Given the 3,000 texts I've gotten in the last 4 minutes reminding me to vote.... I'm about ready to try this now too...
I had my Muse agent put me on the National Do Not Call/Text Directory. By law telemarketers and other companies have 30 days to scrub my number from their lists. Otherwise Muse will automatically start logging every violation and will skip trace and go after every single one of the violations and hopefully collect between $500 and $1,500 per violation. Let's see how this goes.
MJ 🦙 retweeted
We built a haunted house for doc parsers 🎃
Boo Bench is 179 pages that push parsers into repetition loops. One model saw 246 redaction x’s on a page and wrote 23,004 of them.
Results in thread!
Leaderboard + paper: llamaindex.ai/benchmarks/boo…
Dataset: huggingface.co/datasets/llam…
MJ 🦙 retweeted
Anthropic filed their 318-page S-1 yesterday for the biggest IPO in history.
We parsed and synthesized every page in the S-1 and built this reader so that you can get the highlights: documentstories.com/anthropi…
Built with LlamaParse and @vercel
The llamas learned to read. OCRia-1 is live in LlamaParse: our own parsing model, 12+ points ahead of the next-best on ParseBench, way better on tables and charts. Same price, no drama llama. Got a doc that breaks every parser? Send it my way.
Today we’re releasing OCRia-1, a frontier VLM for document parsing that sets a new SOTA in accuracy, cost, and latency.
It not only sets a new high score on ParseBench (87.4), but also leads in three 3rd-party benchmarks: olmOCR-bench* (83.5 overall, 92.9 on tables!), PulseBench-Tab (84.1), and fr-bench-pdf2md (72.1).
OCRia-1 is really, really good at parsing complex tables: nested headers, merged cells, irregular grids, scanned tables, and more. It is also fantastic at parsing complex unlabeled charts (line, bar, pie, technical diagrams), and preserving complex formatting. Most real-world enterprise documents contain at least one of the these, whether it’s a big tax withholding table or a public economic report.
It is a 4B model and outperforms all other models within a similar parameter class: LightOnOCR-3, Chandra-OCR 2, Mistral OCR 4.1, and more. It is also extremely fast.
All credit goes to our research team, who spent countless hours on curating a diverse dataset, tuning our training pipeline, and squeezing every last drop out of model optimization so that it can process billions of pages at scale.
OCRia-1 as a base is powering all of our modes within LlamaParse (cost-effective, agentic, agentic plus), so you can access its capabilities today!
If you’re processing millions/billions of documents at scale, we’re offering enterprises that book a demo up to $3k in credits for a guided evaluation.**
*olmOCR-bench scores are adjusted based on unifying rendering at 1,288px for all models
**enterprise POC credits apply to eligible organizations that book a demo
MJ 🦙 retweeted
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: llamaindex.ai/blog/introduci…
All of these are available on LlamaParse: cloud.llamaindex.ai/ . Come check it out!
MJ 🦙 retweeted
week 2 at @llama_index: pitched a vlog series
week 3: filming mr. beast at the u.s. open 🎾
introducing ep. 1 of Unindexed: the behind-the-scenes (and occasionally chaotic) side of llamaindex
we hosted CTOs + eng leaders at the u.s. open, talked doc processing across finance, legal, and healthcare, and somehow ended up with mr. beast and the williams sisters on camera
more chaos coming soon :D
MJ 🦙 retweeted
We're all over AI Engineer World's Fair on June 29 to July 2. 🦙
📍Visit us at booth L-G47. LlamaParse demos + Fear of Docs swag
🎤 @jerryjliu0, our Founder & CEO, on agentic document parsing and shipping agents that survive production. Tue 6/30, 11:10 AM, Vision & OCR (Room 2006)
🎤 George He, our Head of Engineering, in a live parse-off, LlamaParse vs the leading LLMs. Thu 7/2, 1:55 PM, Expo Stage 4
🥒 The Agent Open (6/30)
RSVP 👉 luma.com/the-agent-open?utm_…
MJ 🦙 retweeted
SoftBank’s investor presentation is one of the greatest things ever made. I’ve been thinking about it all day. These are the real slides shown in a speech where Masayoshi Son said he wouldn’t retire for at least another decade. The goose stuff is perfect.
group.softbank/media/Project…
MJ 🦙 retweeted
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: llamaindex.ai/blog/markdown-…
Come check out LiteParse: github.com/run-llama/litepar…
LiteParse v2.1 is here, and its bringing the fastest markdown output possible.
In this release, we are fulfilling our top request: markdown output. But in the spirit of "lite"-ness, we are doing this completely LLM-free and fast.
Not only is it fast, it also beats all other model-free competitors in 3 separate benchmark datasets.
Read more about it in our release blog: llamaindex.ai/blog/markdown-…
1. It’ll be a good morning when I get Fable back.
2. WHY does Claude need to keep this message up 100% of the time? It’s really annoying me that I can’t dismiss it.
MJ 🦙 retweeted
Last week we revamped Liteparse to be the fastest PDF parser out there ⚡️
An underrated part of liteparse is it doesn't just give you text. It gives you bounding boxes that a coding agent can use to paint exact audit trails back to the source document.
