capabilities, which are prevalent across finance, manufacturing, healthcare, and more * to its credit, it does a decent job over tables (87%) compared to other comparable solutions at the price point our cost-effective mode in LlamaParse starts at 0.375c / page and is more consistently strong across all dimensions. also there's various ways to bring it down with volume discounts if you're interested in learning more about various document parsing modes and comparing tradeoffs in price/accuracy, come talk to us! LlamaParse:
Jerry Liu25,896 görüntüleme • 1 ay önce
one of the most challenging tasks for frontier models is being able to extract thousands of values from extremely dense tables in documents. our new Extract v2.5 agents are able to get 93%-96%+ on long-list extraction, including cells that fall in between pages. in contrast, astra gets ~30% accuracy over this benchmark. in these cases, frontier VLMs can stop early or miss repeated records. they also struggle to attribute each value back to the source. we are able to attribute every single extracted value back to the source. check out the video below, the blog post, and llamaparse! blog: llamaparse:
Jerry Liu13,305 görüntüleme • 15 gün önce
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 Liu108,403 görüntüleme • 6 ay önce
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 Liu11,534 görüntüleme • 13 gün önce
We've created a comprehensive Retrieval Harness for modern agentic retrieval in 2026. The harness provides a persistent data pipeline that can connect to a data source, index and update a large knowledge base, and expose a broad set of tools akin to filesystem operations (semantic/keyword search, regex grep, file search, read). You can plug this into any of your agents to let them autonomously crawl an arbitrary knowledge base to solve a task with any complexity. Check out our reference implementation: LlamaParse:
Jerry Liu57,248 görüntüleme • 3 ay önce
we've built the world's most advanced engine for document extraction over complex documents the video below shows an overview of LlamaExtract Agentic Plus in action. long tables, giant forms, calibrated confidence scores, and grounded extraction. if you have complex document extraction use cases and existing vendors aren't cutting it, let us know: come sign up to LlamaParse today:
Jerry Liu14,285 görüntüleme • 24 gün önce
I built a Claude Code skill that allows it to generate a deep research report over any collection of complex docs (PDFs, Word, Pptx)….and generate word-level citations and bounding boxes directly back to the source! 📝 Check out “/research-docs”. 1. It parses out text and bounding boxes from every doc with liteparse, in seconds. 2. It then generates a full HTML report of the outputs that let you see word-level citations in each page. Raw Claude obviously has deep research capabilities, but it lacks an audit trail back to the source. This skill gives you a researched report that can be audited by others. Check it out: LiteParse:
Jerry Liu77,259 görüntüleme • 6 ay önce
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 processing platform, and liteparse is the central pillar behind our OSS efforts. It's blazing fast (and getting faster soon!), supports 50+ file formats, and is one-shot installable as an agent skill. Webpage: Come check it out:
Jerry Liu70,895 görüntüleme • 6 ay önce
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 Liu18,923 görüntüleme • 1 ay önce
Introducing NotebookLlama - an open-source version of NotebookLM! 📓🦙 NotebookLlama is a full implementation of NotebookLM that includes all the capabilities that makes it so great for researchers+business users: ✅ Create a knowledge repository of documents. Has likely higher accuracy than NotebookLM since it’s using LlamaCloud under the hood for high-quality parsing/extraction over complex docs. ✅ Generate summaries and knowledge graph mind-maps 🤯 ✅ Generate podcasts thanks to ElevenLabs 🗣️ ✅ Agentic chat with docs and view metrics with OpenTelemetry This all lives within an open-source repo so you can clone/modify at will to swap in your own components! Huge shoutout to Clelia Bertelli🧑🚀 for leading this. Repo: LlamaCloud helps power the parsing/ingestion. You can always use your own stuff too, but in the meantime you can check out LlamaCloud here:
Jerry Liu137,934 görüntüleme • 1 yıl önce
We parsed this SpaceX equity research PDF faster than the time it took for Screen Studio to zoom in ⚡️🔥 liteparse is now the best open-source document parsing tool out there. There’s no reason to not use it as a first pass, even if you do have docs that require heavier VLM processing downstream. Try it out now over any document: Repo:
Jerry Liu43,552 görüntüleme • 3 ay önce
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 Liu23,119 görüntüleme • 1 ay önce