LlamaIndex 🦙(@llama_index)

🦙☀️ It’s a hot Llama summer, and it pays to be a PRO at document parsing. For a limited time, upgra...

LlamaIndex 🦙 (@llama_index) — Thu, 13 Aug 2026 18:18:24 GMT

🦙☀️ It’s a hot Llama summer, and it pays to be a PRO at document parsing. For a limited time, upgrade to the LlamaParse Pro plan and we'll triple your credits:

400K → 1.2M credits in your first month. That's $1,000 (~80k pages) of parsing, free.

No code, applied automatically. Upgrade today 👇️ llamaindex.ai/pricingZP

💬1🔄1❤️11👀3482📊3

⚡ Powered by xgo.ing

Every document extraction system has a perception blind spot. We mapped them. For ExtractBench, we ...

LlamaIndex 🦙 (@llama_index) — Thu, 13 Aug 2026 14:05:11 GMT

Every document extraction system has a perception blind spot. We mapped them.

For ExtractBench, we tested 14 systems on documents that weren't born digital: 1950s regulatory filings, hand-filled tax forms, and pages degraded with fax thresholding, photocopier tone curves, sensor noise, and phone-camera capture.

The failures don't overlap. 

💡 Codex reads scans and handwriting above 93%, then drops to ~80% on rotated or image-only pages. 
💡 Specialized APIs are the exact inverse: fine on rotation and handwriting, 81% on scans
💡 Gemini 3.5 Flash falls from 88.6% to 71.1% the moment a page is scanned.

You benchmark on clean PDFs. Production sends you a shadowed photocopy from 1953.

Our new Extract Tier, Agentic Plus, was the only system with no blind spot: 95.9% / 93.9% / 93.8% across rotated, scanned, and handwritten, a 2-point spread where others swing 10+.

Learn more about ExtractBench 👇️ 

Bllnkd.in/gNm97fXpceB6
Paplnkd.in/euAfScWxkQpF

Your browser does not support the video tag.

🔗 View on Twitter

💬5🔄6❤️19👀3538📊8

⚡ Powered by xgo.ing

The most dangerous document extraction failure isn't a wrong value. It's a missing row that looks li...

LlamaIndex 🦙 (@llama_index) — Wed, 12 Aug 2026 16:20:34 GMT

The most dangerous document extraction failure isn't a wrong value. It's a missing row that looks like nothing is wrong.

We released ExtractBench yesterday: 370 enterprise docs, 14 systems. The hardest test: long-list completeness. An unclaimed-property list with 26,725 rows. A creditor matrix with 8,624 records. A 13F with 3,063 holdings.

Frontier VLMs don't misread these docs, they abandon them. Precision stays high, recall collapses: 8.9–35.8% F1 on the longest documents. Every row they return looks correct, so spot checks pass while most of the document never came back.

Our new Extract tier, Agentic Plus, processes long docs iteratively instead of one pass: 96.1% F1 on long-list tasks, and the only system that holds flat as docs get longer.

Learn more about ExtractBench below👇

Blog:llamaindex.ai/blog/introduci…Y
Paper:arxiv.org/pdf/2607.29677u

Your browser does not support the video tag.

🔗 View on Twitter

💬5🔄5❤️36👀5047📊12

⚡ Powered by xgo.ing

Introducing 𝗘𝘅𝘁𝗿𝗮𝗰𝘁𝗕𝗲𝗻𝗰𝗵: the most comprehensive benchmark for information extraction fr...

LlamaIndex 🦙 (@llama_index) — Tue, 11 Aug 2026 13:00:51 GMT

Introducing 𝗘𝘅𝘁𝗿𝗮𝗰𝘁𝗕𝗲𝗻𝗰𝗵: the most comprehensive benchmark for information extraction from complex enterprise documents. Our applied research team tested:

14 systems — frontier VLMs, coding agents, extraction APIs — on 370 enterprise docs, 4,869 pages, 67 doc types. Zero LLM judges, fully deterministic.

Biggest finding: past 50 pages, commercial VLMs collapse below 35% recall. Precision stays high, but they silently drop most of the table rows.

What is your extraction agent missing? Run ExtractBench to see todllamaindex.ai/blog/introduci…o/5UE8frCgithub.com/run-llama/Extr…o/27vJ36bL54
Hhuggingface.co/datasets/llama…o/oeGlwPjcQh

Your browser does not support the video tag.

🔗 View on Twitter

💬17🔄11❤️80👀30563📊30

⚡ Powered by xgo.ing

SF builders, it's time to ditch your agents and head out on a 🏃 Join us for a run tomorrow with t...

LlamaIndex 🦙 (@llama_index) — Mon, 10 Aug 2026 18:40:26 GMT

SF builders, it's time to ditch your agents and head out on a 🏃 

Join us for a run tomorrow with the Lore community at 6pm at Sue Bierman Park (across from the Ferry Building) for a casual 5k down the Embarcadero. All paces welcome, founders and startup teams especially👇luma.com/4iiiprxj?utm_m…6g

💬6🔄2❤️12👀4434📊7

⚡ Powered by xgo.ing

POV: It's the last day at @Ai4conferences and your: 🧢 colorful hats and stickers are all over the...

LlamaIndex 🦙 (@llama_index) — Thu, 06 Aug 2026 17:20:36 GMT

POV: It's the last day at @Ai4conferences and your:

🧢  colorful hats and stickers are all over the conference floor
👨‍🏫  CEO, @jerryjliu0 , delivered a speech to a full room 
🍽️  executive dinner brought in some of the best and brightest in AI 
👟  feet might hurt and new white shoes have a few scuffs, but still 🥴

💬2🔄1❤️8👀4839📊3

⚡ Powered by xgo.ing

"OCR is just a feature now. Frontier models will eat it." We hear this constantly. The data says ot...

LlamaIndex 🦙 (@llama_index) — Wed, 05 Aug 2026 16:14:40 GMT

"OCR is just a feature now. Frontier models will eat it."

