| RT @jerryjliu0: We wrote a 37-page technical report on OCRia-1, our SOTA model for document parsing.
ā
It contains comā¦ |
@llama_index |
Company |
Repost |
2026-10-25 |
328 |
0 |
5 |
0 |
0 |
0 |
| RT @jerryjliu0: OCRia-1 is the best general purpose model for document parsing.
Model card below š
https://t.co/mImFsā¦ |
@llama_index |
Company |
Repost |
2026-10-25 |
494 |
0 |
11 |
0 |
0 |
0 |
| Yesterday we launched OCRia-1, our new state-of-the-art document parsing model powering LlamaParse.
Today, itās on Opeā¦ |
@llama_index |
Company |
Original |
2026-10-23 |
16,402 |
104 |
12 |
9 |
1 |
72 |
| RT @imaanxsultan: this could be you šļø
weāre giving away 2 VIP tickets to F1 in Austin this weekend. all three days,ā¦ |
@llama_index |
Company |
Repost |
2026-10-22 |
542 |
0 |
2 |
0 |
0 |
0 |
| This is a huge moment for LlamaIndex and an incredible milestone for our research team: introducing OCRia-1, our new doā¦ |
@llama_index |
Company |
Quote |
2026-10-22 |
10,857 |
116 |
13 |
12 |
1 |
78 |
| RT @jerryjliu0: Congrats to @nvidia for creating the best open-weight model on document parsing so far.
Nemotron 3.5 Pā¦ |
@llama_index |
Company |
Repost |
2026-10-22 |
489 |
0 |
106 |
0 |
0 |
0 |
| RT @imaanxsultan: best cold outreach iāve ever done: showing up at foundersā doors with arsicault croissants (yes, the ā¦ |
@llama_index |
Company |
Repost |
2026-10-20 |
576 |
0 |
3 |
0 |
0 |
0 |
| LlamaIndex became a croissant delivery service for a day. š„
With Y Combinator and a16z Speedrun demo days coming up, wā¦ |
@llama_index |
Company |
Original |
2026-10-20 |
2,869 |
16 |
3 |
9 |
1 |
1 |
| RT @jerryjliu0: A lot of professional work around documents can be arbitrarily challenging to automate.
It not only reā¦ |
@llama_index |
Company |
Repost |
2026-10-20 |
496 |
0 |
3 |
0 |
0 |
0 |
| The OSS models on OpenDocRouter are slowly powering up! š
We trained additional speculative decoders to help with latā¦ |
@llama_index |
Company |
Original |
2026-10-19 |
3,966 |
18 |
3 |
11 |
1 |
5 |
| RT @jerryjliu0: Document extraction is an arbitrarily complex reasoning problem for both frontier models and humans.
ā
ā¦ |
@llama_index |
Company |
Repost |
2026-10-16 |
440 |
0 |
7 |
0 |
0 |
0 |
| Doc of the Week: VL-DocIRās, a new paper on long-document retrieval. Table 2, where the āData Sourceā header spans Wikiā¦ |
@llama_index |
Company |
Original |
2026-10-16 |
2,686 |
9 |
1 |
7 |
0 |
4 |
| RT @jerryjliu0: Introducing ExtractBenchPro: the most challenging benchmark for real-world document extraction.
We seeā¦ |
@llama_index |
Company |
Repost |
2026-10-15 |
433 |
0 |
16 |
0 |
0 |
0 |
| There are more document parsing models than ever, and theyāre getting harder to tell apart.
Thatās why we built OpenDoā¦ |
@llama_index |
Company |
Original |
2026-10-14 |
3,646 |
22 |
2 |
14 |
0 |
16 |
| RT @jerryjliu0: We benchmarked Gemini 4 Argon, Muse Wonder, and Muse Spark comprehensively on hard document OCR tasks.
ā¦ |
@llama_index |
Company |
Repost |
2026-10-14 |
509 |
0 |
5 |
0 |
0 |
0 |
| OpenDocRouter makes it dead-simple to start parsing your documents across on ton of frontier Models (gemini, luna) and ā¦ |
@llama_index |
Company |
Original |
2026-10-13 |
5,441 |
15 |
1 |
9 |
1 |
7 |
| Doc Chai is real, and on Thursday you can drink it ā
Weāre throwing a launch party for our first drink with @useCorgā¦ |
@llama_index |
Company |
Original |
2026-10-13 |
4,661 |
13 |
1 |
3 |
1 |
0 |
| Three events, one award, a very respectable 4th place in hot sauce.
Our SF Tech Week:
ā AI Demo Night w/ @ClickHouse ā¦ |
@llama_index |
Company |
Original |
2026-10-12 |
5,224 |
11 |
3 |
6 |
1 |
0 |
| What happens when a table contains tables?
Usually, a mess. With LlamaParse, it comes out clean.
Doc of the Week: Micā¦ |
@llama_index |
Company |
Original |
2026-10-09 |
4,216 |
27 |
4 |
9 |
3 |
18 |
| Markdown is all you need.
(Mostly.)
A parser can get every word on the page right and still lose which column a numbā¦ |
@llama_index |
Company |
Original |
2026-10-08 |
11,640 |
112 |
7 |
17 |
4 |
84 |
| Today we're announcing OpenDocRouter: every model for document parsing under one API.
There are ~4,000 OCR models on Hā¦ |
@llama_index |
Company |
Original |
2026-10-07 |
47,823 |
252 |
37 |
32 |
7 |
219 |
| The biggest night of SF Tech Week is black tie.
120+ agent founders, 50 investors, and live jazz at the Redwood Room oā¦ |
@llama_index |
Company |
Original |
2026-10-06 |
3,300 |
13 |
4 |
5 |
0 |
2 |
| OCR is dead šŖ¦ Long live agentic OCR!
Traditional OCR makes one pass and hands back whatever text it got. Tables get flā¦ |
@llama_index |
Company |
Original |
2026-10-05 |
44,841 |
632 |
67 |
26 |
0 |
777 |
| RT @jerryjliu0: We got extremely good at extracting a scanned from layer by layer š - from printed fields, overlaid texā¦ |
@llama_index |
Company |
Repost |
2026-10-05 |
504 |
0 |
13 |
0 |
0 |
0 |
| RT @jerryjliu0: one of the most challenging tasks for frontier models is being able to extract thousands of values fromā¦ |
@llama_index |
Company |
Repost |
2026-10-02 |
438 |
0 |
9 |
0 |
0 |
0 |
| The BEA's new Q2 GDP-by-state was released, but the key data is entirely in an infographic, without a text-layer.
Llamā¦ |
@llama_index |
Company |
Original |
2026-10-02 |
3,541 |
10 |
5 |
6 |
0 |
3 |
| RT @jerryjliu0: Today weāre introducing Extract v2.5 - a series of frontier agents tuned for document extraction.
The ā¦ |
@llama_index |
Company |
Repost |
2026-10-01 |
457 |
0 |
35 |
0 |
0 |
0 |
| How many people show up on a Tuesday night to talk about document processing for AI agents? š¤
In New York, enough to fā¦ |
@llama_index |
Company |
Original |
2026-09-30 |
3,554 |
20 |
8 |
7 |
0 |
1 |
| RT @jerryjliu0: System one models are extremely useful for a variety of document tasks that require fast decisions:
* oā¦ |
@llama_index |
Company |
Repost |
2026-09-30 |
427 |
0 |
20 |
0 |
0 |
0 |
| RT @usekernel: join KERNEL, @braintrust, and @llama_index for agent builders night this evening at 6pm. drinks, demos, ā¦ |
@llama_index |
Company |
Repost |
2026-09-29 |
557 |
0 |
4 |
0 |
0 |
0 |
| RT @jerryjliu0: Yesterday I hosted a fun dinner conversation with @vincentsunnchen from @SnorkelAI on evals and RL enviā¦ |
@llama_index |
Company |
Repost |
2026-09-29 |
413 |
0 |
6 |
0 |
0 |
0 |
| Document parsing requires a lot of on-the-fly decision making.
We explored the early approaches to Jev and Jev-like moā¦ |
@llama_index |
Company |
Original |
2026-09-28 |
5,211 |
22 |
2 |
2 |
0 |
16 |
| Parsing forms still trips up the latest frontier VLMs.
A form isn't text on a page. It's a set of fields, grouped intoā¦ |
@llama_index |
Company |
Original |
2026-09-28 |
10,443 |
11 |
2 |
7 |
1 |
7 |
| A blank cell can change the meaning of a forecast.
Four times a year, the Fed's 18 top policymakers each put their forā¦ |
@llama_index |
Company |
Original |
2026-09-25 |
7,655 |
13 |
3 |
4 |
1 |
6 |
| confidence scores only matter if they help you decide what to automate.
for document extraction, that usually means knā¦ |
@llama_index |
Company |
Original |
2026-09-24 |
15,997 |
20 |
5 |
7 |
2 |
14 |
| RT @jerryjliu0: we've built the world's most advanced engine for document extraction over complex documents
the video ā¦ |
@llama_index |
Company |
Repost |
2026-09-24 |
472 |
0 |
14 |
0 |
0 |
0 |
| RT @daytonaio: Excited for next Tuesday, Sept 29, and our monthly @daytonaio AI Builders Demo Night in SF!
