1. X
  2. LlamaIndex ๐Ÿฆ™
Log inSign up
LlamaIndex ๐Ÿฆ™
3,950 posts
Image
user avatar
LlamaIndex ๐Ÿฆ™
@llama_index
The most accurate agentic OCR platform for production AI. LlamaParse: cloud.llamaindex.ai Docs: developers.llamaindex.ai/python/cloud/
llamaindex.ai
Joined December 2022
33
Following
117.6K
Followers
AffiliatesAffiliatesRepliesRepliesMediaMedia

New to X?

Sign up now to get your own personalized timeline!

Create account

By signing up, you agree to the Terms of Service and Privacy Policy, including Cookie Use.

TermsยทPrivacyยทCookiesยทAccessibilityยทAds Infoยทยฉ 2026 X Corp.
Don't miss what's happening
People on X are the first to know.
Log inSign up
  • LlamaIndex ๐Ÿฆ™ reposted
    user avatar
    Jerry Liu
    LlamaIndex ๐Ÿฆ™
    @jerryjliu0
    Jul 18
    I'm glad people still understand the importance of building high-quality retrieval systems in 2026, especially as the outer models/harnesses are getting better every day. Making agentic retrieval work in production doesn't necessarily require groundbreaking new techniques
    user avatar
    Cerebras
    @cerebras
    Jul 16
    Article cover image
    Article
    How we built our knowledge base
    Authors: @hi_im_isaac_, @learnwdaniel, @gaozenghao note: the interactive version of full technical blog available: https://www.cerebras.ai/blog/how-we-built-our-knowledge-base Employees ask our internal knowledge base more than 15,000...
    46K046K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 17
    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-agenโ€ฆ
    Image
    4.2K04.2K
  • LlamaIndex ๐Ÿฆ™ reposted
    user avatar
    Murtaza Khomusi
    LlamaIndex ๐Ÿฆ™
    @murtazakhomusi
    Jul 16
    vibez are g00d @llama_index
    Image
    00:00
    4.6K04.6K
  • LlamaIndex ๐Ÿฆ™ reposted
    user avatar
    Jerry Liu
    LlamaIndex ๐Ÿฆ™
    @jerryjliu0
    Jul 15
    Article cover image
    Article
    The Best Model Routing is Task Specific
    Model routing is so hot right now. In the last few 1.5 months, OpenRouter shipped Fusion, a compound model that fans your prompt out to a panel of frontier models and synthesizes one answer; Cognition...
    44K044K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 16
    Document processing pipelines are often made up of multiple services: parsing โ†’ chunking โ†’ embeddings โ†’ storage. Until now, LiteParse was only available over REST. That works well for browsers and simple integrations, but itโ€™s not always the best fit for service-to-service
    Image
    9.4K09.4K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 15
    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
    Image
    AWS AI Builder Lab (New York) for Financial Services
    From aicamp.ai
    3K03K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 14
    Your extraction schema is now a conversation away. โฃ ๐Ÿ“„ Upload a doc โ€” the agent drafts the schema from itโฃ ๐Ÿ’ฌ Want changes? Just askโฃ ๐Ÿ“š Or grab a template and goโฃ โฃ Writing JSON Schema by hand? That's over.โฃ โฃ Conversational Extract is live in LlamaParse. Try it now at
    Image
    00:00
    17K017K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 14
    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
    Image
    7.9K07.9K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 14
    We eat docs๐Ÿซข
    Image
    6.4K06.4K
  • LlamaIndex ๐Ÿฆ™ reposted
    user avatar
    Jerry Liu
    LlamaIndex ๐Ÿฆ™
    @jerryjliu0
    Jul 13
    There is a massive opportunity for any startup to build specialized, domain-specific workflows that are at the Pareto frontier in accuracy, cost, and latency. It is clear that not every task requires frontier intelligence (e.g. 5.6 Sol xhigh). Every single task has an optimal
    Image
    13K013K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 13
    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
    Image
    00:00
    21K021K
  • LlamaIndex ๐Ÿฆ™ reposted
    user avatar
    Jerry Liu
    LlamaIndex ๐Ÿฆ™
    @jerryjliu0
    Jul 9
    We comprehensively benchmarked GPT-5.6 on document understanding. At a high-level there's no change between GPT-5.6 Sol and GPT-5.5 in terms of performance over tables, text, charts, layout, and more. The GPT-class of models typically does quite well over table understanding,
    Image
    Image
    user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 9
    @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
    19K019K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 9
    Low user caps in LlamaParse? Gone.๐ŸŽ‰ Every plan โ€” Free through Pro โ€” 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
    Image
    3.6K03.6K
  • user avatar
    LlamaIndex ๐Ÿฆ™
    @llama_index
    Jul 8
    Introducing: Granular job tracking and cost attribution in LlamaParse ๐Ÿฆ™ 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
    Image
    9.7K09.7K
Advertisement
Advertisement