We hear this constantly. The data says otherwise.

Across three GPT generations, parsing accuracy gained ~24 points, while cost per page 4x'd. And the newest frontier models still trail specialized parsers.

Read more below on why the gap persists (and compounds) 👇️llamaindex.ai/blog/document-…b

💬4🔄6❤️34👀9969📊10

⚡ Powered by xgo.ing

Parsing a W-2 into markdown was always the easy part. Getting the fields out was a second pipeline: ...

LlamaIndex 🦙 (@llama_index) — Tue, 04 Aug 2026 16:30:58 GMT

Parsing a W-2 into markdown was always the easy part. Getting the fields out was a second pipeline: define a schema, map the fields, handle the edge cases.

Set processing_options.forms='𝗲𝗻𝗿𝗶𝗰𝗵', and LlamaParse returns a dedicated JSON with field names, values, and checkbox states alongside your standard markdown. No schema. No second API call.

Now available in beta on all paid plans.

Signup for 10k free crelogin.llamaindex.ai/sign-upYFbtG2
developers.api.llamaindex.ai/api/resources/…rv3HTN(resource

💬8🔄4❤️19👀19197📊11

⚡ Powered by xgo.ing

You shouldn't need a vision model to know your PDF has checkboxes. LiteParse can now pull structure...

LlamaIndex 🦙 (@llama_index) — Mon, 03 Aug 2026 13:08:39 GMT

You shouldn't need a vision model to know your PDF has checkboxes.

LiteParse can now pull structured data directly from your PDFs: form field values, checkbox states, annotations, embedded images, vector graphics, tagged document structure, and word-level bounding boxes, all running in ms per page.

For pages that do need a model, new complexity signals tell you why. Scanned pages, multi-column text, tables (ruled and borderless), and dense figures help you route your parsing to the best tools (like LlamaParse!)

Docs 👉️ :developers.llamaindex.ai/liteparse/guid…Udevelopers.llamaindex.ai/liteparse/guid…V

👩‍💻 Try igithub.com/run-llama/pars…8qn

💬6🔄9❤️73👀74346📊27

⚡ Powered by xgo.ing

🦙 is coming coming to Las Vegas for @Ai4Conferences next week (Aug 4–6). Three ways to find us: ...

LlamaIndex 🦙 (@llama_index) — Sat, 01 Aug 2026 03:09:09 GMT

🦙 is coming coming to Las Vegas for @Ai4Conferences next week (Aug 4–6). Three ways to find us:

📍 Booth 1561 on the Expo floor
🎤 @jerryjliu0 will be speaking about unlocking document context for AI agents
🥂 Waitlist for our (very oversubscribed) exec dinner at Tao Bistro (find us on Luma)

Come say hi 👋

💬3🔄2❤️8👀4900📊4

⚡ Powered by xgo.ing

Not every page in your PDF needs the same treatment. A scanned cover, a dense table, a clean text p...

LlamaIndex 🦙 (@llama_index) — Thu, 30 Jul 2026 19:35:05 GMT

Not every page in your PDF needs the same treatment.

A scanned cover, a dense table, a clean text page, a figure-heavy diagram.... most parsing pipelines throw all of them at the same parser, forcing a tradeoff between cost, speed, and accuracy across the whole document.

We built 𝗣𝗮𝗿𝘀𝗲 𝗚𝗮𝘁𝗲𝘄𝗮𝘆 to fix that.

It uses LiteParse's 𝘪𝘴_𝘤𝘰𝘮𝘱𝘭𝘦𝘹 functionality to estimate complexity page-by-page and routes each page to the right tier based on why it's complex (scanned, sparse text, garbled encoding, vector text, embedded images) and how severely. Simple pages get parsed for free, in-process. Genuinely hard pages get routed to more capable LlamaParse tiers. No manual heuristics, no flat one-size-fits-all pipeline.

And it's also available as an MCP server, so your agents can estimate complexity and choose a parsing tier themselves!

The result: you stop paying premium prices for pages that never needed it, without sacrificing accuracy on the ones that dllamaindex.ai/blog/parse-gat…ttps://t.co/K5github.com/run-llama/pars…https://t.co/Gl0Dggv8qn

💬8🔄6❤️67👀42392📊22

⚡ Powered by xgo.ing

Batch parsing used to mean writing API scripts. Now it's a button. 🦙 Parse or extract across up to...

LlamaIndex 🦙 (@llama_index) — Wed, 29 Jul 2026 16:34:08 GMT

Batch parsing used to mean writing API scripts. Now it's a button. 🦙

Parse or extract across up to 10,000 files in one run, straight from the LlamaParse UI. Point it at a folder and go — no code required.

Available now on all paid plans. Bring your files and start parsing �cloud.llamaindex.ai/?utm_medium=so…Dj

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄3❤️17👀11366📊7

⚡ Powered by xgo.ing

Want to run your LlamaParse worker at the edge in minutes? We just released 𝗰𝗿𝗲𝗮𝘁𝗲-...

LlamaIndex 🦙 (@llama_index) — Mon, 27 Jul 2026 16:34:09 GMT

Want to run your LlamaParse worker at the edge in minutes?

We just released 𝗰𝗿𝗲𝗮𝘁𝗲-𝗹𝗹𝗮𝗺𝗮-𝘄𝗼𝗿𝗸𝗲𝗿 🚀

It scaffolds a ready-to-go @Cloudflare Worker that you can configure for Parse, Classify and Extract.

No boilerplate. No setup headaches. Just generate, configure, and deploy.

Get started:
𝘯𝘱𝘮 𝘤𝘳𝘦𝘢𝘵𝘦 @𝘭𝘭𝘢𝘮𝘢𝘪𝘯𝘥𝘦github.com/run-llama/crea…�𝘳

Check out the code:
https://t.co/jsCqbZ7KwX

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄3❤️33👀6296📊8

⚡ Powered by xgo.ing

As of LiteParse v2.8.0, image → PDF conversion no longer depends on ImageMagick. Instead, it’s now h...