Weāre hostiā¦ |
@llama_index |
Company |
Repost |
2026-09-23 |
23 |
0 |
4 |
0 |
0 |
0 |
| RT @imaanxsultan: week 2 at @llama_index: pitched a vlog series
week 3: filming mr. beast at the u.s. open š¾
introduciā¦ |
@llama_index |
Company |
Repost |
2026-09-23 |
611 |
0 |
7 |
0 |
0 |
0 |
| RT @jerryjliu0: liteparse is the fastest pdf parser on the planet
parses each page at just 2.8ms / page!!
check it oā¦ |
@llama_index |
Company |
Repost |
2026-09-22 |
444 |
0 |
13 |
0 |
0 |
0 |
| The fastest PDF-to-Markdown parser just got faster. ā”ļø
With LiteParse v2.14.6, text-based PDFs parse about 25% faster.ā¦ |
@llama_index |
Company |
Original |
2026-09-22 |
28,415 |
63 |
1 |
11 |
2 |
80 |
| RT @jerryjliu0: you can find a nice interactive visualization of docjev splitting in action here.
it matches luna in bā¦ |
@llama_index |
Company |
Repost |
2026-09-22 |
523 |
0 |
24 |
0 |
0 |
0 |
| RT @jerryjliu0: with jev, everyone is understanding the importance of calibrated confidence scores for discrete decisioā¦ |
@llama_index |
Company |
Repost |
2026-09-22 |
453 |
0 |
19 |
0 |
0 |
0 |
| Grounded Confidence is here for Extract! š¦
When your agents and workflows depend on extracted data, you need to know hā¦ |
@llama_index |
Company |
Original |
2026-09-21 |
15,627 |
39 |
2 |
7 |
1 |
15 |
| RT @jerryjliu0: Introducing DocJev - a lightning-fast OSS library for document classification and splitting with jev ā”ļøā¦ |
@llama_index |
Company |
Repost |
2026-09-21 |
475 |
0 |
98 |
0 |
0 |
0 |
| Introducing the first in our Parsed by LlamaParse series. We're outlining the stakes of 'getting parsing wrong' in consā¦ |
@llama_index |
Company |
Original |
2026-09-18 |
3,947 |
30 |
11 |
12 |
0 |
15 |
| It was great to be at Connected Stack last week with founders and builders working on whatās next in enterprise AI.
@jā¦ |
@llama_index |
Company |
Original |
2026-09-17 |
3,501 |
17 |
3 |
9 |
0 |
4 |
| Ready to learn how to build document processing pipelines for insurance agents?
Join LlamaIndex Solutions Architect Aā¦ |
@llama_index |
Company |
Original |
2026-09-16 |
3,673 |
15 |
4 |
4 |
1 |
3 |
| keeping our SDKs up to date can be a pain. every API change brings another round of updates, tests, and releases. and eā¦ |
@llama_index |
Company |
Original |
2026-09-15 |
9,203 |
15 |
3 |
3 |
1 |
5 |
| RT @jerryjliu0: āJust-in-Timeā OCR
The latest agent harnesses (e.g. Cowork, Codex, Grok) do 2 passes of ad-hoc documenā¦ |
@llama_index |
Company |
Repost |
2026-09-15 |
481 |
0 |
18 |
0 |
0 |
0 |
| just-in-time OCR is all the rage.
most pipelines parse every page before anyone asks a question. for an agent working ā¦ |
@llama_index |
Company |
Original |
2026-09-14 |
23,126 |
78 |
11 |
19 |
3 |
56 |
| RT @jerryjliu0: Introducing FlyOCR šŖ° - I trained a fly brain to read a PDF
It uses the full MaleCNS v1.0 fruit fly conā¦ |
@llama_index |
Company |
Repost |
2026-09-14 |
506 |
0 |
77 |
0 |
0 |
0 |
| confidence scores in LlamaParse just got an upgrade š¦øāāļø
our new high-effort mode provides granular page-level scoresā¦ |
@llama_index |
Company |
Original |
2026-09-11 |
10,139 |
32 |
4 |
10 |
3 |
5 |
| RT @jerryjliu0: Astra is awesome, but if you're using it specifically to parse and extract a massive volume of documentā¦ |
@llama_index |
Company |
Repost |
2026-09-10 |
492 |
0 |
14 |
0 |
0 |
0 |
| Last week we brought LlamaParse to Claude. Now itās available in ChatGPT, too š¦
ChatGPT can already read PDFs. But doā¦ |
@llama_index |
Company |
Original |
2026-09-09 |
14,184 |
26 |
5 |
4 |
1 |
13 |
| RT @imaanxsultan: happy to announce i've become an arsicault chocolate almond croissant dealer!
(just for today and toā¦ |
@llama_index |
Company |
Repost |
2026-09-08 |
463 |
0 |
2 |
0 |
0 |
0 |
| RT @jerryjliu0: Astra might finally help me automate what I've spent ~hundreds of hours doing since the start of this cā¦ |
@llama_index |
Company |
Repost |
2026-09-06 |
439 |
0 |
13 |
0 |
0 |
0 |
| RT @jerryjliu0: We benchmarked GPT-6 Astra on hard document parsing and extraction tasks.
It is the best frontier modeā¦ |
@llama_index |
Company |
Repost |
2026-09-05 |
381 |
0 |
10 |
0 |
0 |
0 |
| RT @jerryjliu0: Unlike other players in the OCR space, we don't block our competitors from accessing our platform.
We'ā¦ |
@llama_index |
Company |
Repost |
2026-09-04 |
423 |
0 |
11 |
0 |
0 |
0 |
| Does paying 5x more per page actually get you better document extraction? We ran the data to find out.
We evaluated 14ā¦ |
@llama_index |
Company |
Original |
2026-09-04 |
13,019 |
20 |
4 |
2 |
1 |
9 |
| RT @jerryjliu0: Today, we're excited to launch Extract Turbo ā”ļø - the fastest VLM-powered document extraction solution.ā¦ |
@llama_index |
Company |
Repost |
2026-09-03 |
455 |
0 |
20 |
0 |
0 |
0 |
| Document extraction just got a new gear. ā”ļø
Introducing Turbo mode for Extract, our fastest way yet to pull structuredā¦ |
@llama_index |
Company |
Original |
2026-09-03 |
16,585 |
43 |
11 |
6 |
3 |
28 |
| RT @jerryjliu0: Fable 5.1 didn't come with document OCR benchmarks, so we benchmarked it on ParseBench: a comprehensiveā¦ |
@llama_index |
Company |
Repost |
2026-09-03 |
462 |
0 |
10 |
0 |
0 |
0 |
| ExtractBench is now live on @Kaggle.
It tests schema-guided document extraction on the documents most likely to break ā¦ |
@llama_index |
Company |
Original |
2026-09-02 |
2,161 |
15 |
2 |
1 |
0 |
4 |
| RT @imaanxsultan: SO excited to share my next chapter: iām joining @llama_index to lead all things growth marketing, brā¦ |
@llama_index |
Company |
Repost |
2026-09-02 |
508 |
0 |
3 |
0 |
0 |
0 |
| RT @jerryjliu0: Thereās generally a massive difference in quality between specialized OCR providers, āsimpleā open-weigā¦ |
@llama_index |
Company |
Repost |
2026-09-01 |
469 |
0 |
21 |
0 |
0 |
0 |
| RT @juliafedorin: My conversation with @jerryjliu0.
He's building @llama_index: document infrastructure for AI agents,ā¦ |
@llama_index |
Company |
Repost |
2026-08-31 |
599 |
0 |
5 |
0 |
0 |
0 |
| LlamaParse is officially a verified connector on Claude! š¦
Claude is perfectly fine for the occasional text-only PDF. ā¦ |
@llama_index |
Company |
Original |
2026-08-31 |
11,771 |
36 |
4 |
6 |
2 |
17 |
| RT @jerryjliu0: PDF parsing is fun because there's an infinite variety of enteprise documents š. For each document cateā¦ |
@llama_index |
Company |
Repost |
2026-08-28 |
475 |
0 |
7 |
0 |
0 |
0 |
| Static embeddings offer unmatched throughput, but they also suffer from accuracy loss compared to traditional embeddingā¦ |
@llama_index |
Company |
Original |
2026-08-28 |
11,089 |
30 |
7 |
3 |
3 |
13 |
| Most extraction tools treat spreadsheets like PDFs. They flatten the file into text or markdown, then ask a model to inā¦ |
@llama_index |
Company |
Original |
2026-08-27 |
13,441 |
56 |
11 |
2 |
2 |
40 |
| RT @perplexity_ai: Parsing runs entirely on-device, so sensitive documents never leave the machine.
