Knowledge catalogue
LlamaIndex 发布了一个面向 AI Agent 的文档解析评测基准「ParseBench」 @llama_index 100 种解析方法参与评测（vlm - 67、专用解析器 - 33），2000 页真实企业文档（人工两轮校验），169011 条确定性规则，完全不用 LLM 当裁判，可复现。评测五个维度取无加权平均：表格结构、图表抽取、内容忠实度、格式语义、视觉定位。 https://ww
Recently, Datalab released OmniExtractBench, a benchmark that combines several benchmarks (our own ExtractBench, LongExtractBench, other vendors) to measure structured document quality. The benchmark
what if we...increased the air gap OpenAI's Noam Brown says air-gapping the computers may not stop a misaligned AI, because two air-gapped machines can still talk by running a CPU hot and reading the
with jev, it's nice to see builder energy back on X, reminiscent of the early days of building with LLMs (back when gpt_index/llama_index/langchain first started) before jev, most of the 2026 AI demo
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
The difference with using VLMs for OCR vs. other tasks is that the ratio of output/input tokens is quite high - meaning the model can spend a lot of time writing markdown. Speculative decoding offers
au revoir, Stainless Building production-level SDKs is extremely important for any developer product, and also really hard. This is a fun post from our engineering team on why there's value in tooling
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 und
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 la
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
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
“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 pa
Jerry Liu suggested that users who don’t want to rely on a “fly brain” approach for reading PDFs could instead use an OCR solution called **llamaparse** hosted at *cloud.llamaindex.ai*. The tweet, pos
agreed, one of the biggest bottlenecks right now is my own ability to internalize the information that these models convey the latest models (astra, fable 5.1) are either way too verbose, or try too h
Astra is one of the best models we've tested at parsing complex documents with tables, at 93.2% on ParseBench. So it seems well suited for ad-hoc analysis over table-heavy documents e.g. in finance. T
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 d
Last Friday night, our team hosted a lit event at the US Open 🎾 we gathered a group of enterprise and startup AI leaders + founders together to drink, talk about AI and document parsing, and watch ten
let Astra cook 👩🍳 let LlamaParse read 🤓 Last week we brought LlamaParse to Claude. Now it’s available in ChatGPT, too 🦙 ChatGPT can already read PDFs. But document work gets harder when the informati
Lightning-fast extraction over any document. ICYMI, we launched Extract Turbo last week, that lets you process documents from 1 page to dozens of pages with lightning-fast speed. Come check it out! Ch
One of the main issues with AI document parsing is that because no solution is 100% accuracy, it's hard to tell if a given page is parsed incorrectly: for instance a misaligned table, missing/hallucin
We've trained new models for checkbox parsing ☑️ This lets you convert checkboxes of any size and shape, filled or unfilled, into structured JSON that's suitable for programmatic or agentic use. Use i
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 LlamaP
Last week we brought LlamaParse to Claude. Now it’s available in ChatGPT, too 🦙 ChatGPT can already read PDFs. But document work gets harder when the information you need is buried in messy scans, den
Our agentic extraction harness can extract 54+ fields from an insurance policy with 100% accuracy ✅ coverage limits ✅ nested sublimits ✅ explicit noncoverage This includes a full result review UI wher
holy shit We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics. The proof was produced by a group of agents, using an Open
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 o
correction: the switching costs weren't enough to stop my desire to try out gpt-6 astra i ported over all my skills and conversational context to codex this weekend. planning to use it as my daily dri
We benchmarked GPT-6 Astra on hard document parsing and extraction tasks. It is the best frontier model for one-shotting document extraction over short and medium-sized documents: 📊 97.2% over short d
Does paying 5x more per page actually get you better document extraction? We ran the data to find out. We evaluated 14 frontier systems across 370 enterprise documents, then plotted their accuracy aga
Gemini 3.8 Flash might be maxxed on other benchmarks, but not quite on document parsing. We benchmarked it on ParseBench. It does slightly better on tables + content faithfulness compared to Gemini 3.
