Skip to content

A fast, helpful, and open-source document parser

Revise README to streamline LiteParse description

Logana3cd70d1a575
diff --git a/README.md b/README.md
index b7fcbcc..4a882ab 100644
--- a/README.md
+++ b/README.md
@@ -4,25 +4,6 @@
[![npm version](https://img.shields.io/npm/v/@llamaindex/liteparse.svg)](https://www.npmjs.com/package/@llamaindex/liteparse)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-LiteParse is a lightweight, open-source document parser built for developers who need fast, local extraction from clean, well-structured files. It handles common document formats — PDFs, DOCX, HTML, and more — with minimal setup and no API calls required.
-
-**LiteParse is great when:**
-- Your documents are relatively straightforward (no complex tables, mixed layouts, or scanned pages)
-- You want to run parsing locally without sending data to an external service
-- You're prototyping or building a lightweight pipeline and don't need enterprise-grade accuracy
-
-**Hitting the limits of local parsing?**
-For complex documents — dense tables, multi-column layouts, charts, handwritten text, or
-scanned PDFs — you'll get significantly better results with [LlamaParse](https://developers.llamaindex.ai/python/cloud/llamaparse/?utm_source=github&utm_medium=liteparse),
-our cloud-based document parser built for production RAG pipelines. LlamaParse handles the
-hard stuff so your models see clean, structured data.
-
-> 👉 [Sign up for LlamaParse free](https://cloud.llamaindex.ai?utm_source=github&utm_medium=liteparse)
-
-## Overview
-
-LiteParse is a standalone OSS PDF parsing tool focused exclusively on **fast and light** parsing. It provides high-quality spatial text parsing with bounding boxes, without proprietary LLM features or cloud dependencies. Everything runs locally on your machine.
-
LiteParse is a standalone OSS PDF parsing tool focused exclusively on **fast and light** parsing. It provides high-quality spatial text parsing with bounding boxes, without proprietary LLM features or cloud dependencies. Everything runs locally on your machine.
**Hitting the limits of local parsing?**
@@ -35,7 +16,6 @@ hard stuff so your models see clean, structured data and markdown.
## Overview
-
- **Fast Text Parsing**: Spatial text parsing using PDF.js
- **Flexible OCR System**:
- **Built-in**: Tesseract.js (zero setup, works out of the box!)