On ParseBench-100,ā¦ |
@llama_index |
Company |
Repost |
2026-08-26 |
465 |
0 |
1 |
0 |
0 |
0 |
| Our 2nd founder dinner in SF co-hosted by @jerryjliu0 and @GuangyuRobert at @Fundamental - the team behind @tryshortcutā¦ |
@llama_index |
Company |
Original |
2026-08-26 |
3,577 |
7 |
1 |
1 |
0 |
1 |
| Every extraction API demos well on a clean invoice. But what about the scanned form, the nested table, the 40-page finaā¦ |
@llama_index |
Company |
Original |
2026-08-25 |
6,540 |
14 |
2 |
5 |
1 |
1 |
| Our 2nd founder dinner in SF co-hosted by @jerryjliu0 and @GuangyuRobert at @Fundamental - the team behind @tryshortcutā¦ |
@llama_index |
Company |
Original |
2026-08-24 |
1,541 |
5 |
2 |
1 |
0 |
0 |
| RT @jerryjliu0: The latest RAG trend for the current agent harnesses (Codex, Cowork) is to do two passes of document prā¦ |
@llama_index |
Company |
Repost |
2026-08-24 |
465 |
0 |
31 |
0 |
0 |
0 |
| Our CEO @jerryjliu0 is speaking at @CoreWeave Fully Connected 2026 in SF. š¤
"Automating Document Work with Long-Horizoā¦ |
@llama_index |
Company |
Original |
2026-08-21 |
3,656 |
24 |
6 |
6 |
0 |
3 |
| RT @jerryjliu0: If youāre building an āagent over your PDFsā in 2026, one of the most underrated things you can do is tā¦ |
@llama_index |
Company |
Repost |
2026-08-18 |
437 |
0 |
11 |
0 |
0 |
0 |
| Most parsers treat tracked changes as noise. Result: a deleted clause comes back as live text, and your pipeline reads ā¦ |
@llama_index |
Company |
Original |
2026-08-18 |
11,600 |
31 |
4 |
7 |
1 |
15 |
| RT @gmi_cloud: spotlighting the partners and speakers joining Summer Signal '26
š¦@llama_index joins as an agentic paā¦ |
@llama_index |
Company |
Repost |
2026-08-17 |
582 |
0 |
2 |
0 |
0 |
0 |
| Most document extraction APIs can't tell you where a value came from.
For ExtractBench, we scored grounding strictly: ā¦ |
@llama_index |
Company |
Original |
2026-08-17 |
20,397 |
35 |
5 |
10 |
1 |
14 |
| RT @jerryjliu0: We tuned an AI agent that can do large-scale document extraction from long docs (50+ pages, some with 1ā¦ |
@llama_index |
Company |
Repost |
2026-08-17 |
486 |
0 |
15 |
0 |
0 |
0 |
| Get ready to break racks and agents.
If you're in SF, next Thursday we're co-hosting a billiards night for AI engineeā¦ |
@llama_index |
Company |
Original |
2026-08-14 |
4,516 |
15 |
1 |
8 |
0 |
2 |
| š¦āļø Itās a hot Llama summer, and it pays to be a PRO at document parsing. For a limited time, upgrade to the LlamaParseā¦ |
@llama_index |
Company |
Original |
2026-08-13 |
120,543 |
17 |
1 |
3 |
0 |
5 |
| Every document extraction system has a perception blind spot. We mapped them.
For ExtractBench, we tested 14 systems oā¦ |
@llama_index |
Company |
Original |
2026-08-13 |
11,176 |
22 |
7 |
5 |
1 |
11 |
| The most dangerous document extraction failure isn't a wrong value. It's a missing row that looks like nothing is wrongā¦ |
@llama_index |
Company |
Original |
2026-08-12 |
5,536 |
35 |
5 |
6 |
1 |
22 |
| Introducing šš
ššæš®š°ššš²š»š°šµ: the most comprehensive benchmark for information extraction from complex enterprise documentsā¦ |
@llama_index |
Company |
Original |
2026-08-11 |
31,528 |
80 |
11 |
17 |
3 |
39 |
| SF builders, it's time to ditch your agents and head out on a š
Join us for a run tomorrow with the Lore community atā¦ |
@llama_index |
Company |
Original |
2026-08-10 |
4,771 |
12 |
2 |
6 |
1 |
0 |
| POV: It's the last day at @Ai4conferences and your:
š§¢ colorful hats and stickers are all over the conference floor
šØāā¦ |
@llama_index |
Company |
Original |
2026-08-06 |
5,025 |
8 |
1 |
2 |
0 |
0 |
| "OCR is just a feature now. Frontier models will eat it."
We hear this constantly. The data says otherwise.
Across thā¦ |
@llama_index |
Company |
Original |
2026-08-05 |
10,208 |
33 |
6 |
4 |
1 |
15 |
| Parsing a W-2 into markdown was always the easy part. Getting the fields out was a second pipeline: define a schema, maā¦ |
@llama_index |
Company |
Original |
2026-08-04 |
19,478 |
18 |
4 |
8 |
2 |
10 |
| š¦ is coming coming to Las Vegas for @Ai4Conferences next week (Aug 4ā6). Three ways to find us:
š Booth 1561 on the Exā¦ |
@llama_index |
Company |
Original |
2026-08-01 |
5,138 |
7 |
2 |
3 |
0 |
3 |
| Not every page in your PDF needs the same treatment.
A scanned cover, a dense table, a clean text page, a figure-heavyā¦ |
@llama_index |
Company |
Original |
2026-07-30 |
42,677 |
67 |
6 |
8 |
3 |
45 |
| Batch parsing used to mean writing API scripts. Now it's a button. š¦
Parse or extract across up to 10,000 files in oneā¦ |
@llama_index |
Company |
Original |
2026-07-29 |
11,554 |
17 |
3 |
4 |
1 |
8 |
| Want to run your LlamaParse worker at the edge in minutes?
We just released š°šæš²š®šš²-š¹š¹š®šŗš®-šš¼šæšøš²šæ š
It scaffolds a readā¦ |
@llama_index |
Company |
Original |
2026-07-27 |
6,411 |
33 |
3 |
4 |
0 |
10 |
| As of LiteParse v2.8.0, image ā PDF conversion no longer depends on ImageMagick. Instead, itās now handled natively in ā¦ |
@llama_index |
Company |
Original |
2026-07-24 |
16,585 |
57 |
7 |
4 |
2 |
53 |
| You asked, we delivered! š
Expanding our developer toolkit with:
š¹ Go SDK
š¢ Java SDK
>_ CLI
Parse a document from ā¦ |
@llama_index |
Company |
Original |
2026-07-23 |
4,831 |
19 |
1 |
5 |
0 |
3 |
| Your agentic workflows are only as good as the context you feed them.
In finance, that context is stuck inside your meā¦ |
@llama_index |
Company |
Original |
2026-07-22 |
6,145 |
11 |
4 |
1 |
1 |
4 |
| The team flew into SF for a week onsite. š
2x'd in size since we last did this ā first time this many of us have been ā¦ |
@llama_index |
Company |
Original |
2026-07-21 |
8,166 |
13 |
1 |
1 |
1 |
1 |
| We're kicking off a founder dinner series in SF. First one's July 28 - one table, 16 seats, invite-only, co-hosted by @ā¦ |
@llama_index |
Company |
Original |
2026-07-20 |
4,517 |
12 |
1 |
6 |
0 |
2 |
| Teaming up with https://t.co/IBgKPZBnJY for their Agentic Hackathon at the AWS Builder Loft in SF, July 24th. One day tā¦ |
@llama_index |
Company |
Original |
2026-07-17 |
4,979 |
15 |
5 |
5 |
0 |
2 |
| Document processing pipelines are often made up of multiple services: parsing ā chunking ā embeddings ā storage.
Untilā¦ |
@llama_index |
Company |
Original |
2026-07-16 |
10,018 |
43 |
6 |
1 |
1 |
38 |
| We're part of the Amazon Web Services (AWS) AI Builder Lab in New York on Friday, July 24 - a Clash of Agents competitiā¦ |
@llama_index |
Company |
Original |
2026-07-15 |
3,382 |
9 |
2 |
2 |
0 |
3 |
| Your extraction schema is now a conversation away.
ā£
š Upload a doc ā the agent drafts the schema from itā£
š¬ Want changā¦ |
@llama_index |
Company |
Original |
2026-07-14 |
17,373 |
20 |
7 |
3 |
1 |
11 |
| Co-hosting 'Swap and Pitch Night' this Thursday in SF with @tembo, @clerk, and @autonomaai.
Pitch night where founderā¦ |
@llama_index |
Company |
Original |
2026-07-14 |
8,354 |
8 |
1 |
3 |
1 |
2 |
| We eat docsš«¢ https://t.co/jmeNj27LRi |
@llama_index |
Company |
Original |
2026-07-14 |
6,779 |
12 |
1 |
0 |
1 |
0 |
| Ever wanted to quickly turn a PDF into clean text to paste into your favorite AI agent, without having use CLIs or openā¦ |
@llama_index |
Company |
Original |
2026-07-13 |
21,201 |
52 |
6 |
7 |
2 |
76 |
| @OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in document understandiā¦ |
@llama_index |
Company |
Original |
2026-07-09 |
23,171 |
23 |
1 |
4 |
1 |
4 |
| @OpenAI released GPT 5.6 today and we ran a day 0 benchmark in ParseBench to test improvements in document understandiā¦ |
@llama_index |
Company |
Original |
2026-07-09 |
3,067 |
14 |
4 |
1 |
0 |
3 |
| Low user caps in LlamaParse? Gone.š
Every plan ā Free through Pro ā now unlocks up to 100 team members.
