LiteParse v2.14.6 Hits 2.8ms/Page, 1.5x Faster Than Nearest Local Parser

llama_index · x · 2026-09-23

LlamaIndex released LiteParse v2.14.6, making text-based PDF parsing 25% faster. On realistic documents it processes pages at 2.8ms/page — 1.5x faster than the next-fastest local parser. The open-source tool (12.4k GitHub stars) runs locally in Python, Node.js, Rust, or directly in the browser, offering high-quality spatial text parsing with bounding boxes without proprietary LLM features. A strong pick for local PDF-to-Markdown pipelines in RAG/agent workflows.

Related event: LiteParse Gets 25% Faster, Parses a PDF Page in 2.8ms(2 posts)→

Original post →

More from coding & agent

coding & agent channel →