Jerry Liu expressed that he is awaiting access to GPT‑6 “Astra” while subscribed to ChatGPT Pro. According to OpenAI’s tweet, GPT‑6 Astra aims to replicate any computer task and deliver results quickl
Unlike other players in the OCR space, we don't block our competitors from accessing our platform. We're also fully committed towards open, reproducible benchmarks for document parsing and extraction
We've massively improved our document parsing capabilities across the board in the past ~3 months. Our LlamaParse cost-effective mode is one of the cheapest OCR solutions out there at <0.4c per page,
Check out the blog here: https://www.llamaindex.ai/blog/introducing-turbo-our-fastest-extraction-tier If you're interested in trying it out, come sign up for a LlamaParse account: https://cloud.llamai
Document extraction just got a new gear. ⚡️ Introducing Turbo mode for Extract, our fastest way yet to pull structured data from documents. It runs roughly 4× faster than our Cost Effective Tier at co
I trust these vibe checks more than I trust most of the benchmark results GPT-6 astra seems more powerful for e2e automation and better at writing (a massively underrated gap for these models). But it
We've benchmarked all the latest frontier models on hard document extraction tasks (with Fable 5.1 and Gemini 3.8 Flash coming soon!). ExtractBench is now live on @kaggle . 5.6 Sol leads the pack, fol
ExtractBench is now live on @Kaggle. It tests schema-guided document extraction on the documents most likely to break downstream agents and workflows, including long record lists, noisy scans, handwri
Fable 5.1 didn't come with document OCR benchmarks, so we benchmarked it on ParseBench: a comprehensive parsing benchmark that's comprised of 2k+ real-world documents across finance, legal, insurance,
Most document OCR solutions have parse (doc->markdown) and extract (doc + schema -> structured output) endpoints. Sometimes you want to extract information from a semi-structured document like a form,
SO excited to share my next chapter: i’m joining @llama_index to lead all things growth marketing, brand, and community! 🦙🩷 when i came along them, it clicked incredibly fast: a team building the solu
There’s generally a massive difference in quality between specialized OCR providers, “simple” open-weight OCR models, and free/OSS solutions. 1️⃣ Specialized OCR models (including LlamaParse) solve fo
LlamaParse is officially a verified connector on Claude! 🦙 Claude is perfectly fine for the occasional text-only PDF. But most of the context your agent needs lives in messy PDFs, spreadsheets, scanne
My conversation with @jerryjliu0. He's building @llama_index: document infrastructure for AI agents, the layer underneath everything models need to work. Did you know he's the guy whose tool half the
Thanks @juliafedorin for a great conversation! Some tidbits from the podcast on the AI space: - We've pivoted from building a RAG framework towards building the document infrastructure for agents - Do
We’re excited to launch the official LlamaParse connector on Claude! Yes Claude can already read PDFs, and it probably works fine for relatively simple queries over relatively simple docs. But if you
at the end of the day, we all have to stand by our company and the values it represents 🙂 * frontier labs will want to own their own application/harness/model e2e. or at least, openai will to start wi
Agentic spreadsheet extraction 📊 is hard to execute well from a price/performance standpoint because your agent needs to ingest a massive quantity of input tokens from a highly complex interface (e.g.
Obligatory plug for static embeddings. Are you using static embeddings in your projects? Would love to hear how people are leveraging them, whether for retrieval and beyond. Static embeddings offer un
PDF parsing is fun because there's an infinite variety of enteprise documents 📑. For each document category, there's a long tail of work to build more precise bounding boxes, confidence scores, and do
static embeddings are extremely fast/cheap compared to dense embeddings, and still quite powerful. one issue is that they lose accuracy over longer text, since the tokens get pooled and averaged late
Most extraction tools treat spreadsheets like PDFs. They flatten the file into text or markdown, then ask a model to infer the original structure. But spreadsheets depend on structure. Headers, formul
We've introduced native, agentic spreadsheet extraction 📊 into LlamaParse. Spreadsheets are a wildly different format from PDFs (or any other document format). They can span arbitrarily many rows/colu
Another special guest is hitting the stage at #FullyConnected26! @jerryjliu0 built @llama_index, the framework thousands of teams use to connect LLMs to their data. Come see Jerry and many more Sept 2
Big shoutout to @perplexity_ai for properly benchmarking document understanding in their Portable Computer release 🔥 They took a subset of our ParseBench benchmark (https://www.parsebench.ai/) and mea
Hosting the 2nd founder dinner in sf on August 31 with @GuangyuRobert at @Fundamental - the team behind @tryshortcutai Agents are increasingly capable of solving tasks for longer task horizons without
I'm actually curious if it's that scary to be in the #1 camp * I still think humans will use software instead only doing work through agent apps. So humans will continue to use SaaS through the UI and
Perplexity.ai published a blog post titled “A Local‑First Agent for Private and Cost‑Effective Knowledge Work” on August 26 2026. The article describes the company’s new local‑first AI agent, which pr
We benchmarked 20+ open-weight models on easy-to-hard document extraction tasks through ExtractBench. The results are all available on @huggingface 🤗 ExtractBench is a schema-guided extraction benchma
We built one of the most comprehensive benchmarks for document extraction, and evaluated it across a lot of different systems: ✅ one-shot frontier VLMs ✅ frontier VLMs + coding agent harnesses ✅ one-s