No more pickinā¦ |
@llama_index |
Company |
Original |
2026-07-09 |
3,726 |
11 |
1 |
3 |
0 |
0 |
| Introducing: Granular job tracking and cost attribution in LlamaParse š¦
Parsing thousands of pages a day is a lot to ā¦ |
@llama_index |
Company |
Original |
2026-07-08 |
9,805 |
22 |
1 |
3 |
1 |
4 |
| We've rolled out improvements to LlamaParse Cost Optimizer.
Our intelligent tier routing now more reliably ensures yoā¦ |
@llama_index |
Company |
Original |
2026-07-07 |
10,361 |
15 |
2 |
2 |
1 |
5 |
| Most agentic retrieval demos assume clean, well-structured documents. Enterprise reality is often different, consistingā¦ |
@llama_index |
Company |
Original |
2026-07-06 |
5,763 |
38 |
10 |
4 |
0 |
30 |
| The team at @vercel recently released the Eve agent framework, so we built a template that integrates LiteParse with itā¦ |
@llama_index |
Company |
Original |
2026-07-03 |
32,553 |
43 |
3 |
7 |
2 |
26 |
| LiteParse runs anywhere, including inside agent runtimes.
To prove it, we built an email processing assistant using @flā¦ |
@llama_index |
Company |
Original |
2026-07-02 |
7,954 |
41 |
5 |
6 |
0 |
30 |
| Game. Match. That's a wrap on the inaugural Agent Open š¦š¤ļøš
Hundreds of AI builders, 64 matches, 7 partners, 2 courts.ā¦ |
@llama_index |
Company |
Original |
2026-07-01 |
4,140 |
22 |
1 |
1 |
0 |
0 |
| Agentic retrieval is changing the way retrieval-augmented applications are built, especially in domains like legal and ā¦ |
@llama_index |
Company |
Original |
2026-07-01 |
67,787 |
105 |
11 |
16 |
2 |
145 |
| Doors are open at Agent Open, right next door to AI Engineer
Two courts, blue sky, no fog (a San Francisco miracle) š¤ļøā¦ |
@llama_index |
Company |
Original |
2026-06-30 |
4,948 |
20 |
2 |
3 |
0 |
2 |
| We just made it a lot easier for AI agents to work with your documents.
LlamaParse MCP now does more than parse or claā¦ |
@llama_index |
Company |
Original |
2026-06-30 |
6,515 |
64 |
8 |
4 |
0 |
59 |
| Semantic search alone doesn't cut it. Neither does brute-force grep.
Agents need both.
Today we're shipping the Retrieā¦ |
@llama_index |
Company |
Original |
2026-06-29 |
29,552 |
68 |
6 |
5 |
3 |
70 |
| We're all over AI Engineer World's Fair on June 29 to July 2. š¦
šVisit us at booth L-G47. LlamaParse demos + Fear of Dā¦ |
@llama_index |
Company |
Original |
2026-06-29 |
3,369 |
14 |
4 |
3 |
0 |
2 |
| The @n8n_io node for the LlamaParse Platform is now an officially verified community node, as part of a broader partnerā¦ |
@llama_index |
Company |
Original |
2026-06-26 |
12,284 |
39 |
6 |
6 |
1 |
30 |
| We built LiteParse, the fastest document parsing solution on the planet and made it open source.
And it just hit 10k gā¦ |
@llama_index |
Company |
Original |
2026-06-25 |
22,202 |
39 |
4 |
5 |
1 |
32 |
| Bring your hot takes and your drop shots.š„
Next week, we're co-hosting The Agent Open: an afternoon of pickleball, fooā¦ |
@llama_index |
Company |
Original |
2026-06-22 |
10,093 |
7 |
2 |
4 |
1 |
0 |
| LiteParse v2.1 is here, and its bringing the fastest markdown output possible.
In this release, we are fulfilling our ā¦ |
@llama_index |
Company |
Original |
2026-06-18 |
304,850 |
171 |
29 |
14 |
8 |
178 |
| ~90% of enterprise data is unstructured, locked in the documents that power the majority of knowledge work. The next maā¦ |
@llama_index |
Company |
Original |
2026-06-18 |
6,314 |
18 |
4 |
7 |
2 |
13 |
| Vector databases or pure grep? Teams are split on the right retrieval architecture for agents.āØā£
ā£
The reality? You neeā¦ |
@llama_index |
Company |
Original |
2026-06-17 |
12,949 |
55 |
8 |
9 |
1 |
27 |
| Our CEO Jerry Liu is joining founders from LangChain, CrewAI, and others at @Databricks #DataAISummit today for a panelā¦ |
@llama_index |
Company |
Original |
2026-06-17 |
3,027 |
15 |
3 |
7 |
0 |
1 |
| How much can good documentation save an AI agent in cost and time? Turns out, a lot.
We built a custom skill that teacā¦ |
@llama_index |
Company |
Original |
2026-06-16 |
13,865 |
38 |
5 |
9 |
2 |
29 |
| Contracts are where business commitments live, but most organizations still manage them manually, searching PDFs for reā¦ |
@llama_index |
Company |
Original |
2026-06-15 |
10,882 |
31 |
3 |
5 |
1 |
24 |
| We're headed back to @Databricks #DataAISummit to parse your PDFs next week š¦
Catch our co-founder & CEO @jerryjliu0 ā¦ |
@llama_index |
Company |
Original |
2026-06-12 |
4,597 |
31 |
3 |
7 |
0 |
3 |
| Day 0 Anthropic Fable 5 in ParseBench: We tested the model's advancements when it comes to document understanding. The ā¦ |
@llama_index |
Company |
Original |
2026-06-10 |
41,015 |
56 |
6 |
15 |
1 |
18 |
| Parsing a document accurately is one thing. Proving where every value came from is another.
When a compliance team rā¦ |
@llama_index |
Company |
Original |
2026-06-09 |
29,123 |
45 |
7 |
4 |
3 |
23 |
| The Agent Open: AI's Pickleball Tournament š
Come put your code and backhand to the test and embrace the full Open exā¦ |
@llama_index |
Company |
Original |
2026-06-08 |
132,801 |
27 |
5 |
5 |
1 |
7 |
| Most AI pipelines are only as good as the data we provide them with, and that usually means PDFs or other unstructured ā¦ |
@llama_index |
Company |
Original |
2026-06-04 |
15,785 |
75 |
13 |
8 |
2 |
51 |
| We're presenting ParseBench at CVPR 2026 today. š¦
Come learn why document understanding is an AGI-complete problem (anā¦ |
@llama_index |
Company |
Original |
2026-06-04 |
16,556 |
35 |
7 |
5 |
2 |
12 |
| āļø Come meet the LlamaIndex Team at Snowflake Summit 2026.
It might be chilly in Snow Park āļø but the AI infrastructuā¦ |
@llama_index |
Company |
Original |
2026-06-01 |
8,535 |
16 |
4 |
5 |
1 |
0 |
| When we say āLiteParse runs everywhere,ā we mean it.
Our WASM package is lightweight, minimal, and built for browser aā¦ |
@llama_index |
Company |
Original |
2026-05-29 |
45,905 |
138 |
20 |
10 |
3 |
138 |
| Opus 4.8 dropped today. ParseBench results are out.
ā
Slight gains: tables, semantic formatting, layout
ā ļø Slight regrā¦ |
@llama_index |
Company |
Original |
2026-05-29 |
25,794 |
40 |
6 |
9 |
2 |
20 |
| Is grep š³š¦š¢šššŗ all your AI agent needs for search?
For a small codebase or a docs folder, the answer might be yes, but ā¦ |
@llama_index |
Company |
Original |
2026-05-28 |
4,520 |
39 |
7 |
13 |
0 |
23 |
| LiteParse v2.0 is out now, and it is blazing fast + runs everywhere!
We rewrote everything from scratch in Rust, and ā¦ |
@llama_index |
Company |
Original |
2026-05-27 |
503,713 |
603 |
70 |
32 |
15 |
664 |
| Automate a loan underwriting pipeline in just a few lines of codeāØļø
A typical loan file is a stack of pay stubs and bā¦ |
@llama_index |
Company |
Original |
2026-05-26 |
4,331 |
33 |
5 |
4 |
0 |
17 |
| LlamaParse now parses HEIC files natively š .
HEIC is Apple's default image format, so it shows up all over enterpriseā¦ |
@llama_index |
Company |
Original |
2026-05-25 |
13,092 |
33 |
7 |
4 |
2 |
10 |
| How do you know your document parser is ready for production?
š¤Existing benchmarks miss what AI agents actually need.ā¦ |
@llama_index |
Company |
Original |
2026-05-22 |
5,536 |
18 |
5 |
3 |
0 |
13 |
| New in LlamaParse: Latency Metrics is now live.
