Turn emails into revenue with Brew. No credit card, free credits to try.
llamaindex.ai · newsletter
Explore this email design and adapt it to your own brand. Review the copy, links, and offer before sending.
Email Newsletter 1200x360 2026-07-29
Hi there, LlamaParser!
Frontier-model week. Claude Opus 5, Gemini 3.6 Flash, and Kimi K3's open weights all landed within about 96 hours of each other, and the group chat barely survived. We kept our heads down and shipped anyway: agentic_plus extract went GA, forms parsing hit beta, and LiteParse finally dropped its ImageMagick dependency (a moment of silence, please). Here's the rundown...
Discover LlamaParse — most accurate document ingestion API for your agents.
GET API KEY
GET IN TOUCH
🚢 Product Updates
Batch Processing is now a simple button click — Parse or extract 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. See how it works →
LlamaParse now speaks Go, Java, and shell — you asked, we delivered: new Go and Java SDKs, plus a CLI join Python and TypeScript. Parse a document in a few lines from either language, or straight from your terminal.
🤩 Community Updates
Webinar: From Complex Docs to Decision-Ready Context for Financial Services Agents — July 30, 9:00–9:45am PT — Solution Architect, Harsh Dindigal runs 3 financial workflows (PE investment analysis, corporate lending, mortgage) through parsing +extraction: dense tables kept intact, schema-driven extraction with page-level citations and per-field confidence, and low-confidence values routed to review. RSVP →
Ai4 2026 — August 3–6, Las Vegas — the summer's biggest enterprise AI gathering. Stop by our booth win prizes to help beat the heat. Details →
🔗 AI News
Claude Opus 5 is here — Anthropic's flagship refresh. At this pace, "frontier" is a weekly release cadence.
Kimi K3 weights are public — Moonshot finally released them, and the open-weight gap keeps shrinking.
Gemini 3.6 Flash is out — and already on ParseBench — Results: 3.6 Flash drops 14% on charts vs its predecessor, and 3.5 Flash Lite trades 12% on tables for 11% on layout. Newer isn't uniformly better. See the board →
Gradient_Newsletter
TRY FOR FREE
SEE PRICING
Building a new agent? Get in touch with our team
Need support? Join our Discord
Check out our GitHub for the latest code releases and documentation.
Thanks for reading this week's newsletter!
We are trying a new format and would love your feedback. Did we miss anything? Feel free to reply directly or email news@llamaindex.ai with your input.
LlamaIndex-logo
LlamaIndex, 405 Howard Street, San Francisco, California 94105, United States
Unsubscribe
Manage preferences
github
discord
X
YouTube
Outline_Text_Newsletter