About this Catalog

Alfresco Addons Catalog is a community-driven space where customers, partners, and community members can showcase add-ons, solutions, and real-world use cases built around Alfresco. Browse the catalog to quickly discover extensions and ideas that may inspire or accelerate your projects.


Want to share your own work?

Click “+ Submit Entry” to suggest a new listing, every submission is reviewed by the Hyland Team before it appears here.

Alfresco TEngine Convert to Markdown

by Angel Borroy

Community

AI-powered Alfresco Transform Engine that converts PDF files to clean, richly-described Markdown using Docling, with optional LLaVA multimodal image captioning via Ollama.

screenshot

Compatibility ACS 25.x, ACS 26.x

License Apache-2.0

Keywordstransformer, pdf, markdown, ai, docling, ollama

Download

About

Transforms application/pdftext/markdown using Docling.

CapabilityDetails
PDF to MarkdownExtracts text and layout, turning each page into structured Markdown
Image handlingplaceholder, embedded (base64), referenced (PNG), or described (LLaVA caption)
Multilingual captionsEnglish, Spanish, French, German, Italian, Portuguese when using described mode
Alfresco‑readyImplements the Alfresco Transform Core SPI (TransformEngine & CustomTransformer)
ContainerisedMulti‑stage Docker build (Java 17 + Python 3.11), published to Docker Hub as angelborroy/alf-tengine-convert2md
ACS 26.1 readyReady-to-use docker-compose-261.yaml included

Image captioning (image=described) requires a local Ollama daemon with llava pulled.

Update Entry Request Removal