For every Parse, Extract, and Classify job, you can now get a full latā¦ |
@llama_index |
Company |
Original |
2026-05-21 |
10,578 |
28 |
6 |
8 |
1 |
7 |
| Financial analysts spend ~70% of their time pulling numbers out of PDFs.
We built a demo agent that ingests SEC filingsā¦ |
@llama_index |
Company |
Original |
2026-05-20 |
28,004 |
28 |
7 |
10 |
1 |
28 |
| We're live at @googleio!
Thanks, @OfficialLoganK for the shoutout in the developer keynote. Lots of exciting featureā¦ |
@llama_index |
Company |
Original |
2026-05-19 |
7,185 |
15 |
6 |
3 |
1 |
1 |
| š The team at @Google just released the Agents API, a service for building and running custom agents inside a sandboxedā¦ |
@llama_index |
Company |
Original |
2026-05-19 |
22,508 |
54 |
12 |
9 |
2 |
69 |
| That's a wrap at @aiDotEngineer Singapore šøš¬
Thanks for all the devs that tuned into our workshop, keynote, and execā¦ |
@llama_index |
Company |
Original |
2026-05-17 |
11,018 |
50 |
3 |
6 |
1 |
5 |
| Yesterday we committed a cardinal sin: two first-party events in NYC, back-to-back. We had to close registration for boā¦ |
@llama_index |
Company |
Original |
2026-05-14 |
4,403 |
12 |
1 |
2 |
0 |
1 |
| Need document parsing that stays fully local and private? š
Meet liteparse-server, a self-hostable, open-source HTTP sā¦ |
@llama_index |
Company |
Original |
2026-05-12 |
15,663 |
55 |
18 |
4 |
3 |
66 |
| Ever wished your agent could read PDFs, images, and Office documents as easily as plain text?
Or combine the safety ofā¦ |
@llama_index |
Company |
Original |
2026-05-11 |
17,622 |
71 |
12 |
8 |
2 |
84 |
| A few weeks ago @simonw got Claude to port LiteParse to the browser. Today, we are launching that work as a complete guā¦ |
@llama_index |
Company |
Original |
2026-05-07 |
3,256 |
18 |
2 |
4 |
0 |
8 |
| What if you could extract text from any photo on your phone?
We built LlamaParse Mobile, an @expo + @reactnative app fā¦ |
@llama_index |
Company |
Original |
2026-05-06 |
9,634 |
19 |
6 |
4 |
1 |
18 |
| LlamaIndex NYC takeover, 5/13 š½
Our CEO Jerry Liu is in town.
Two events, open to every NYC builder:
š ļø FinParse Woā¦ |
@llama_index |
Company |
Original |
2026-05-06 |
6,500 |
7 |
1 |
2 |
1 |
1 |
| š @CBinsights AI 100 2026 is out and LlamaIndex made the list.
We're proud to provide the leading document understanā¦ |
@llama_index |
Company |
Original |
2026-05-05 |
11,781 |
19 |
6 |
4 |
1 |
3 |
| May the 4th be with you!āØ Celebrate with us, you must. Join our Start Up Party Up this Thursday before SF's free 2nd Stā¦ |
@llama_index |
Company |
Original |
2026-05-05 |
6,008 |
8 |
2 |
2 |
1 |
1 |
| Our CEO @jerryjliu0 in @VentureBeat , on what's actually changing in the LLM stack:
"We've really identified that theā¦ |
@llama_index |
Company |
Original |
2026-05-01 |
11,248 |
20 |
5 |
3 |
2 |
13 |
| Thank you AI Dev Day '26 @DeepLearningAI
@jerryjliu0 shares why SOTA LLMs can build an app but can't read a PDF š¤Æ httā¦ |
@llama_index |
Company |
Original |
2026-04-30 |
4,358 |
14 |
3 |
1 |
1 |
1 |
| Building scalable, distributed document processing pipelines isnāt easy.
Thatās why we teamed up with @render to build ā¦ |
@llama_index |
Company |
Original |
2026-04-30 |
27,345 |
69 |
14 |
6 |
5 |
61 |
| Parsing documents with AI agents just got a lot more seamlessš
We've rebuilt the LlamaParse MCP server to handle your ā¦ |
@llama_index |
Company |
Original |
2026-04-29 |
19,906 |
48 |
13 |
4 |
3 |
45 |
| Let's talk document formatting.
Bold. Italics. Superscripts. Strikethroughs. The visual cues humans rely on every timeā¦ |
@llama_index |
Company |
Original |
2026-04-28 |
6,808 |
37 |
3 |
3 |
0 |
25 |
| Loan processors spend 40ā60% of their time reconciling income across tax returns, pay stubs, W-2s, and bank statements.ā¦ |
@llama_index |
Company |
Original |
2026-04-27 |
7,998 |
11 |
2 |
4 |
2 |
13 |
| ParseBench is now live on @Kaggle.
The first document OCR benchmark built for AI agents ā 2,000 enterprise pages, 167Kā¦ |
@llama_index |
Company |
Original |
2026-04-23 |
13,134 |
57 |
5 |
2 |
2 |
27 |
| LiteParse: our open-source, layout-aware PDF parser for AI agents.
The secret? Grid projection. Instead of heavy ML layā¦ |
@llama_index |
Company |
Original |
2026-04-22 |
42,708 |
87 |
17 |
2 |
3 |
71 |
| Let's talk parsing charts šš.
Last week we released ParseBench, the first document OCR benchmark for AI agents.
Newā¦ |
@llama_index |
Company |
Original |
2026-04-21 |
14,347 |
39 |
8 |
2 |
2 |
20 |
| NYC FinTech Week just got an AI track š½
Next week we're co-hosting the AI Builders Rooftop Happy Hour with @LinkupAPIā¦ |
@llama_index |
Company |
Original |
2026-04-20 |
2,853 |
9 |
2 |
3 |
0 |
1 |
| Let's talk content faithfulness.
Four days ago, we launched ParseBench, the first document OCR benchmark for AI agentsā¦ |
@llama_index |
Company |
Original |
2026-04-17 |
36,644 |
42 |
8 |
6 |
1 |
39 |
| Anthropic says Opus 4.7 hits 80.6% on Document Reasoning ā up from 57.1%.
But "reasoning about documents" ā "parsing dā¦ |
@llama_index |
Company |
Original |
2026-04-16 |
69,078 |
134 |
9 |
9 |
4 |
50 |
| LiteParse hit 4.3K+ GitHub stars in a few weeks.
Today it officially joins the LlamaIndex ecosystem, with its own page ā¦ |
@llama_index |
Company |
Original |
2026-04-16 |
86,126 |
160 |
17 |
8 |
4 |
182 |
| Let's talk parsing tables.
Two days ago we launched ParseBench,the first document OCR benchmark built for AI agents.
ā¦ |
@llama_index |
Company |
Original |
2026-04-15 |
26,485 |
59 |
11 |
1 |
4 |
33 |
| LiteParse hit 4K+ GitHub stars in 3 weeks. ~500 pages in 2 seconds. No GPU. No API keys. 50+ file formats.
Now @LoganMā¦ |
@llama_index |
Company |
Original |
2026-04-10 |
15,119 |
38 |
9 |
0 |
3 |
33 |
| Agents like @openclaw are incredibly powerful, as long as the information they receive is clean and structuredš¦
When iā¦ |
@llama_index |
Company |
Original |
2026-04-09 |
10,609 |
32 |
6 |
6 |
2 |
11 |
| Common Failure Modes Break VLM-Powered OCR in Production.
š Repetition Loops ā model spirals into infinite whitespaā¦ |
@llama_index |
Company |
Original |
2026-04-08 |
15,762 |
20 |
5 |
4 |
2 |
15 |
| Visually rich documents are especially challenging for agents.
Tables, charts, and images often break traditional documā¦ |
@llama_index |
Company |
Original |
2026-04-07 |
4,928 |
36 |
11 |
3 |
1 |
29 |
| Open call to fintech leaders in NYC š¦ May 13, in-person workshop with @jerryjliu0 on turning complex financial docs intā¦ |
@llama_index |
Company |
Original |
2026-04-07 |
2,468 |
12 |
3 |
2 |
0 |
2 |
| We took a brief break from parsing PDFs this First Thursday and welcomed the AI community to "Series B Lane" in San Fraā¦ |
@llama_index |
Company |
Original |
2026-04-03 |
9,182 |
23 |
4 |
3 |
2 |
1 |
| After the release of Parse v2, Extract is also getting an upgrade ā š¶š»ššæš¼š±šš°š¶š»š“ šš
ššæš®š°š šš®! š
We've been reworking theā¦ |
@llama_index |
Company |
Original |
2026-04-02 |
15,673 |
57 |
10 |
3 |
3 |
38 |
| Lawyers <3 documents
We're proud to sponsor @StanfordLaw and @CodeXStanford's FutureLaw Week 2026! šļøāļø
AI x Law boā¦ |
@llama_index |
Company |
Original |
2026-04-01 |
5,129 |
11 |
3 |
1 |
1 |
3 |
| LlamaIndex is proud to be named to the 2026 Enterprise Tech 30, #3 in the Early Stage category.
