Skip to content
View original post on X: LlamaIndex 🦙Official
Published
36/100

LlamaIndex integrates MiniCPM-OCR into its LiteParse document parser

AILlamaIndex says its open-source LiteParse document parser now integrates with MiniCPM-OCR from OpenBMB, a lightweight OCR model that runs on cropped layout regions. The company says MiniCPM-OCR beats Gemini 3.5 Flash Lite and PaddleOCR-VL-1.6 on content faithfulness on ParseBench.
LlamaIndex 🦙Verified on XOfficial
@llama_index
View on X

LiteParse integrates with MiniCPM-OCR from @openBMB 🚀

MiniCPM-OCR is a new lightweight OCR model that performs OCR after capturing cropped layout regions. On ParseBench, it beats Gemini 3.5 Flash Lite and PaddleOCR-VL-1.6 on content faithfulness.

LiteParse is our ultra-fast OSS document parser. When OCR is required, LiteParse lets you connect any existing OCR model.

See the integration: https://github.com/run-llama/liteparse/tree/main/ocr/minicpmocr

Source details

LlamaIndex 🦙 · x.comPublished · added here

Original title: LiteParse integrates with MiniCPM-OCR from @openBMB 🚀

Topics

Open-source ecosystemChina AIProduct updates