LlamaIndex 🦙 (@llama_index) — Fri, 24 Jul 2026 17:30:07 GMT

As of LiteParse v2.8.0, image → PDF conversion no longer depends on ImageMagick. Instead, it’s now handled natively in Rust 🦀

The result? Conversion is now 1.2× to 7.2× faster, depending on the image format⚡️ 

But the bigger win is what this enables: we’re one step closer to making LiteParse fully self-contained, with zero external system dependencies 🚀

If you’re using LiteParse, make sure to upgrade and to check out the project on GitHub �github.com/run-llama/lite…CQ0

Your browser does not support the video tag.

🔗 View on Twitter

💬4🔄7❤️57👀16397📊19

⚡ Powered by xgo.ing

You asked, we delivered! 🚀 Expanding our developer toolkit with: 🐹 Go SDK 🏢 Java SDK >_ CLI ...

LlamaIndex 🦙 (@llama_index) — Thu, 23 Jul 2026 17:46:28 GMT

You asked, we delivered!  🚀

Expanding our developer toolkit with: 
🐹 Go SDK
🏢 Java SDK
>_  CLI

Parse a document from Go or Java in a few lines, or straight from your terminal.
🦙 Grab an API key and start parsing today!

Dodevelopers.llamaindex.ai/llamaparse4OyE
Start frcloud.llamaindex.ai/?utm_medium=so…1ip6

💬5🔄1❤️19👀4761📊7

⚡ Powered by xgo.ing

Your agentic workflows are only as good as the context you feed them. In finance, that context is s...

LlamaIndex 🦙 (@llama_index) — Wed, 22 Jul 2026 18:09:57 GMT

Your agentic workflows are only as good as the context you feed them.

In finance, that context is stuck inside your messiest documents: dense tables, footnoted adjustments, and the details buried in the notes that actually carry the risk. Most tooling flattens exactly the structure that matters, so what reaches your systems is already degraded.

On July 30, join Harsha, a Solution Architect on our team, as he shows how to turn a real, dense financial document into clean, structured, decision-ready context.

On the agenda:
→ Tables and footnotes that stay intact, not flattened into text
→ Extracted figures traceable to the exact source page
→ Values checked against your rules, with exceptions surfaced

Thursday, July 30 · 9:00 AM PT / 12:00 PM ET 
Save your seat: watch.getcontrast.io/register/llama…

💬1🔄4❤️11👀6064📊4

⚡ Powered by xgo.ing

The team flew into SF for a week onsite. 🌉 2x'd in size since we last did this — first time this m...

LlamaIndex 🦙 (@llama_index) — Tue, 21 Jul 2026 17:55:20 GMT

The team flew into SF for a week onsite. 🌉

2x'd in size since we last did this — first time this many of us have been in the same room.

The recap:
🧠 Locked in our roadmap for AI agent document infra
🎨 Spraypainting, Topgolf, soccer, & escape rooms
⚽️ Caught a few World Cup matches between sessions
🍗 Raising Cane's for lunch
🎯 Darts + way too many dinners across the city

Ready for Q3.

💬1🔄1❤️13👀8023📊3

⚡ Powered by xgo.ing

We're kicking off a founder dinner series in SF. First one's July 28 - one table, 16 seats, invite-o...

LlamaIndex 🦙 (@llama_index) — Mon, 20 Jul 2026 17:00:06 GMT

We're kicking off a founder dinner series in SF. First one's July 28 - one table, 16 seats, invite-only, co-hosted by @jerryjliu0 and @dexhorthy. Topic is loop engineering.

A room of founders and CTOs building agents in production, comparing notes on what holds up.

💬6🔄1❤️12👀4455📊7

⚡ Powered by xgo.ing

Teaming up with https://t.co/IBgKPZBnJY for their Agentic Hackathon at the AWS Builder Loft in SF, J...

LlamaIndex 🦙 (@llama_index) — Fri, 17 Jul 2026 17:00:02 GMT

Teaming up with You.com for their Agentic Hackathon at the AWS Builder Loft in SF, July 24th. One day to build agents on live web data - real-time intelligence, deep research, or multi-agent systems - then demo to the judges.

RSVP here: luma.com/youdotcom-agen…

💬5🔄5❤️15👀4921📊7

⚡ Powered by xgo.ing

Document processing pipelines are often made up of multiple services: parsing → chunking → embedding...

LlamaIndex 🦙 (@llama_index) — Thu, 16 Jul 2026 16:25:07 GMT

Document processing pipelines are often made up of multiple services: parsing → chunking → embeddings → storage.

Until now, LiteParse was only available over REST. That works well for browsers and simple integrations, but it’s not always the best fit for service-to-service communication.

Today we’re introducing liteparse-grpc.

With  @𝘭𝘭𝘢𝘮𝘢𝘪𝘯𝘥𝘦𝘹/𝘭𝘪𝘵𝘦𝘱𝘢𝘳𝘴𝘦-𝘨𝘳𝘱𝘤 (npm) or the  𝘨𝘩𝘤𝘳.𝘪𝘰/𝘳𝘶𝘯-𝘭𝘭𝘢𝘮𝘢/𝘭𝘪𝘵𝘦𝘱𝘢𝘳𝘴𝘦-𝘨𝘳𝘱𝘤 Docker image, you can run LiteParse as a gRPC service and:

📄 Parse PDFs, Office documents, and images into JSON, text, or Markdown
📸 Render PDF pages as screenshots
📊 Estimate document complexity and whether OCR is needed

The package also includes a CLI client for testing, generated TypeScript client stubs and the protobuf definitions, so you can generate clients for Python, Go, Java, or any other language supported by 𝘱𝘳𝘰𝘵𝘰𝘤

The REST server isn’t going anywhere, this is simply another interface for teams building polyglot, microserllamaindex.ai/blog/introduci…elines.

