A blank cell can change the meaning of a forecast. Four times a year, the Fed's 18 top policymakers each put their forecasts on paper: where growth, jobs, inflation, and interest rates are headed. This is September 2026's edition, home of the "dot plot" that markets treat as the Fed tipping its hand. This release is the closest thing to the Fed saying what it plans to do. Most analysts will want to throw this documents to an AI agent, but this messy doc is dense: full of complex tables and charts that hold valuable context. All things that frequently trip up raw LLM APIs. The Fed’s September 2026 projections table includes a 2029 column, but its June comparison row leaves that cell empty. This is a common but silent failure point for document parsers. We parsed page 2 with LlamaParse and checked the displayed GDP median excerpt against the original PDF. All nine numbers matched and the data stays aligned in the returned HTML. Try LlamaParse on a table where headers and missing cells matter. Source:

confidence scores only matter if they help you decide what to automate. for document extraction, that usually means knowing how much work you can safely accept at a given precision target. in our latest post, we look at confidence scoring through that lens, including: ✅️ confidence cutoffs ✅️ precision vs. recall ✅️ score coverage ✅️ score granularity ✅️ human review volume using ExtractBench, we compare how different extraction systems perform after confidence filtering. at a 97% precision target, LlamaParse Agentic Plus reached 66.48% recall on expected fields after filtering. the useful part of a confidence score isn’t the number itself. it’s whether you can use it to control automation and review in production. 👉️ read the full post:

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:

Excited for next Tuesday, Sept 29, and our monthly @daytonaio AI Builders Demo Night in SF! We’re hosting at @WorkOS SF Office in partnership with @llama_index. Join us for an evening of great demos, conversations, and networking with the AI builder community. Event details & RSVP ⬇️

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

The fastest PDF-to-Markdown parser just got faster. ⚡️ With LiteParse v2.14.6, text-based PDFs parse about 25% faster. Across realistic documents, LiteParse processed pages at 2.8ms/page and 1.5× faster than the next-fastest local parser. LiteParse is open source and runs locally in Python, Node.js, Rust, or directly in the browser. Grab v2.14.6 → Bench Docs →

you can find a nice interactive visualization of docjev splitting in action here. it matches luna in being able to split complex document text along the right semantic boundaries

with jev, everyone is understanding the importance of calibrated confidence scores for discrete decision making we've taken that approach one-step further and created grounded confidence scores for general schema-guided document extraction: ✅ this includes primitive types like bool, int, and float. the numbers don't have to be bounded ✅ this also includes free-form text extraction ✅ each extracted value also carries a bounding box directly back into the source document calibrated confidence scores are extremely important for human review. By setting a threshold, you can let a human reviewer audit the lower confidence values while automating the extraction of higher confidence values. If you have needs for large scale doc extraction, come check it out: Sign up to LlamaParse here:

Grounded Confidence is here for Extract! 🦙 When your agents and workflows depend on extracted data, you need to know how accurate that data is. We’ve added confidence scores to give you a better read on extraction accuracy, field by field. Use them to decide which results your app can accept automatically and which need human review. Available on Cost Effective, Agentic, and Agentic Plus. Try it out on your docs ->

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:

Introducing the first in our Parsed by LlamaParse series. We're outlining the stakes of 'getting parsing wrong' in consequential documents. We’re starting with the U.S. Energy Information Administration’s September 2026 Short-Term Energy Outlook, a dense government report covering energy supply, demand, prices, and forecasts. Table 7a alone packs multiple years, quarters, row hierarchies, units, and footnotes into one electricity-industry table. Take 1,186. Parsed correctly, it means electricity sales to ultimate customers in Q3 2026, measured in billion kilowatthours. Parsed incorrectly, it could be assigned to the wrong quarter, metric, or unit , which means the error can flow straight into a dashboard, forecast, alert, or AI application. And the values aren’t the only thing that matters. Footnotes define the data too: “small-scale solar,” for example, refers to systems under one megawatt, not solar generation overall. LlamaParse preserves the structure and context that make document data usable downstream: whether you’re populating a database, updating a dashboard, running forecasting workflows, or building an AI app over complex documents. Source doc here:

