Tag
Jerry Liu promotes LlamaParse and LlamaAgents for large-scale document extraction, emphasizing LLM evals and hillclimbing for accuracy and cost. He also connects FDE work with evals and RL environments.
LlamaIndex introduces a new LlamaParse feature that automatically extracts complex form fields into structured JSON without requiring a predefined schema, simplifying document form processing.
LlamaIndex shares highlights from the final day at Ai4 conference, including CEO Jerry Liu's keynote speech and an executive dinner with AI leaders.
LiteParse now supports extracting structured data from PDFs—form fields, checkbox states, annotations, images, vector graphics, and word-level bounding boxes—without a vision model, plus complexity signals to route harder pages to tools like LlamaParse.
LlamaIndex introduces Parse Gateway, a page-level document OCR router that estimates each page's complexity and routes it to the appropriate parsing tier (LiteParse or LlamaParse), balancing cost, latency, and quality.
LiteParse is a fast, lightweight, open-source PDF parsing tool written in Rust, supporting image-to-PDF conversion natively and providing spatial text parsing with bounding boxes, available via multiple packages (Rust, Node.js, Python, WASM).
Jerry Liu highlights the engineering challenges of productionizing agentic retrieval systems, emphasizing that success depends on careful tuning of chunking, synchronization, reranking, and tool API design rather than novel techniques.
LlamaIndex has created a Retrieval Harness for modern agentic retrieval, providing a persistent data pipeline for connecting, indexing, and querying large knowledge bases with tools like semantic search and regex grep, allowing agents to autonomously navigate knowledge bases.
Built a fast PDF parsing service using LiteParse, an open-source tool by LlamaIndex, with help from Cursor AI.
LiteParse v2.1 is released, delivering the fastest LLM-free PDF-to-markdown conversion with top benchmark scores among model-free tools.
LlamaIndex's blog post describes building a custom LiteParse skill for Claude agents that reduced cost per question by 37% and improved answer quality by analyzing agent traces to fix inefficiencies in PDF parsing.
LiteParse is a fast, open-source document parser written in Rust that provides high-quality spatial text extraction with bounding boxes, supporting multiple languages and platforms for AI document workloads.
LlamaIndex founder Jerry Liu discusses the company's strategic pivot from a general AI framework to focusing on providing high-accuracy context extraction from enterprise documents like PDFs and PowerPoints, aiming for 95%+ accuracy for agentic workflows in legal, insurance, and finance.
Jerry Liu of LlamaIndex announces a $1M+ billboard campaign in SF promoting their PDF parsing service for AI agents, and lists their booth appearances at upcoming tech conferences.
Jerry Liu, CEO of LlamaIndex, discusses on the Venture with Grace podcast why data infrastructure is crucial for the agentic AI boom, emphasizing that AI agents need access to the right data at the right time.
Jerry Liu announces a revamped LiteParse, a fast PDF parser that provides bounding boxes for audit trails, with sample demos available.
LlamaIndex demonstrates how to automate a loan underwriting pipeline using LlamaParse to extract structured data from financial PDFs, with cross-document analysis and human-in-the-loop review.
Nasdaq features an interview with Llama Index CEO Jerry Liu, discussing the company's document understanding and OCR technologies powering enterprise AI agents, in partnership with Wing VC's Enterprise Tech 30 list.
Jerry Liu announces that all research, engineering, and product team members at LlamaIndex are now Members of Technical Staff, reflecting the collapse of traditional roles due to AI and coding agents.
At AI Engineer Singapore, LlamaIndex presented a 90-minute workshop on building agentic workflows to extract information from enterprise PDFs; slides will be shared soon.