📖github.com/run-llama/lite…n: https://t.co/iAIBoXzhEH
💻 GitHub: https://t.co/K0d8XVE7Rc

💬1🔄6❤️43👀9880📊12

⚡ Powered by xgo.ing

We're part of the Amazon Web Services (AWS) AI Builder Lab in New York on Friday, July 24 - a Clash ...

LlamaIndex 🦙 (@llama_index) — Wed, 15 Jul 2026 17:00:20 GMT

We're part of the Amazon Web Services (AWS) AI Builder Lab in New York on Friday, July 24 - a Clash of Agents competition with OpenAI, LangChain, HiddenLayer, Protopia AI, Fiddler AI, and Coder.

One day of building multi-agent systems on Bedrock, hands-on the whole way - partner challenges, a live leaderboard, and the top builders walk away with AirPods and Meta glasses. No panels, no name-tag mingling.

Capped at 200 developers and free to RSVP. If you're building agents in New York, grab a spot: aicamp.ai/event/eventdet…

💬2🔄2❤️9👀3313📊4

⚡ Powered by xgo.ing

Your extraction schema is now a conversation away. ⁣ 📄 Upload a doc — the agent drafts the schema f...

LlamaIndex 🦙 (@llama_index) — Tue, 14 Jul 2026 21:51:07 GMT

Your extraction schema is now a conversation away.
⁣
📄 Upload a doc — the agent drafts the schema from it⁣
💬 Want changes? Just ask⁣
📚 Or grab a template and go⁣
⁣
Writing JSON Schema by hand? That's over.⁣
⁣
Conversational Extract is live in LlamaParse. Try it now cloud.llamaindex.ai/?utm_medium=so…ip6

Your browser does not support the video tag.

🔗 View on Twitter

💬3🔄7❤️20👀17247📊8

⚡ Powered by xgo.ing

Co-hosting 'Swap and Pitch Night' this Thursday in SF with @tembo, @clerk, and @autonomaai. Pitch ...

LlamaIndex 🦙 (@llama_index) — Tue, 14 Jul 2026 17:00:21 GMT

Co-hosting 'Swap and Pitch Night' this Thursday in SF with @tembo, @clerk, and @autonomaai. 

Pitch night where founders pitch each other's startups. Good test of whether you actually listen, and sometimes someone pitches your startup better than you do.

855 Brannan, 6 to 8:30pm. 

RSVP here: luma.com/swapandpitch

💬3🔄1❤️8👀8264📊4

⚡ Powered by xgo.ing

We eat docs🫢

LlamaIndex 🦙 (@llama_index) — Tue, 14 Jul 2026 14:40:13 GMT

We eat docs🫢

💬0🔄1❤️12👀6700📊2

⚡ Powered by xgo.ing

Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent, without havi...

LlamaIndex 🦙 (@llama_index) — Mon, 13 Jul 2026 16:08:09 GMT

Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent, without having use CLIs or open the browser?

We built exactly that.

Using @TauriAp ps, with a Rust backend powered by LiteParse and a React frontend, we created a cross-platform desktop app that lets you:

• Drag and drop PDFs
• Convert them into clean Markdown
• Preview page screenshots with extracted bounding boxes overlaid for easy inspection

It's a simple way to understand your document's structure and verify the parsing results before handing them off to an LLM.

Check out the demo below! 👇

GitHub:github.com/run-llama/lite…W
Get started with LiteParse:developers.llamaindex.ai/liteparse/S

Your browser does not support the video tag.

🔗 View on Twitter

💬7🔄6❤️52👀21128📊25

⚡ Powered by xgo.ing

@OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in d...

LlamaIndex 🦙 (@llama_index) — Thu, 09 Jul 2026 22:48:21 GMT

@OpenAI  released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in document understanding. The new family of models continues to excel at reading text and tables, but continues to struggle with charts and layout. 

What's most interesting is that Luna is about 6 x cheaper than Sol and only results in minor degradations across all ParseBench metrics, showing that an increase in reasoning tokens doesn't always result in a commensurate improvement in visual understanding.

💬4🔄1❤️23👀23011📊7

⚡ Powered by xgo.ing

@OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in d...

LlamaIndex 🦙 (@llama_index) — Thu, 09 Jul 2026 22:47:13 GMT

@OpenAI  released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in document understanding. The new family of models continues to excel at reading text and tables, but continues to struggle with charts and layout. 

What's most interesting is that Luna is about 6 x cheaper than Sol and only results in minor degradations across all ParseBench metrics, showing that an increase in reasoning tokens doesn't always result in a commensurate improvement in visual understanding.

💬1🔄4❤️14👀2912📊3

⚡ Powered by xgo.ing

Low user caps in LlamaParse? Gone.🎉 Every plan — Free through Pro — now unlocks up to 100 team mem...

LlamaIndex 🦙 (@llama_index) — Thu, 09 Jul 2026 17:12:52 GMT

Low user caps in LlamaParse? Gone.🎉

Every plan — Free through Pro — now unlocks up to 100 team members.
No more picking who gets a seat. No more shared logins. No more upgrading just to invite a teammate.

Whether you're a two-person startup on the free tier or a team scaling on Pro, your whole team can now build together, same workspace, same projects, every tier.

True team collaboration is now the default, not a premium feature.

Signup for free and invite your team today -->cloud.llamaindex.ai/?utm_medium=so…6

💬3🔄1❤️11👀3656📊4

⚡ Powered by xgo.ing

Introducing: Granular job tracking and cost attribution in LlamaParse 🦙 Parsing thousands of page...

LlamaIndex 🦙 (@llama_index) — Wed, 08 Jul 2026 21:13:09 GMT

Introducing: Granular job tracking and cost attribution in LlamaParse 🦙 

Parsing thousands of pages a day is a lot to manage. Engineering teams need to have a pulse on what's running, who ran it, and what it costs. Our latest tagging system make it easier to track and attribute usage and costs at scale in LlamaParse:

🏷️ 𝗨𝘀𝗲𝗿 𝗠𝗲𝘁𝗮𝗱𝗮𝘁𝗮: Always know where every job belongs. Attach your own labels to any parse job and they come back on every response.

