Search: “jerry-liu--x”

Document extraction is an arbitrarily complex reasoning problem for both frontier models and humans. ✅ The schema encodes essentially hundreds of interrelated reasoning tasks ✅ A PDF can be hundreds o

Introducing ExtractBenchPro: the most challenging benchmark for real-world document extraction. We see a massive long tail of document complexity in terms of use cases brought on from our customers, t

This was my first blog post at @llama_index! Go check out the cool diagrams and stuff Media Introducing ExtractBenchPro: the most challenging benchmark for real-world document extraction. We see a mas

Benchmarks are becoming the core competency of any company. Our company mission is to build the world’s best models for document processing. This also means that we have to build the world’s best benc

Gemini 4 Argon, Muse Spark 1.3, and Muse Wonder 1.0 are all really good at pdf parsing. Come check it out on OpenDocRouter! https://www.opendocrouter.ai/ Media OpenDocRouter makes it dead-simple to st

muse wonder sota on hard document ocr tasks the more you know! We benchmarked Gemini 4 Argon, Muse Wonder, and Muse Spark comprehensively on hard document OCR tasks. They're all pretty good! - Muse Sp

Startups are built on relationships. That’s why IRL events are a core part of our growth strategy at @lemma_ . We hosted our biggest one yet during @SFTechWeek : The Agent Economy Gala. 400+ founders,

There are more document parsing models than ever, and they’re getting harder to tell apart. That’s why we built OpenDocRouter. Every model we serve is benchmarked on ParseBench, with latency and cost

Niel Pal hosted the Agent Economy Gala last week—a rare Black‑Tie event held in San Francisco that drew approximately 300 builders and investors. The evening featured participants from the llama_index

OpenDocRouter makes it dead-simple to start parsing your documents across on ton of frontier Models (gemini, luna) and latest OSS models (LightOnOCR-3, MinerU2.5-pro). Parse your first document in 60

On October 13, 2026, Tim Baer announced he would take a short break from tweeting about AI on the internet to instead discuss “AI in a tuxedo.” He reported enjoying the Agent Economy Gala with the lla

Imaan Sultan posted on October 13, 2026 to thank attendees of the Agent Economy Gala and highlight his collaboration with Sarah Fan in planning the event. He noted his role in proudly representing lla

We benchmarked Gemini 4 Argon, Muse Wonder, and Muse Spark comprehensively on hard document OCR tasks. They're all pretty good! - Muse Spark and Gemini 4 Argon* are SOTA at their respective price poin

least clickbait slop post China has killed the entire vector database industry. They open-sourced TencentDB Agent Memory. It gives any AI agent long-term memory that runs 100% locally. No Pinecone. No

Three events, one award, a very respectable 4th place in hot sauce. Our SF Tech Week: → AI Demo Night w/ @ClickHouse + @artie_labs: @imaanxsultan won best demo → @matissemlk took 4th in the Blazel hot

Kemi posted on October 11, 2026 from San Francisco about attending events during SF Tech Week, highlighting the Agent Economy Gala where she praised @imaanxsultan and @llama_index. She noted a “silico

One of the biggest historical bottlenecks for training specialized models has been curating ground-truth. This is typically a very labor intensive process done with human supervision. Now frontier mod

'a corollary is that information about product quality will become more important and impactful' This feels like the next evolution of SEO/AEO that every product will try to game. Even if agents do th

Mistral OCR is on OpenDocRouter! For its price, it is decent over tables and reading order. It's also blazing fast at p50 1.8s per page We're constantly bringing in new models since OpenDocRouter laun

i'm pulling out my suit for this Huge shoutout to @imaanxsultan and everyone else for organizing! The Agent Economy Gala just maxed out at 400 guests Here’s a breakdown: - 203 founders ($1B+ raised co

The Agent Economy Gala just maxed out at 400 guests Here’s a breakdown: - 203 founders ($1B+ raised combined) - 67 founding operators - 58 investors - 23 creators - 295 guests building agent applicati