It was great to be at Connected Stack last week with founders and builders working on what’s next in enterprise AI. @jerryjliu0 joined the Founder Flash Talks to talk about a problem every enterprise agent eventually runs into: messy, complex documents that general-purpose models struggle to read. Agents are the new knowledge workers, and we are building the document infrastructure for agents. Thanks @trueventures and @GreylockVC for having us! 📸

Ready to learn how to build document processing pipelines for insurance agents? Join LlamaIndex Solutions Architect Abrar Mahi for a webinar on turning insurance documents into structured data for underwriting, policy review, and claims workflows. Using LlamaParse and Extract, we’ll cover: ✅️ Parsing complex accord forms, policy documents and other popular document types in the insurance industry. ✅️ Extracting policy details, property information, and claims history into a defined schema. ✅️ Verifying extracted values with citations and bounding boxes. ✅️ Combining confidence scores with validation rules to decide what proceeds automatically and what needs human review. We’ll bring these steps together in a working pipeline you can adapt to your own workflows. Register:

keeping our SDKs up to date can be a pain. every API change brings another round of updates, tests, and releases. and each SDK should still feel like it was written by someone who actually uses the language. Stainless helped us do that for LlamaParse. It also pushed us to improve the API itself. inconsistent names and schemas become harder to ignore when they show up in the code developers use. with the Stainless team joining Anthropic, George He and Yong Park wrote about what worked, what we learned, and why changing SDK generators takes more care than you might expect. -> thanks to the Stainless team for saving us a lot of SDK work. 👋 au revoir, Stainless

“Just-in-Time” OCR The latest agent harnesses (e.g. Cowork, Codex, Grok) do 2 passes of ad-hoc document processing when executing over a user-uploaded ‘data room’ of documents: 1️⃣ A fast and light pass using a free/OSS doc parsing tool, can be cheaply run over 100+ docs 2️⃣ A “just-in-time” pass using a dedicated OCR tool (like LlamaParse) that does more accurate transcription over a subset of pages. This pattern is common enough that I wanted to give it a name: “Just-in-Time OCR”. It works surprisingly well over a small to medium batch of docs (e.g. 10-100 docs); it is accurate at the expense of cost and latency. It’s not a substitute for large-scale offline indexing and retrieval. The ‘default’ approach for any frontier agent harness is to use an OSS tool like pypdf for the first pass and its native VLM (e.g. Fable 5.1) as the second pass. This is both expensive and lacks accuracy and grounding. If you’re a builder looking to implement this type of harness of a document data room, you can try out our suite of tools: - Liteparse as the first pass (the best/fastest OSS text parser) - LlamaParse as the second pass (most Pareto-efficient, includes grounding) Check out the blog post below!

just-in-time OCR is all the rage. most pipelines parse every page before anyone asks a question. for an agent working through an ad-hoc data room, that's slow, expensive, and most of those pages never get read. the better pattern is just-in-time OCR in two passes: ✅️ LiteParse (free, OSS, Rust, 50+ formats) does a fast layout-aware first pass: spatial text, bounding boxes, headings, tables, and a per-page complexity flag. a full data room in 32 seconds. ✅️ LlamaParse zooms in on only the pages that need it, by page number, and returns cell-level tables, bounding boxes, and confidence scores. the rest fills in the background. pypdf and pdftotext can't do the first pass well. parsing everything up front can't do it cheaply. two passes gets you both. full breakdown with numbers:

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 @wormuth 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:

confidence scores in LlamaParse just got an upgrade 🦸‍♀️ our new high-effort mode provides granular page-level scores with text explanations to help you intimately understand parsing quality of your documents. we even refer back to the original document for an extra check when generating the score. use high-effort only when you need it, at 5 additional credits per page. try it on your docs:

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: