Let's Talk About Raw Documents - Extracting Structured Data for ML Pipelines

Let's Talk About Raw Documents - Extracting Structured Data for ML Pipelines

MLOps.community via YouTube Direct link

[] Introduction to Crag Wolfe

1 of 25

1 of 25

[] Introduction to Crag Wolfe

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Let's Talk About Raw Documents - Extracting Structured Data for ML Pipelines

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

  1. 1 [] Introduction to Crag Wolfe
  2. 2 [] Agenda
  3. 3 [] Unstructured.io introduction
  4. 4 [] Then open-source community
  5. 5 [] The goal
  6. 6 [] Rapidly build custom preprocessing API
  7. 7 [] Staging
  8. 8 [] Demo
  9. 9 [] Developer quick start
  10. 10 [] SEC Filing Section Pipeline
  11. 11 [] Section 1: Pulling in Raw Documents
  12. 12 [] Section 2: Reading the Document
  13. 13 [] Section 3: Custom Partitioning Bricks
  14. 14 [] Section 4: Cleaning Bricks
  15. 15 [] Section 5: Staging Bricks
  16. 16 [] Section 6: Define the Pipeline API
  17. 17 [] SEC Sentiment Analysis Model notebook
  18. 18 [] Stage for transformers
  19. 19 [] Training a summarization model with Unstructured + Argilla + Huggingface
  20. 20 [] Crag's previous engineering experience
  21. 21 [] Deciding what to tackle next
  22. 22 [] Editing documents
  23. 23 [] Scaling issues
  24. 24 [] Moving out of NLP
  25. 25 [] Wrap up

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.