The ET30 is an annual ā¦ |
@llama_index |
Company |
Original |
2026-03-31 |
5,853 |
24 |
6 |
3 |
3 |
1 |
| Weāve moved to the '#AI Waterfront' and itās time to celebrate. Swing by on April 2nd to see our new office on 2nd streā¦ |
@llama_index |
Company |
Original |
2026-03-30 |
17,300 |
11 |
1 |
1 |
2 |
0 |
| Our OSS engineer @itsclelia recently built š¹š¶šš²šš²š®šæš°šµ, a fully local document ingestion and retrieval CLI/TUI applicatiā¦ |
@llama_index |
Company |
Original |
2026-03-30 |
14,900 |
78 |
15 |
0 |
2 |
67 |
| Transform your document processing with intelligent table extraction that goes beyond basic OCR.
Tables in PDFs aren'tā¦ |
@llama_index |
Company |
Original |
2026-03-27 |
7,874 |
91 |
13 |
3 |
1 |
72 |
| š The @GoogleDeepMind team just added Gemini 3.1 to the Live API, so we built a small demo showing how Gemini voice ageā¦ |
@llama_index |
Company |
Original |
2026-03-26 |
15,503 |
61 |
12 |
3 |
2 |
33 |
| Bounding boxes are key for citations, and we just shipped a new guide showing how to use LiteParse for visual citationsā¦ |
@llama_index |
Company |
Original |
2026-03-26 |
15,440 |
42 |
8 |
3 |
2 |
30 |
| Word docs are one of the most common file formats people process in LlamaParse, and they've always been surprisingly frā¦ |
@llama_index |
Company |
Original |
2026-03-25 |
11,906 |
67 |
7 |
1 |
3 |
43 |
| Congratulations to @zubeensyed, one of our LlamAgent contest winners, for building an agentic AI workflow that automateā¦ |
@llama_index |
Company |
Original |
2026-03-24 |
10,901 |
36 |
10 |
8 |
2 |
27 |
| Weāve published a new blog with @googledevs on how to build a smart financial assistant using LlamaParse, our state-of-ā¦ |
@llama_index |
Company |
Original |
2026-03-23 |
8,029 |
56 |
12 |
2 |
3 |
42 |
| If you've ever worked in or around legal, you know that discovery is where document parsing really gets stress-tested.
ā¦ |
@llama_index |
Company |
Original |
2026-03-23 |
4,378 |
31 |
9 |
2 |
1 |
17 |
| LlamaParse now has an official Agent Skill you can use across 40+ agents.
With built-in instructions for parsing complā¦ |
@llama_index |
Company |
Original |
2026-03-20 |
53,234 |
92 |
14 |
4 |
3 |
85 |
| Our new open-source LiteParse comes with ready-to-use agent skills that work seamlessly with coding agents.
`npx skillā¦ |
@llama_index |
Company |
Original |
2026-03-20 |
7,764 |
85 |
12 |
6 |
2 |
46 |
| We've spent years building LlamaParse into the most accurate document parser for production AI. Along the way, we learnā¦ |
@llama_index |
Company |
Original |
2026-03-19 |
581,650 |
411 |
56 |
13 |
11 |
446 |
| Context engineering is the new prompt engineering ā and if you're building AI agents, you need to understand the differā¦ |
@llama_index |
Company |
Original |
2026-03-18 |
14,614 |
212 |
39 |
13 |
3 |
230 |
| LlamaParse Agentic Plus mode now delivers precise visual grounding with bounding boxes for the most challenging documenā¦ |
@llama_index |
Company |
Original |
2026-03-18 |
26,517 |
59 |
10 |
1 |
4 |
36 |
| One of the hardest problems with document parsing is trust. How do you know the output actually corresponds to what's iā¦ |
@llama_index |
Company |
Original |
2026-03-17 |
24,690 |
45 |
6 |
4 |
2 |
41 |
| Agentic AI transforms document extraction from simple text transcription into intelligent reasoning, dramatically reducā¦ |
@llama_index |
Company |
Original |
2026-03-16 |
4,255 |
29 |
6 |
9 |
1 |
12 |
| Choosing between Skills and MCP tools for your AI agents? Here's an overview from @itsclelia and @tuanacelik
š§ MCP tooā¦ |
@llama_index |
Company |
Original |
2026-03-13 |
6,723 |
51 |
11 |
8 |
2 |
48 |
| Ever wondered what we mean by 'agentic' OCR? It's parsing that reasons about documents instead of just reading them.
Aā¦ |
@llama_index |
Company |
Original |
2026-03-12 |
28,965 |
84 |
13 |
10 |
4 |
82 |
| š semtools v3.0.0 is out, and it's a great step forward for anyone using semantic search and document parsing from the ā¦ |
@llama_index |
Company |
Original |
2026-03-11 |
40,531 |
106 |
17 |
4 |
4 |
85 |
| š The team at @GoogleDeepMind just released Gemini Embedding 2, a frontier embeddings model with 3072 dimensions and stā¦ |
@llama_index |
Company |
Original |
2026-03-10 |
34,951 |
315 |
52 |
7 |
8 |
204 |
| If youāre working with lots of slide decks and need a better way to search through them, Surreal Slides makes it simpleā¦ |
@llama_index |
Company |
Original |
2026-03-09 |
38,259 |
47 |
16 |
6 |
4 |
35 |
| PDFs are the bane of every AI agent's existence: here's why parsing them is so much harder than you think š
Every deveā¦ |
@llama_index |
Company |
Original |
2026-03-06 |
103,537 |
134 |
15 |
6 |
4 |
171 |
| "Just send the PDF to GPT-5.4"
Ok. We did. Here's what happened:
ā¢ Reading order? Wrong.
ā¢ Tables? Half missing.
ā¢ Haā¦ |
@llama_index |
Company |
Original |
2026-03-06 |
9,452 |
68 |
12 |
15 |
1 |
39 |
| "Just send the PDF to GPT-4o"
Ok. We did. Here's what happened:
ā¢ Reading order? Wrong.
ā¢ Tables? Half missing.
ā¢ Halā¦ |
@llama_index |
Company |
Original |
2026-03-05 |
27,327 |
55 |
6 |
2 |
4 |
36 |
| Creating agent workflows and architecting the logic is one thing, making them durable, fail-safe, and scalable is anothā¦ |
@llama_index |
Company |
Original |
2026-03-05 |
3,462 |
42 |
13 |
1 |
0 |
21 |
| Huge thank you to everyone who joined the @GoogleDeepMind hackathon in NYC with us over the weekend š
Our DevRel @tuanā¦ |
@llama_index |
Company |
Original |
2026-03-04 |
1,783 |
12 |
2 |
1 |
1 |
0 |
| If you need to split complex or composite documents into structured categories or sections, LlamaSplit is built for theā¦ |
@llama_index |
Company |
Original |
2026-03-04 |
17,499 |
27 |
3 |
0 |
2 |
27 |
| LlamaIndex has evolved far beyond a RAG framework - we're now focused on agentic document processing that automates knoā¦ |
@llama_index |
Company |
Original |
2026-03-03 |
34,598 |
62 |
7 |
7 |
2 |
59 |
| Most agents donāt fail on modelsā¦
they fail on context: those ugly, messy, complex documents that trip up even the latā¦ |
@llama_index |
Company |
Original |
2026-03-03 |
29,509 |
19 |
2 |
1 |
2 |
13 |
| When you parse a document with LlamaParse, you also get access to layout data for figures, charts, etc.
Parse the docuā¦ |
@llama_index |
Company |
Original |
2026-03-02 |
4,816 |
16 |
3 |
1 |
0 |
16 |
| Turn your PDF charts into pandas DataFrames with specialized chart parsing in LlamaParse!
This tutorial walks you throā¦ |
@llama_index |
Company |
Original |
2026-02-27 |
3,053 |
11 |
2 |
1 |
1 |
18 |
| Build a private equity deal sourcing agent that automatically classifies investment opportunities and extracts key finaā¦ |
@llama_index |
Company |
Original |
2026-02-26 |
9,687 |
29 |
5 |
0 |
2 |
38 |
| Document OCR benchmarks are hitting a ceiling - and that's a problem for real-world AI applications.
Our latest analysā¦ |
@llama_index |
Company |
Original |
2026-02-24 |
14,051 |
65 |
9 |
3 |
2 |
55 |
| š LlamaAgents Builder just leveled up: File uploads are here!
Our natural language interface for building agentic docuā¦ |
@llama_index |
Company |
Original |
2026-02-23 |
24,925 |
26 |
6 |
1 |
2 |
16 |
| š Big drop from @GoogleDeepMind: Gemini 3.1 Pro is here, and we built a hands-on demo powered by LlamaCloud to put it tā¦ |
@llama_index |
Company |
Original |
2026-02-20 |
14,180 |
29 |
5 |
4 |
2 |
23 |
| More reasoning doesn't always mean better results - especially for document parsing.
