Data Prep Kit / Docling Examples

🔗 bit.ly/dpk-examples

Sujee Maniyam (AI Developer Advocate)
sujee@sujee.dev   •   sujee.dev   •   linkedin   •   @sujee_dev

---

Jump to:

• About
• Events
• Examples

About

This repo has example code for preparing data using Data Prep Kit, Docling and other tools.

Data Prep Kit can help you with preparing data for machine learing applications.

Docling is a powerful, versatile document processor.

---

Events

• Data Prep Kit workshop - Latest
• 2025-11-20: SF QCon workshop: Open Source Rag Pipeline With Docling + Data Prep Kit + Milvus + Open LLMs
• 2025-02-13: AI Alliance Office hour - Workshop : RAG with Data Prep Kit + Milvus + Granite
• 2025-02-06: AI Alliance Office hour - Data Preparation with Data Prep Kit
• 2025-01-30: AI Alliance Office hour - Data Preparation with Docling
• 2024-10-21: Workshop @ IBM Tech XChange , Las Vegas, NV
• 2024-09-21: Hands on RAG workshop @ Data Riders meetup - Hacker Dojo, Mountain View, CA
• 2024-08-08: Open Source AI Demo Nigh, San Francisco, CA

Examples

• docling examples
  • getting started | performing OCR
• Data Prep Kit Examples
• Milvus
  • A quick start of Milvus - Run an embedded milvus
  • Vector search of movie plots using Milvus - load movie data, index it with embeddings, upload the data into milvus and run semantic queries
• RAG - open source RAG pipeline/stacks
  • RAG for PDF documents
• Chat (RAG) with website is now a new project allycat
  • older example here

---

Dev Notes

Creating requirements.txt using uv

When we update uv deps, run this command to update requirements.txt

uv export --frozen --no-hashes --no-emit-project --no-default-groups --output-file=requirements.txt