# Docling v2.149.0 adds MiniCPM-OCR preset for PDF processing

> Original title: Excited to see MiniCPM-OCR integrated into Docling! 🚀💙 Thanks for making open-source document processing even more accessible! 🙌

- Source: OpenBMB
- Published: 2026-11-10T01:40:38.000Z
- Bad Influence: https://badinfluence.news/items/b37q7dhgzqi89cgjnc2pwtuwc
- Original: https://x.com/OpenBMB/status/2119968444238217459

## Summary

Docling v2.149.0 adds a minicpm_ocr preset for OpenBMB's 1.3B MiniCPM-OCR model, which handles English and Chinese text. Users can run it on one consumer GPU with docling doc.pdf --pipeline vlm --vlm-model minicpm_ocr. The release also adds an opt-in --use-embedded-picture-images flag and ASR support on mlx-audio, and fixes the --vlm-model flag, which now switches to the VLM pipeline.

## Post

Excited to see MiniCPM-OCR integrated into Docling! 🚀💙 Thanks for making open-source document processing even more accessible! 🙌

## Quoted post @Khaled865412521

> Docling v2.149.0 just shipped and who should update depends on what you feed it 📄
> 
> Building RAG over PDFs?
> New opt-in --use-embedded-picture-images pulls a figure straight out of the PDF at native pixels instead of a rendered crop. If the region also holds text or vector shapes it falls back to the crop
> 
> Need OCR on one consumer GPU?
> New minicpm_ocr preset for OpenBMB's 1.3B MiniCPM-OCR (English + Chinese):
> docling doc.pdf --pipeline vlm --vlm-model minicpm_ocr
> 
> Transcribing audio on a Mac?
> ASR can now run on mlx-audio with no torch, and Granite Speech recordings get split into ~30s windows
> 
> ⚠️ Scripts: --vlm-model X now really switches to the VLM pipeline (it used to be silently ignored), and pairing it with --pipeline standard now errors
> 
> pip install -U docling
> 
> https://github.com/docling-project/docling/releases/tag/v2.149.0

https://x.com/Khaled865412521/status/2119645305301856497