🏷️ 𝗨𝘀𝗮𝗴𝗲 𝗧𝗮𝗴𝘀: Know what your document processing actually costs, by project and by team. Tag your requests, and your spend becomes filterable by those tags: by customer, by team, by product line, whatever makes sense for your org.

🏷️ 𝗦𝗶𝗴𝗻𝗲𝗱 𝗪𝗲𝗯𝗵𝗼𝗼𝗸𝘀: Trust every callback you receive. Every webhook delivery now includes an HMAC signature, so your systems can verify a callback really came from us before acting on it.

💬3🔄1❤️22👀9714📊6

⚡ Powered by xgo.ing

We've rolled out improvements to LlamaParse Cost Optimizer. Our intelligent tier routing now more ...

LlamaIndex 🦙 (@llama_index) — Tue, 07 Jul 2026 20:27:42 GMT

We've rolled out improvements to LlamaParse Cost Optimizer. 

Our intelligent tier routing now more reliably ensures you always strike the right balance between cost and accuracy when processing large documents. Simple pages default to our cost-effective tier, complex pages are still processed by our higher accuracy and higher cost agentic and agentic plus tiers.

Only pay for the quality each page actually needs.

Live now for all customers.

💬2🔄2❤️15👀10261📊5

⚡ Powered by xgo.ing

Most agentic retrieval demos assume clean, well-structured documents. Enterprise reality is often di...

LlamaIndex 🦙 (@llama_index) — Mon, 06 Jul 2026 16:35:50 GMT

Most agentic retrieval demos assume clean, well-structured documents. Enterprise reality is often different, consisting of messy PDFs where critical information is buried across tables, figures, and complex layouts.

That’s why we teamed up with @lancedb to explore how LiteParse (our lightning-fast parser) combined with LanceDB’s native multimodal storage can improve retrieval quality and agent response accuracy.

By separating PDFs into multiple information layers - pages (text + screenshots + embeddings), chunks, and extracted assets - and storing them in LanceDB for fast multimodal retrieval, we built a hybrid pipeline that unlocks information traditional RAG systems often miss.

Instead of relying on chunk-level retrieval alone, agents can retrieve and reason across pages, chunks, and visual assets, making complex enterprise PDFs far more accessible.

The result is a significantly stronger retrieval foundation for agentic workflows.

📖 Read the full breakdown in the blog post:lancedb.com/blog/from-mess…h
💻 Explore the full implementation on GitHubgithub.com/lancedb/litepa…Rx

💬4🔄9❤️37👀5706📊13

⚡ Powered by xgo.ing

The team at @vercel recently released the Eve agent framework, so we built a template that integrate...

LlamaIndex 🦙 (@llama_index) — Fri, 03 Jul 2026 17:30:11 GMT

The team at @vercel recently released the Eve agent framework, so we built a template that integrates LiteParse with it🦙 

The template provides a set of read-only filesystem tools that let Eve resolve paths, list directories, and read text-based files. We then pair those with LiteParse, which parses files from their source and returns clean, structured Markdown⚙️ 

Finally, we equipped the agent with detailed instructions on when and how to combine these tools effectively, giving it a reliable workflow for navigating and understanding document collections out of the box📁 

The result is a solid starting point that you can extend with your own channels, tools, and skills🔧 

Check it ougithub.com/run-llama/eve-…3E0

Your browser does not support the video tag.

🔗 View on Twitter

💬7🔄3❤️41👀32360📊15

⚡ Powered by xgo.ing

LiteParse runs anywhere, including inside agent runtimes. To prove it, we built an email processing ...

LlamaIndex 🦙 (@llama_index) — Thu, 02 Jul 2026 16:08:07 GMT

LiteParse runs anywhere, including inside agent runtimes.
To prove it, we built an email processing assistant using @flueai (the agentic framework by @astrodotbuild), @resend webhooks, and @tursodatabase for persistence📩 

Here's how it works:
→ Send an email
→ The agent reads its corpus, fetches attachments, and parses any PDFs with LiteParse
→ It summarizes the message and drafts a reply for you

This integration is an example of how parsing tools shouldn't just handle files, they should deepen what agents understand about them, augmenting their context📂 

👩‍💻 Code hegithub.com/run-llama/flue…Luy4

Your browser does not support the video tag.

🔗 View on Twitter

💬6🔄6❤️40👀7809📊15

⚡ Powered by xgo.ing

Game. Match. That's a wrap on the inaugural Agent Open 🦙🌤️🏓 Hundreds of AI builders, 64 matches,...

LlamaIndex 🦙 (@llama_index) — Wed, 01 Jul 2026 21:01:19 GMT

Game. Match. That's a wrap on the inaugural Agent Open 🦙🌤️🏓

Hundreds of AI builders, 64 matches, 7 partners, 2 courts. 
No dink shots or demos, just backhands and hot takes.

Thanks to our partners @BrainTrust, @Modal, @turbopuffer, @p0, @Browserbase, and @Cursor_ai for everyone's time and sweat spent to ace yesterday's event.

💬1🔄1❤️22👀4075📊3

⚡ Powered by xgo.ing

Agentic retrieval is changing the way retrieval-augmented applications are built, especially in doma...

LlamaIndex 🦙 (@llama_index) — Wed, 01 Jul 2026 17:30:14 GMT

Agentic retrieval is changing the way retrieval-augmented applications are built, especially in domains like legal and fintech, where agents need to autonomously navigate large, evolving knowledge bases.

That’s exactly the use case we designed Index v2 for.

To demonstrate what’s possible, we built legal-kb, a reference application that integrates Index v2 into an agentic knowledge automation workflow. It uses Index v2 as the underlying knowledge base and exposes its retrieve, read, grep, and find APIs as tools that an AI agent can use to autonomously explore and reason over your documents.

