---
type: "raw_signal"
id: "liteparse-updates-september-2026-8b1194"
slug: "liteparse-updates-september-2026-8b1194"
title: "LiteParse Updates: September 2026"
description: "LlamaIndex’s September 2026 LiteParse release reports a 20–25% reduction in PDFium text-extraction time, with LiteParse 2.14.6 averaging 2.76 ms/page for text extraction and 3.94 ms/page for markdown rendering on its real-world PDF set with OCR disabled."
retrieval_nugget: "LlamaIndex’s September 2026 LiteParse release reports a 20–25% reduction in PDFium text-extraction time, with LiteParse 2.14.6 averaging 2.76 ms/page for text extraction and 3.94 ms/page for markdown rendering on its real-world PDF set with OCR disabled."
observed_at: "2026-09-22"
record_date: "2026-09-22"
date_kind: "observed_at"
why_it_matters: "Source: https://www.llamaindex.ai/blog/liteparse-updates-september-2026"
novelty: "notable"
verification_level: "source-linked"
signal_type: "release"
source_platform: "llamaindex.ai"
topics: []
entities: []
related_patterns: []
source_url: "https://www.llamaindex.ai/blog/liteparse-updates-september-2026"
source_urls: ["https://www.llamaindex.ai/blog/liteparse-updates-september-2026"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:liteparse-updates-september-2026-8b1194"
status: "published"
visuals: []
routes: {"html":"https://newruntime.com/signals/liteparse-updates-september-2026-8b1194/","markdown":"https://newruntime.com/signals/liteparse-updates-september-2026-8b1194.md","json":"https://newruntime.com/signals/liteparse-updates-september-2026-8b1194.json"}
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
---

# LiteParse Updates: September 2026

## Retrieval answer

LlamaIndex’s September 2026 LiteParse release reports a 20–25% reduction in PDFium text-extraction time, with LiteParse 2.14.6 averaging 2.76 ms/page for text extraction and 3.94 ms/page for markdown rendering on its real-world PDF set with OCR disabled.

LlamaIndex’s September 2026 LiteParse release reports a 20–25% reduction in PDFium text-extraction time, with LiteParse 2.14.6 averaging 2.76 ms/page for text extraction and 3.94 ms/page for markdown rendering on its real-world PDF set with OCR disabled. The release also adds markdown blocks with page bounding boxes and an `is-complex` API for detecting scans, garbled text, text coverage, and layout complexity. The company reports improved table results, including 0.693 to 0.818 on OpendataLoader-Bench.

Source: https://www.llamaindex.ai/blog/liteparse-updates-september-2026

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)