LlamaIndex
LlamaIndex is where developers come to build document agents. We bring together industry-leading agentic OCR and a low-code workflow builder to power intelligent agents that read and reason over complex documents, adapt to business logic, and scale reliably to production. Our SDK is downloaded more than 25M+ every month and used by the fastest growing AI companies and the Fortune 50.
Channel created: May 05, 2023
28,200
Subscribers
137
Total Videos
1,025,487
Total Views
178
Videos
Recent Videos
View All Videos
Build a Financial Due Diligence Agent with LiteParse
Financial documents are some of the messiest data sources your agents will ever encounter. In this hands-on workshop, our Head of Open Source, Logan, will walk through building a financial resear...
Deep Dive into Semantic Formatting Score: A New Metric for Meaningful Document Formatting
Most parsers treat formatting as cosmetic and strip it. But some formatting carries meaning: - A strikethrough price is not the current price - A superscript "1" is a footnote reference, not the n...
Deep Dive into ChartDataPointMatch: A New Metric for Evaluating Parsing Accuracy on Charts
ParseBench, the first document OCR benchmark for AI agents, introduces 5 novel metrics for measuring document parsing accuracy. In this video we do a deep dive into parsing charts using our new met...
Deep Dive into Content Faithfulness: A new metric for ensuring text accuracy
Parsebench is the first document OCR benchmark for AI agents. With its release we defined five new metrics for determining the accuracy of your document parser. In this video, we dive deep into the...
Deep Dive into TableRecordMatch: A New Metric for Evaluating Parsing Accuracy on Complex Tables
ParseBench introduces 5 novel metrics for measuring document OCR accuracy for AI agents. For tables specifically, we introduce TableRecordMatch — a metric that evaluates tables the way downstream s...
Introducing ParseBench: The First Document Parsing Benchmark for AI Agents
LlamaIndex is open sourcing the first document OCR benchmark for the agentic era, ParseBench. Document parsing is the foundation of every AI agent that works with real-world files. But until now, t...
LlamaParse vs LLMs: Live OCR Battleground
Everyone thinks you can just throw a PDF at an LLM and call it done. We're about to prove them wrong — live. LlamaIndex showcases here a head-to-head battleground where we pit the leading LLMs agai...
LiteParse: Local Document Parsing for AI Agents
LiteParse is a new open-source parsing CLI tool from LlamaIndex. It open-sources our core parsing tech from LlamaParse to give users a fast and local experience. - text parsing from a variety of fo...
Scaling Document Ingestion for AI Agents Lessons from the field with StackAI
How do you build AI agents that actually understand enterprise documents in production? In this video, you'll learn how StackAI, creators of a leading enterprise agent platform, use LlamaParse to ...
Build Agents From Your Files (with LlamaAgents Builder)
In this quick demo, Clelia walks you through the new file upload feature in LlamaAgents Builder. Upload example files to give the agent a concrete starting point — it reads them and uses them to co...