With legal-kb, you get:

📚 Project-scoped knowledge bases for agent-powered chat
📖 Visual citations directly in agent responses
🌿 Version control for your knowledge base
📦 Data export capabilities

Try it olegal-kb.devMEGx
Explore the cogithub.com/run-llama/lega…KZdn
Get started with LlamaParcloud.llamaindex.ai/signup1Brf

Your browser does not support the video tag.

🔗 View on Twitter

💬16🔄12❤️106👀67343📊49

⚡ Powered by xgo.ing

Doors are open at Agent Open, right next door to AI Engineer Two courts, blue sky, no fog (a San Fr...

LlamaIndex 🦙 (@llama_index) — Tue, 30 Jun 2026 22:35:35 GMT

Doors are open at Agent Open, right next door to AI Engineer 
Two courts, blue sky, no fog (a San Francisco miracle) 🌤️

This is the perfect walk-over window, we are just 3 minutes from Moscone.

Don't miss the State of AI panel at 5PM, tournament + party til 10PM.

RSVP:luma.com/the-agent-open…c

Your browser does not support the video tag.

🔗 View on Twitter

💬3🔄2❤️20👀4886📊5

⚡ Powered by xgo.ing

We just made it a lot easier for AI agents to work with your documents. LlamaParse MCP now does mor...

LlamaIndex 🦙 (@llama_index) — Tue, 30 Jun 2026 16:08:02 GMT

We just made it a lot easier for AI agents to work with your documents.

LlamaParse MCP now does more than parse or classify files: it can pull structured data out of contracts, invoices, and reports automatically, and give agents direct access to your knowledge base (PDFs, Office docs, images, and more) so they can search, read, and retrieve information just like a human would.

We also reorganized everything into focused, purpose-built tools: whether you're classifying documents, extracting data, or building search over your company's files, agents can do it faster, more reliably, and in parallel.

This allows for smarter, more capable AI workflows for anyone working with documents at scale.

Curious to try it out? 
Get started now with the LlamaParse Platform → cloud.llamaindex.ai/?utm_medium=so…
Blog post: llamaindex.ai/blog/extending…
Take a look at the GitHub repository → github.com/run-llama/mcp-…

💬4🔄9❤️65👀6439📊20

⚡ Powered by xgo.ing

Semantic search alone doesn't cut it. Neither does brute-force grep. Agents need both. Today we're ...

LlamaIndex 🦙 (@llama_index) — Mon, 29 Jun 2026 18:05:29 GMT

Semantic search alone doesn't cut it. Neither does brute-force grep.
Agents need both.

Today we're shipping the Retrieval Harness in LlamaParse Index: semantic search, server-side grep, and file-level navigation working together in a single agent reasoning loop. 🦙🌤️

Grep a file, list what's in an index, read past a chunk boundary,
run hybrid search with reranking — all as native agent tools.

Now in beta across all paid tiers. Full breakdown in the blog 👇

Learn Morllamaindex.ai/blog/announcin…dOI

Your browser does not support the video tag.

🔗 View on Twitter

💬5🔄6❤️68👀29314📊23

⚡ Powered by xgo.ing

We're all over AI Engineer World's Fair on June 29 to July 2. 🦙 📍Visit us at booth L-G47. LlamaPa...

LlamaIndex 🦙 (@llama_index) — Mon, 29 Jun 2026 17:30:02 GMT

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)
RSluma.com/the-agent-open…Y1vX8l

💬2🔄5❤️15👀3301📊5

⚡ Powered by xgo.ing

The @n8n_io node for the LlamaParse Platform is now an officially verified community node, as part o...

LlamaIndex 🦙 (@llama_index) — Fri, 26 Jun 2026 16:05:04 GMT

The @n8n_io node for the LlamaParse Platform is now an officially verified community node, as part of a broader partnership with n8n to bring cutting-edge document intelligence to the low-code and no-code world🚀 

The new version of the node brings together document parsing, classification, extraction, splitting, and retrieval in one place, all wired to a single LlamaParse API credential🦙
 
Each resource can now also act as a callable tool inside an n8n AI Agent: so instead of building static pipelines, you can let the agent decide when to retrieve context, parse a file, or extract structured data based on what the user actually needs🤖 

A few workflows worth highlighting: routing documents by type before extracting structured fields, plugging retrieval directly into an agent backed by your own knowledge base, and running parse outputs through different tiers side by side to find the right balance between accuracy and cost🔃 

If you're already using n8n, install it directly from your workflow canvas by searching 𝘓𝘭𝘢𝘮𝘢𝘗𝘢𝘳𝘴𝘦 𝘗𝘭𝘢𝘵𝘧𝘰𝘳𝘮 and give it a try!🔧 

📚️ Full breallamaindex.ai/blog/bring-you…https://t.co/8LJB80HCJ8

💬5🔄7❤️41👀12173📊14

⚡ Powered by xgo.ing

We built LiteParse, the fastest document parsing solution on the planet and made it open source. An...

LlamaIndex 🦙 (@llama_index) — Thu, 25 Jun 2026 16:26:37 GMT

We built LiteParse, the fastest document parsing solution on the planet and made it open source.

And it just hit 10k github stars. 🦙 
Fast to run. Fast to love.

Thanks for building with us. If you haven't tried it already, repo at:github.com/run-llama/lite…q

💬5🔄4❤️39👀22007📊14

⚡ Powered by xgo.ing

Bring your hot takes and your drop shots.🔥 Next week, we're co-hosting The Agent Open: an afternoo...

LlamaIndex 🦙 (@llama_index) — Mon, 22 Jun 2026 20:29:01 GMT

Bring your hot takes and your drop shots.🔥

Next week, we're co-hosting The Agent Open: an afternoon of pickleball, food, drinks, and industry-leading speakers who ace their code and commit to their serves. 🏓

Catch our co-founder and CEO, Jerry Liu after Day 2 of AIE World's Fair on a panel moderated by Gergely Orosz (𝘛𝘩𝘦 𝘗𝘳𝘢𝘨𝘮𝘢𝘵𝘪𝘤 𝘌𝘯𝘨𝘪𝘯𝘦𝘦𝘳). Get ready for a real conversation about the Future of AI and learn how to avoid the hype, stay out of the kitchen, and strategically position your team for what's next.