We tested GPT-5.2 at four reasoniā¦ |
@llama_index |
Company |
Original |
2026-02-19 |
9,521 |
21 |
3 |
1 |
2 |
17 |
| š We're running a LlamaAgents contest right now. Throw your hardest documents at our agent builder, and tell us how it ā¦ |
@llama_index |
Company |
Original |
2026-02-18 |
4,772 |
21 |
5 |
0 |
1 |
14 |
| "It's somewhere in the PDF" is not a citation.
Page-level extraction in LlamaExtract gives you:
ā Data mapped to specā¦ |
@llama_index |
Company |
Original |
2026-02-17 |
5,692 |
15 |
4 |
0 |
2 |
6 |
| What if an AI agent could review every invoice against your contracts ā and flag what doesn't match?
That's exactly whā¦ |
@llama_index |
Company |
Original |
2026-02-16 |
6,907 |
18 |
3 |
5 |
1 |
18 |
| š The @posthog team has just rolled out LlamaIndex support for their LLM Analytics, and we built a demo to showcase whaā¦ |
@llama_index |
Company |
Original |
2026-02-13 |
9,621 |
22 |
6 |
1 |
1 |
11 |
| Next week at @DeveloperWeek, fuel up for hackathon success with free breakfast at the same bakery that fed the Superbowā¦ |
@llama_index |
Company |
Original |
2026-02-12 |
2,677 |
10 |
2 |
0 |
0 |
0 |
| 2026 is the year of long-horizon agents. @sequoia predicts that this year, agents will be able to tackle long-horizon tā¦ |
@llama_index |
Company |
Original |
2026-02-12 |
2,968 |
13 |
3 |
2 |
0 |
15 |
| The rise of coding agents is fundamentally changing open source - Our head of OSS @LoganMarkewich breaks down how LLM-pā¦ |
@llama_index |
Company |
Original |
2026-02-11 |
7,794 |
21 |
2 |
0 |
4 |
7 |
| Are you trying to solve high-quality document ingestion for your product?
Gain lessons from the field on how @stackai ā¦ |
@llama_index |
Company |
Original |
2026-02-10 |
16,995 |
28 |
6 |
4 |
2 |
16 |
| Everybodyās talking about @openclaw, so @itsclelia decided to build her own crustacean AI assistant for document workflā¦ |
@llama_index |
Company |
Original |
2026-02-09 |
8,512 |
68 |
9 |
7 |
0 |
51 |
| LlamaExtract citations just got an upgrade: we now show you exactly where extracted data comes from in your documents wā¦ |
@llama_index |
Company |
Original |
2026-02-06 |
30,358 |
68 |
7 |
2 |
1 |
57 |
| Kicking off the Document Agent Olympics. Build a document agent - Win $200 š„
Document agents turn messy PDFs, invoicesā¦ |
@llama_index |
Company |
Original |
2026-02-05 |
12,146 |
32 |
9 |
1 |
3 |
23 |
| Ready to master production-grade multi-agent AI systems in one intensive day? š
We're partnering with @AWS and leadingā¦ |
@llama_index |
Company |
Original |
2026-02-04 |
3,466 |
19 |
5 |
0 |
2 |
7 |
| How does @NTTDATA scale enterprise AI?
They use LlamaIndex to improve document parsing & power RAG applications foā¦ |
@llama_index |
Company |
Original |
2026-02-04 |
8,282 |
10 |
2 |
0 |
2 |
5 |
| Confused about whether to use Skills or MCP tools for your AI agents? We break down the key differences and when to useā¦ |
@llama_index |
Company |
Original |
2026-02-03 |
22,684 |
170 |
28 |
2 |
4 |
123 |
| AI in 60 Seconds ā±ļø
@Experian's Head of AI Innovation shares how AI is shaping the future of fintech, from smarter decā¦ |
@llama_index |
Company |
Original |
2026-02-02 |
5,018 |
20 |
7 |
0 |
0 |
5 |
| Weāve fully revamped our LlamaCloud integration with @n8n_io as part of the LlamaParse v2 + new LlamaCloud SDK launch.
ā¦ |
@llama_index |
Company |
Original |
2026-01-23 |
13,204 |
26 |
4 |
1 |
2 |
16 |
| New LlamaParse v2 API + New SDKs for LlamaCloud are here š¦
LlamaParse API v2 is here with cleaner configuration, strucā¦ |
@llama_index |
Company |
Original |
2026-01-22 |
5,847 |
28 |
8 |
0 |
2 |
18 |
| Congratulations to DungeonMaster AI by @bhupeshsf for winning the MCP hackathon using LlamaIndex! š
One of the closingā¦ |
@llama_index |
Company |
Original |
2026-01-19 |
6,423 |
49 |
11 |
6 |
3 |
40 |
| Files are becoming the primary interface for AI agents to manage context, store conversations, and access skills š
@jeā¦ |
@llama_index |
Company |
Original |
2026-01-15 |
45,790 |
130 |
10 |
8 |
4 |
138 |
| Context engineering isn't just about throwing more data at your LLM - it's about giving it the right context at the rigā¦ |
@llama_index |
Company |
Original |
2026-01-14 |
9,478 |
99 |
8 |
4 |
3 |
76 |
| Can filesystem tools really replace vector search? We put agentic file exploration to the test against traditional RAG.ā¦ |
@llama_index |
Company |
Original |
2026-01-13 |
31,443 |
80 |
10 |
8 |
3 |
70 |
| Tired of wrestling with messy Excel files that break traditional parsers? š
Join our workshop on January 29th at 11 AMā¦ |
@llama_index |
Company |
Original |
2026-01-12 |
7,944 |
18 |
6 |
2 |
2 |
16 |
| A problem we see often: long documents with different pieces of repeating content. Example: a resume book with a cover ā¦ |
@llama_index |
Company |
Original |
2026-01-09 |
11,331 |
15 |
3 |
7 |
2 |
19 |
| Check out the form-filling agent that automates PDF forms using AI by @jerryjliu0 šš¤
Use any fillable PDF with an agenā¦ |
@llama_index |
Company |
Original |
2026-01-07 |
55,754 |
91 |
15 |
6 |
3 |
76 |
| Transform messy Excel files into AI-ready data with LlamaSheetsāour solution for parsing complex spreadsheets while preā¦ |
@llama_index |
Company |
Original |
2026-01-06 |
14,041 |
33 |
6 |
5 |
1 |
47 |
| We're listening šLlamaSheets is in beta and we want your feedback
Spreadsheets in the wild are messyāmerged cells, broā¦ |
@llama_index |
Company |
Original |
2026-01-02 |
35,692 |
33 |
5 |
5 |
2 |
18 |
| Agent Workflows are the fastest and most flexible way to build complex agentic systems, and we put them to the test.
Oā¦ |
@llama_index |
Company |
Original |
2026-01-02 |
16,228 |
213 |
21 |
6 |
2 |
141 |
| As we wrap up 2025, we're incredibly proud of what this team shipped.
We set out to solve document AI reliability and ā¦ |
@llama_index |
Company |
Original |
2025-12-30 |
10,794 |
27 |
6 |
1 |
2 |
11 |
| Get started with pre-built document agent templates that solve real-world problems out of the box.
We've created a colā¦ |
@llama_index |
Company |
Original |
2025-12-29 |
7,323 |
38 |
6 |
2 |
1 |
29 |
| Santa receives thousands of letters every yearāProcessing these manually takes a lot of time, so this year, we're helpā¦ |
@llama_index |
Company |
Original |
2025-12-23 |
4,633 |
27 |
4 |
4 |
0 |
13 |
| We love seeing all of the out of office emails around the holidays! So we thought we'd keep things light this week. We'ā¦ |
@llama_index |
Company |
Original |
2025-12-22 |
4,630 |
27 |
5 |
1 |
0 |
14 |
| Do you want to run coding agents safely, without damaging to your filesystem? š
Last week, we published a blog post andā¦ |
@llama_index |
Company |
Original |
2025-12-19 |
4,301 |
41 |
7 |
2 |
0 |
21 |
| LlamaParse v2 is here: simpler configuration, better performance, and up to 50% cost reduction for document parsing.
Wā¦ |
@llama_index |
Company |
Original |
2025-12-18 |
49,757 |
43 |
5 |
3 |
3 |
35 |
| See how @intelligenceco built Cofounder, an AI chief of staff that turns business documents into agent-ready context atā¦ |
@llama_index |
Company |
Original |
2025-12-17 |
52,626 |
57 |
8 |
3 |
5 |
87 |
| Ever opened a repo and thought:
āWhat does this codebase actually do?ā
āWhere did I put that file?ā š¤
Youāre not alone.ā¦ |
@llama_index |
Company |
Original |
2025-12-17 |
74,646 |
50 |
6 |
3 |
1 |
71 |
| LlamaSplit automatically separates bundled documents into distinct sections so you don't have to manually split them anā¦ |
@llama_index |
Company |
Original |
2025-12-16 |
5,169 |
42 |
8 |
1 |
0 |
40 |
| Secure your coding agents with virtual filesystems and better document understanding.
