Latest AI and tech news

LlamaIndex Newsletter 6-10-26

Announcing Granular Bounding Boxes in LlamaParse

Designing a Visual Document Intelligence Workflow with LlamaParse

Extract Contract Metadata: Building Structured Intelligence from Legal Documents

How to Make a PDF Searchable: The Fast Methods, and What "Searchable" Really Gets You

Is grep all you need? Lexical VS Sematic Search for Agents

LiteParse v2.0 Runs Everywhere

LlamaIndex Newsletter 5-26-26

Building a Financial Document Pipeline with LlamaParse

OCR for Insurance Documents: Transforming Claims Processing

Loan Document Automation: Why the Extraction Layer Makes or Breaks Your Pipeline

Passport OCR: Why the MRZ Is More Than Two Lines of Text

AI-Powered Document Analysis for Financial Compliance in Fintech

OCR in Healthcare: Automating Patient Data Extraction Without Breaking HIPAA

Medical Claims Processing Systems: Why Most Claim Denials Start at Document Intake

LlamaIndex Newsletter 5-19-26

Building a Financial Due Diligence Agent with LiteParse

OCR for KYC: Why Standard Text Extraction Falls Short of Compliance Requirements

Mortgage Document Automation: Transforming Loan Processing

Income Verification API: How to Automate Document-Based Income Checks at Scale

KYC Automation: How to Replace Manual Verification with Scalable, Compliant Workflows

LiteParse Server: Self-Hostable Document Parsing

LlamaParse MCP: Agentic OCR tools for your AI agents

Build Automated Loan Income Verification with LlamaParse + Claude Agent SDK

LlamaIndex and Kaggle launch a new Document OCR leaderboard for AI agents

How LiteParse Turns PDFs Into Text: A deep-dive into the grid projection algorithm

Why Single-Pass Extraction Fails and What Deep Extraction Actually Solves