For instance, check out the deep research skill we compiled in liteparse_samples: github.com/jerryjliu/litepar…
Come check out liteparse: github.com/run-llama/litepar…
We are hard at work making liteparse even better (e.g. Markdown support). Please feel free to open up issues, PRs, and let us know your feature requests 🙏
We've created the world's fastest PDF parser ⚡️
And it's more accurate than any other open-source, model-free PDF parser out there (pymupdf, pypdf, markitdown, pdftotext, opendataloader, pymupdf4llm)
Introducing LiteParse v2 - we rewrote the entire library into Rust and adapted it as native packages for Python and Node.
It supports 50+ different document types, can be triggered directly or installable directly within your favorite AI agent.
Blog: llamaindex.ai/blog/liteparse…
Repo: github.com/run-llama/litepar…
MJ 🦙 retweeted
Last week we launched LiteParse - a free and fast document parser that provides more accurate AI-ready text than other free/fast parser libraries.
It’s a great tool you can plug into assistant agents like Claude Code/OpenClaw and get good results, especially when paired with its screenshotting capabilities.
But I do want to note that it doesn’t use any models under the hood (no VLMs/LLMs/even OCR models natively), and it’s not a replacement for VLM-based OCR solutions. It is fast because it is heuristic based!
I attached a comparison table below.
✅ It is really good at text extraction and even table extraction, *specifically for LLM understanding*. It will lay the text out in a manner that’s easy for humans/AI to understand.
✅ It is great for assistant coding agents because the agent harness can use its text parsing to do a “fast” step, and then its screenshot capabilities to “dive deep” into a specific page
🚫 It is not great over scanned pages/visuals/anything requiring OCR. We do have OOB integrations with EasyOCR and PaddleOCR
🚫It doesn’t do layout detection and segmentation - it won’t draw bounding boxes over different elements on the page (though it does have word-level bounding boxes!)
Tl;dr it’s great for plugging into an AI assistant tool. If you’re trying to OCR a bunch of docs in batch, check out LlamaParse :)
LiteParse: github.com/run-llama/litepar…
LlamaParse: cloud.llamaindex.ai/?utm_sou…
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 @LoganMarkewich and @itsclelia for all the work here.
Come check it out: llamaindex.ai/blog/liteparse…
Repo: github.com/run-llama/litepar…
MJ 🦙 retweeted
Improve document parsing accuracy by 15% for financial PDFs.
Use LlamaParse and Gemini 3.1 Pro to extract high-quality data from unstructured brokerage statements and complex tables.
📈 Precise reasoning
📂 Structured PDF data
⚡️ Event-driven scaling
Dive into the code on GitHub → goo.gle/4dCPjjd
MJ 🦙 retweeted
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 @LoganMarkewich and @itsclelia for all the work here.
Come check it out: llamaindex.ai/blog/liteparse…
Repo: github.com/run-llama/litepar…
We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood.
Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙
It's a CLI + TS-native library for layout-aware text parsing from PDFs, Office docs, and images. Local, zero Python dependencies, and built specifically for agents and LLM pipelines. Think of it as our way of giving the community a solid starting point for document parsing:
npm i -g @llamaindex/liteparse
lit parse anything.pdf
- preserves spatial layout (columns, tables, alignment)
- built-in local OCR, or bring your own server
- screenshots for multimodal LLMs
- handles PDFs, office docs, images
Blog: llamaindex.ai/blog/liteparse…
Repo: github.com/run-llama/litepar…
MJ 🦙 retweeted
We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learned a lot about what fast, lightweight parsing actually looks like under the hood.
Today, we're open-sourcing a light-weight core of that tech as LiteParse 🦙
It's a CLI + TS-native library for layout-aware text parsing from PDFs, Office docs, and images. Local, zero Python dependencies, and built specifically for agents and LLM pipelines. Think of it as our way of giving the community a solid starting point for document parsing:
npm i -g @llamaindex/liteparse
lit parse anything.pdf
- preserves spatial layout (columns, tables, alignment)
- built-in local OCR, or bring your own server
- screenshots for multimodal LLMs
- handles PDFs, office docs, images
Blog: llamaindex.ai/blog/liteparse…
Repo: github.com/run-llama/litepar…
MJ 🦙 retweeted
Our new bounding box approach in LlamaParse gives you clean bounding boxes while preserving clean reading order of the text through agentic reconstruction.
The issue with traditional parsing methods is that the quality of the output is directly dependent on the layout detector - if the predicted boxes are wrong / in the wrong sequence, then your output is garbled.
Here we use LLMs to reconstruct the entire semantic flow of the text, but still allow bounding box processing in parallel for additional metadata!
Now available in LlamaParse: cloud.llamaindex.ai/
MJ 🦙 retweeted
🚀 LlamaIndex is headed to @money2020 in Las Vegas!
We’re meeting with fintech and financial leaders to show how AI agents built on LlamaIndex are transforming underwriting, compliance, operations and more — all powered by private docs & data.
Want to see how? Book a meeting with us & enter to win limited-edition LlamaIndex swag:
👉 landing.llamaindex.ai/llamai…
#Fintech #AI #AIAgents #DocumentAI #Money2020