Building safe AI coding agents rā¦ |
@llama_index |
Company |
Original |
2025-12-15 |
62,941 |
85 |
8 |
5 |
3 |
103 |
| LlamaSheets is our new way to handle complex, messy spreadsheets that come as many sheets disguised as one, multiple reā¦ |
@llama_index |
Company |
Original |
2025-12-11 |
15,029 |
42 |
6 |
2 |
1 |
44 |
| "ask" and you shall receive! SemTools now ships with a dedicated "ask" CLI command
- performs agentic search over documā¦ |
@llama_index |
Company |
Original |
2025-12-10 |
16,212 |
20 |
3 |
2 |
2 |
8 |
| Split documents into distinct sections automatically with our new LlamaSplit API šāļø
We're excited to introduce LlamaSā¦ |
@llama_index |
Company |
Original |
2025-12-09 |
24,706 |
62 |
8 |
1 |
2 |
60 |
| Need to parse multiple PDFs efficiently? Learn how to use LlamaParse with async batch processing.
š Process entire folā¦ |
@llama_index |
Company |
Original |
2025-12-08 |
33,667 |
57 |
6 |
4 |
1 |
70 |
| OCR benchmarks matter, so in this blog @jerryjliu0 analyzes OlmOCR-Bench, one of the most influential document OCR bencā¦ |
@llama_index |
Company |
Original |
2025-12-04 |
24,320 |
51 |
6 |
3 |
1 |
25 |
| Deploy production-ready agent workflows with just one click from LlamaCloud. Here's us deploying the SEC filling extracā¦ |
@llama_index |
Company |
Original |
2025-12-03 |
27,488 |
27 |
3 |
1 |
2 |
15 |
| Calling all community members: Join us this Thursday for an office hours in our Discord server, all about LlamaAgents aā¦ |
@llama_index |
Company |
Original |
2025-12-02 |
3,766 |
18 |
4 |
2 |
0 |
1 |
| Build scripts that automate spreadsheet analysis using coding agents and LlamaSheets to extract clean data from messy Eā¦ |
@llama_index |
Company |
Original |
2025-12-01 |
82,329 |
82 |
11 |
4 |
1 |
93 |
| POV: You're building an agent and it keeps giving weird answers because your PDF parsing is broken š«
This is a great wā¦ |
@llama_index |
Company |
Original |
2025-11-28 |
9,906 |
34 |
7 |
5 |
0 |
35 |
| Stop losing 80% of your data when extracting from long documents with repeating entities like catalogs, tables, and lisā¦ |
@llama_index |
Company |
Original |
2025-11-26 |
30,999 |
19 |
6 |
2 |
1 |
20 |
| Announcing LlamaSheets in beta š„
Transform your messy spreadsheets into AI-ready data with our newest LlamaCloud API š
ā¦ |
@llama_index |
Company |
Original |
2025-11-25 |
78,470 |
71 |
10 |
4 |
2 |
90 |
| Have a LlamaAgent organize your study material: meet StudyLlama, a web app that uses LlamaAgents to help you organize aā¦ |
@llama_index |
Company |
Original |
2025-11-24 |
15,844 |
49 |
7 |
0 |
1 |
45 |
| Extract data from table rows with precision using LlamaExtract's Table Row mode š
LlamaExtract now offers granular extā¦ |
@llama_index |
Company |
Original |
2025-11-21 |
17,502 |
48 |
6 |
2 |
1 |
44 |
| Not another PDF parser š š¤Æ? Here's why AI-powered document parsing is all the rave.
AI document parsing has evolved beā¦ |
@llama_index |
Company |
Original |
2025-11-20 |
29,271 |
152 |
19 |
2 |
3 |
150 |
| Agentic Document Workflows are crucial for AI-driven knowledge work and automation, but they are often treated as blackā¦ |
@llama_index |
Company |
Original |
2025-11-19 |
15,465 |
39 |
8 |
3 |
3 |
30 |
| The @GoogleDeepMind team just dropped Gemini 3, and we at LlamaIndex have day-zero support!
We also made a little demo ā¦ |
@llama_index |
Company |
Original |
2025-11-18 |
5,590 |
41 |
8 |
8 |
0 |
19 |
| LlamaAgents is now in open preview - the fastest way to build, serve, and deploy multi-step document agents that combinā¦ |
@llama_index |
Company |
Original |
2025-11-18 |
25,069 |
79 |
11 |
2 |
1 |
56 |
| Document AI goes beyond traditional OCR to create intelligent systems that read, understand, and act on documents like ā¦ |
@llama_index |
Company |
Original |
2025-11-17 |
43,790 |
266 |
47 |
12 |
6 |
269 |
| Chart OCR just got a major upgrade with our new experimental "agentic chart parsing" feature in LlamaParse šš§Ŗ
Most LLMā¦ |
@llama_index |
Company |
Original |
2025-11-13 |
9,162 |
83 |
14 |
3 |
1 |
77 |
| Build a document understanding agent for SEC filings that uses a multi-step approach with LlamaClassify and Extract to ā¦ |
@llama_index |
Company |
Original |
2025-11-12 |
8,182 |
65 |
10 |
6 |
1 |
64 |
| See how @pathwork scaled their life insurance document processing from 5,000 to 40,000 pages per week using LlamaParse.ā¦ |
@llama_index |
Company |
Original |
2025-11-11 |
25,629 |
25 |
6 |
1 |
1 |
21 |
| There are Vegas parties and there is Late Shift š
Join us for an exclusive re:Invent afterparty that brings together tā¦ |
@llama_index |
Company |
Original |
2025-11-10 |
8,746 |
9 |
5 |
0 |
1 |
4 |
| Trigger your agent workflows directly from your inbox, using our LlamaAgents and @resend webhooksš§
In this demo, we buiā¦ |
@llama_index |
Company |
Original |
2025-11-07 |
20,236 |
18 |
5 |
1 |
1 |
15 |
| We probably shouldn't tell you how to build your own document parsing agents, but we will š®.
AI agents are transforminā¦ |
@llama_index |
Company |
Original |
2025-11-07 |
56,840 |
138 |
21 |
4 |
1 |
198 |
| Here's a common scenario: Your finance team gets emails all day with invoices from partners and expense reports from emā¦ |
@llama_index |
Company |
Original |
2025-11-06 |
11,900 |
28 |
5 |
3 |
1 |
21 |
| Last week, we teamed up with @MongoDB to break down one of the most persistent challenges in production AI systems: turā¦ |
@llama_index |
Company |
Original |
2025-11-05 |
38,230 |
54 |
9 |
2 |
1 |
101 |
| MavenBio transformed complex scientific visuals in biopharma documents into searchable, analyzable intelligence using Lā¦ |
@llama_index |
Company |
Original |
2025-11-04 |
4,043 |
20 |
5 |
7 |
0 |
8 |
| Augment your LlamaIndex agent workflows with memory and persistent states:
Check out @itsclelia's talk at @qdrant_enginā¦ |
@llama_index |
Company |
Original |
2025-11-03 |
5,577 |
24 |
4 |
3 |
2 |
6 |
| LlamaIndex now ships native MCP search with our documentation! - your coding agents can directly access search tools acā¦ |
@llama_index |
Company |
Original |
2025-10-31 |
4,775 |
30 |
4 |
1 |
0 |
21 |
| LlamaIndex is sponsoring + speaking at @wandb ( @CoreWeave ) Fully Connected London (Nov 4ā5), a 2-day event for engineā¦ |
@llama_index |
Company |
Original |
2025-10-30 |
4,234 |
19 |
7 |
0 |
0 |
2 |
| Learn how to implement DRIFT Search with @neo4j and agent Workflows - a hybrid approach that combines global and local ā¦ |
@llama_index |
Company |
Original |
2025-10-29 |
4,352 |
26 |
6 |
2 |
0 |
20 |
| Vibe-code your way from idea to production!
Our OSS engineer @itsclelia tried using Claude Code with high-quality docuā¦ |
@llama_index |
Company |
Original |
2025-10-29 |
3,503 |
21 |
4 |
2 |
0 |
20 |
| Last call! Learn how to transform PDFs, reports, and contracts into intelligent, searchable data pipelines.
Join our wā¦ |
@llama_index |
Company |
Original |
2025-10-28 |
4,569 |
21 |
5 |
0 |
0 |
20 |
| Proud to be named by @TechCrunch & @GreenfieldVC as one of the 60 companies shaping AI. https://t.co/kxbvIlqwDE |
@llama_index |
Company |
Original |
2025-10-27 |
4,438 |
34 |
4 |
1 |
0 |
2 |
| The new "OCR" model by @deepseek_ai represents a vision-based compression strategy that could change how we think aboutā¦ |
@llama_index |
Company |
Original |
2025-10-27 |
25,999 |
98 |
17 |
5 |
1 |
67 |
| š LlamaClassify, our state-of-the-art agentic document classification service, is now available to use also in the Typā¦ |
@llama_index |
Company |
Original |
2025-10-27 |
5,950 |
33 |
3 |
2 |
1 |
22 |