🗓️ Tuesday, June 30th @ 5:00pm PT
📍 San Francisco (register for the address)
🦙 Co-hosted by LlamaIndex with Braintrust, turbopuffer, Cursor, Parallel Web Systems, Modal, and Browserbase

Come for the panel, stay for the chaluma.com/the-agent-open…: #AIEngineeringG#AIAgents#DocumentAIing #AIAgents#DocumentAI

💬4🔄2❤️7👀9964📊5

⚡ Powered by xgo.ing

LiteParse v2.1 is here, and its bringing the fastest markdown output possible. In this release, we ...

LlamaIndex 🦙 (@llama_index) — Thu, 18 Jun 2026 17:17:04 GMT

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-…

Your browser does not support the video tag.

🔗 View on Twitter

💬14🔄30❤️168👀267720📊64

⚡ Powered by xgo.ing

~90% of enterprise data is unstructured, locked in the documents that power the majority of knowledg...

LlamaIndex 🦙 (@llama_index) — Thu, 18 Jun 2026 15:10:54 GMT

~90% of enterprise data is unstructured, locked in the documents that power the majority of knowledge work. The next massive frontier? AI agents that can deeply understand, reason over, and edit these files at scale to automate entire workflows.

Our CEO, Jerry Liu is speaking at @Databricks#DataAISummit today on the core advances in OCR and agent orchestration making this a reality.

📍 Yerba Buena Salon 7 · 10:20 AM
🔗 Link to Jerry's sessiondataaisummit.databricks.com/flow/db/dais20…MB

💬7🔄5❤️19👀6144📊11

⚡ Powered by xgo.ing

Vector databases or pure grep? Teams are split on the right retrieval architecture for agents. ⁣ ⁣ T...

LlamaIndex 🦙 (@llama_index) — Wed, 17 Jun 2026 18:20:40 GMT

Vector databases or pure grep? Teams are split on the right retrieval architecture for agents. ⁣
⁣
The reality? You need both. Semantic search for a fast first pass; grep and file reads for surgical precision when top-k chunks cut off mid-answer. ⁣
⁣
On June 29, our Head of Engineering George He goes under the hood on the architecture decisions and dead ends behind building this harness into LlamaParse Index.⁣
⁣
 Register here : landing.llamaindex.ai/retrieval-harn…

💬9🔄9❤️56👀12828📊19

⚡ Powered by xgo.ing

Our CEO Jerry Liu is joining founders from LangChain, CrewAI, and others at @Databricks #DataAISummi...

LlamaIndex 🦙 (@llama_index) — Wed, 17 Jun 2026 16:32:57 GMT

Our CEO Jerry Liu is joining founders from LangChain, CrewAI, and others at @Databricks#DataAISummit today for a panel on the The Agentic Stack — what the stack looks like, where it's headed, and what happens when agents become the primary consumers of infrastructure, not humans.

Panel begins at 11.30 am, see you there. 👋

💬7🔄3❤️15👀2981📊8

⚡ Powered by xgo.ing

How much can good documentation save an AI agent in cost and time? Turns out, a lot. We built a cus...

LlamaIndex 🦙 (@llama_index) — Tue, 16 Jun 2026 16:08:02 GMT

How much can good documentation save an AI agent in cost and time? Turns out, a lot.

We built a custom skill that teaches Claude how to parse PDFs more efficiently, then used real usage traces to find where it was wasting time and money (re-reading the same file over and over, taking unnecessary "screenshots" of pages, etc.)

After a few rounds of fixes based on what we observed, the results vs. just having Claude read PDFs the default way:
→ 37% lower cost per question
→ Better answer quality across the board
→ Fewer wasted steps

The big takeaway: look at what an agent actually leaves in its traces, and fix bottlenecks from there.

Full case study 👉️llamaindex.ai/blog/building-…m
Benchmark code 👉github.com/run-llama/benc…m5

💬9🔄7❤️37👀13638📊18

⚡ Powered by xgo.ing

Contracts are where business commitments live, but most organizations still manage them manually, se...

LlamaIndex 🦙 (@llama_index) — Mon, 15 Jun 2026 16:08:02 GMT

Contracts are where business commitments live, but most organizations still manage them manually, searching PDFs for renewal dates, chasing down payment terms, and hoping nothing slips through the cracks.

The problem isn't just volume. Legacy OCR treats contracts like flat text, unable to interpret what it reads: the same payment term appears under three different headings, renewal conditions are buried mid-paragraph, and termination clauses span multiple amendments.

We wrote up how LlamaParse solves this by:
✅️ Preserving document hierarchy
✅️  Using semantic reasoning to identify key fields regardless of how they're drafted
✅️ Mapping everything into validated, schema-aligned output

Ultimately, it transforms contracts from flat PDF text into structured data your downstream systems can actually use.

Read the full breakdown here: 
llamaindex.ai/blog/extract-c…

💬5🔄4❤️30👀10773📊12

⚡ Powered by xgo.ing

We're headed back to @Databricks #DataAISummit to parse your PDFs next week 🦙 Catch our co-founder...

LlamaIndex 🦙 (@llama_index) — Fri, 12 Jun 2026 19:44:41 GMT

We're headed back to @Databricks#DataAISummit to parse your PDFs next week 🦙

Catch our co-founder & CEO @jerryjliu0  twice:

📄 Automating Document Work with Long-Horizon AI Agents databricks.com/dataaisummit/s…gT
🧱 The Agentic Stack: founder panel with LangChain, CrewAI, Agno + Databricksdatabricks.com/dataaisummit/s…Xzc

Then swing by booth #137, talk document agents, see LlamaParse, leave with 🔥 swag.

