Build an AI Document Processing Pipeline for RAG - OCR, Image to Text, VLM, Chunking

Build an AI Document Processing Pipeline for RAG - OCR, Image to Text, VLM, Chunking

Venelin Valkov via YouTube Direct link

00:00 - Welcome

1 of 13

1 of 13

00:00 - Welcome

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Build an AI Document Processing Pipeline for RAG - OCR, Image to Text, VLM, Chunking

Automatically move to the next video in the Classroom when playback concludes

  1. 1 00:00 - Welcome
  2. 2 01:01 - Document processing pipeline
  3. 3 02:07 - Full-text tutorial and source code on MLExpert.io
  4. 4 02:41 - Docling
  5. 5 03:53 - PDF document sample
  6. 6 04:38 - Notebook setup
  7. 7 05:45 - PDF to Markdown OCR, layout analysis, image to text
  8. 8 08:45 - Visual inspection
  9. 9 11:02 - Image annotations
  10. 10 14:37 - Chunking with Ollama and Gemma 3
  11. 11 19:58 - Contextual enrichment retrieval
  12. 12 21:50 - Test the pipeline with simple RAG
  13. 13 24:42 - Conclusion

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.