These days, you can pretty much solve any task by defining an eval and hillclimbing over it, instead of directly defining the deterministic/agentic workflow to solve it. The data provider companies' e

The team has announced the launch of **LlamaIndex**, an open‑source information‑retrieval library, with its main site listed at **llamaindex.ai**. The announcement was shared on Twitter by Imaan Sulta

What happens when a table contains tables? Usually, a mess. With LlamaParse, it comes out clean. Doc of the Week: Micron’s latest earnings deck. Even with two business units and same row names, LlamaP

LightOn OCR-3 is now available on OpenDocRouter, priced at 0.28 / 1m input and 1.40 / 1m output (it is ~$3.19 / 1k pages on ParseBench). We benchmarked it on ParseBench. It is on the pareto frontier f

Markdown has become a universal representation of information between humans and agents. It preserves core primitives needed to express structure (headings, lists), allows agents to read the informati

OpenDocRouter is basically OpenRouter for document OCR You can compare and use all your favorite OCR models under a single API / billing interface. They range from some of the lightweight/OSS models (

Claude Haiku 5.5 is now available on OpenDocRouter as one of the cheapest models for document parsing. It is roughly $1.2 / 1k pages and does quite well on tables and text reading order compared to ot

Imaan Sultan delivered a well-received presentation on the OpenAI‑style library @llama_index during an AI demo night hosted by @ClickHouseDB, filling the venue. The event's best demonstration award we

On October 7, 2026 Jerry Liu tweeted that “llamaparse” delivers consistently high document‑parsing quality across every dimension. The service can be accessed through cloud.llamaindex.ai. His post cur

OCR is the perfect example of a use case that has been dominated by legacy/brittle systems, and can be solved both accurately and cheaply by applying the right amount of agentic intelligence. A proper

OpenDocRouter is here! https://www.opendocrouter.ai/ Some time ago, I realized LlamaIndex was really good at benchmarking and applying nearly every model to document parsing (see: ParseBench). So, why

The power of OpenDocRouter is already working: Anthropic just dropped Haiku 5.5 and we already have initial benchmark results. I see pretty comparable results to Luna overal. Slightly better at tables

Today I’m excited to introduce OpenDocRouter - a unified API for document parsing with the latest frontier and open-weight models. There are a lot of VLMs and OCR models that can be used for document

Today we're announcing OpenDocRouter: every model for document parsing under one API. There are ~4,000 OCR models on Hugging Face, and the frontier labs ship a new one nearly every month. Whatever's b

You may ask why we’re doing this given that our main focus within LlamaParse (https://cloud.llamaindex.ai/) is building the best frontier models for document parsing and extraction. While we believe o

There's a party on Friday night that most of SF Tech Week will only hear about on Saturday. So, we made a vintage film to announce it. In the 1920s, inventions were rewriting everyday life and nobody

OCR is dead 🪦 Long live agentic OCR! Traditional OCR makes one pass and hands back whatever text it got. Tables get flattened, charts disappear, and multi-column layouts come out scrambled. Nothing ch

I agree that chatgpt/codex has the current best agent interface for deep work. - It unifies all my work (coding/knowledge work) in one interface. Toggling between chatgpt/codex doesn't have explicitly

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 agent

Our new extraction agents are extremely good at reasoning over tables that span multiple pages sometimes a record starts on one page and finishes on the next. extremely common for real world docs (ins

Can your agent read the documents your business runs on? @jerryjliu0 on parsing, search & source citations. World’s Fair 2026 recording: https://www.youtube.com/watch?v=RQi7x-navxU Keep learning with

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 lon

The BEA's new Q2 GDP-by-state was released, but the key data is entirely in an infographic, without a text-layer. LlamaParse's agentic parsing tier understands documents like this by default, and fait

Records that span multiple pages: 85.5% → 96.5%. That's where we most often see customers get stuck with existing tools. With citations on every value, the output is easy to trust. Great work from the

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 ext