San Francisco, June 15–18. See you there. 👋

💬7🔄4❤️30👀4543📊10

⚡ Powered by xgo.ing

Day 0 Anthropic Fable 5 in ParseBench: We tested the model's advancements when it comes to document ...

LlamaIndex 🦙 (@llama_index) — Wed, 10 Jun 2026 00:18:06 GMT

Day 0 Anthropic Fable 5 in ParseBench: We tested the model's advancements when it comes to document understanding. The model clearly peaks when it comes to adherence to the original text:

📃 Content faithfulness: 90.02% vs 86.19% (Gemini 3 Flash) and 86.81% (GPT-5.5)
🔢 Semantic formatting: 72.62% vs 58.35% and 60.12%, a 12+ point lead

These are two of the most important metrics for SOTA document understanding: does the output preserve what the document actually says, and does it preserve formatting that carries meaning? 

But ... it's not a sweep there continues to be a lot of alpha in unlocking document understanding for frontier models.

Full results below 👇

💬15🔄7❤️55👀40764📊22

LlamaIndex 🦙(@llama_index)

🦙☀️ It’s a hot Llama summer, and it pays to be a PRO at document parsing. For a limited time, upgra...

Every document extraction system has a perception blind spot. We mapped them. For ExtractBench, we ...

The most dangerous document extraction failure isn't a wrong value. It's a missing row that looks li...

Introducing 𝗘𝘅𝘁𝗿𝗮𝗰𝘁𝗕𝗲𝗻𝗰𝗵: the most comprehensive benchmark for information extraction fr...

SF builders, it's time to ditch your agents and head out on a 🏃 Join us for a run tomorrow with t...

POV: It's the last day at @Ai4conferences and your: 🧢 colorful hats and stickers are all over the...

"OCR is just a feature now. Frontier models will eat it." We hear this constantly. The data says ot...

Parsing a W-2 into markdown was always the easy part. Getting the fields out was a second pipeline: ...

You shouldn't need a vision model to know your PDF has checkboxes. LiteParse can now pull structure...

🦙 is coming coming to Las Vegas for @Ai4Conferences next week (Aug 4–6). Three ways to find us: ...

Not every page in your PDF needs the same treatment. A scanned cover, a dense table, a clean text p...

Batch parsing used to mean writing API scripts. Now it's a button. 🦙 Parse or extract across up to...

Want to run your LlamaParse worker at the edge in minutes? We just released 𝗰𝗿𝗲𝗮𝘁𝗲-...

As of LiteParse v2.8.0, image → PDF conversion no longer depends on ImageMagick. Instead, it’s now h...

You asked, we delivered! 🚀 Expanding our developer toolkit with: 🐹 Go SDK 🏢 Java SDK >_ CLI ...

Your agentic workflows are only as good as the context you feed them. In finance, that context is s...

The team flew into SF for a week onsite. 🌉 2x'd in size since we last did this — first time this m...

We're kicking off a founder dinner series in SF. First one's July 28 - one table, 16 seats, invite-o...

Teaming up with https://t.co/IBgKPZBnJY for their Agentic Hackathon at the AWS Builder Loft in SF, J...

Document processing pipelines are often made up of multiple services: parsing → chunking → embedding...

We're part of the Amazon Web Services (AWS) AI Builder Lab in New York on Friday, July 24 - a Clash ...

Your extraction schema is now a conversation away. ⁣ 📄 Upload a doc — the agent drafts the schema f...

Co-hosting 'Swap and Pitch Night' this Thursday in SF with @tembo, @clerk, and @autonomaai. Pitch ...

We eat docs🫢

Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent, without havi...

@OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in d...

@OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in d...

Low user caps in LlamaParse? Gone.🎉 Every plan — Free through Pro — now unlocks up to 100 team mem...

Introducing: Granular job tracking and cost attribution in LlamaParse 🦙 Parsing thousands of page...

We've rolled out improvements to LlamaParse Cost Optimizer. Our intelligent tier routing now more ...

Most agentic retrieval demos assume clean, well-structured documents. Enterprise reality is often di...

The team at @vercel recently released the Eve agent framework, so we built a template that integrate...

LiteParse runs anywhere, including inside agent runtimes. To prove it, we built an email processing ...

Game. Match. That's a wrap on the inaugural Agent Open 🦙🌤️🏓 Hundreds of AI builders, 64 matches,...

Agentic retrieval is changing the way retrieval-augmented applications are built, especially in doma...

Doors are open at Agent Open, right next door to AI Engineer Two courts, blue sky, no fog (a San Fr...

We just made it a lot easier for AI agents to work with your documents. LlamaParse MCP now does mor...

Semantic search alone doesn't cut it. Neither does brute-force grep. Agents need both. Today we're ...

We're all over AI Engineer World's Fair on June 29 to July 2. 🦙 📍Visit us at booth L-G47. LlamaPa...

The @n8n_io node for the LlamaParse Platform is now an officially verified community node, as part o...

We built LiteParse, the fastest document parsing solution on the planet and made it open source. An...

Bring your hot takes and your drop shots.🔥 Next week, we're co-hosting The Agent Open: an afternoo...

LiteParse v2.1 is here, and its bringing the fastest markdown output possible. In this release, we ...

~90% of enterprise data is unstructured, locked in the documents that power the majority of knowledg...

Vector databases or pure grep? Teams are split on the right retrieval architecture for agents. ⁣ ⁣ T...

Our CEO Jerry Liu is joining founders from LangChain, CrewAI, and others at @Databricks #DataAISummi...

How much can good documentation save an AI agent in cost and time? Turns out, a lot. We built a cus...

Contracts are where business commitments live, but most organizations still manage them manually, se...

We're headed back to @Databricks #DataAISummit to parse your PDFs next week 🦙 Catch our co-founder...

Day 0 Anthropic Fable 5 in ParseBench: We tested the model's advancements when it comes to document ...

Vector databases or pure grep? Teams are split on the right retrieval architecture for agents. ⁣ ⁣ T...