Skip to content

Conversation

@jioffe502
Copy link
Collaborator

Description

This introduces the first production example for our new UDF/Lambda implementations, featuring a structural text splitter UDF that demonstrates how to extend the NV-Ingest pipeline with custom processing logic for markdown documents.

We've created comprehensive documentation and examples showing UDF usage across CLI, Python API, and pipeline integration to showcase the functionality's usefulness for custom document processing tasks.

One note is that the final location for customer UDFs remains under discussion. Notebook for a full detailed example will be coming as well.

Checklist

  • I am familiar with the Contributing Guidelines.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.
  • If adjusting docker-compose.yaml environment variables have you ensured those are mimicked in the Helm values.yaml file.

@jioffe502 jioffe502 requested a review from a team as a code owner August 15, 2025 20:30
@jioffe502 jioffe502 requested review from jdye64 and removed request for a team August 15, 2025 20:30
@copy-pr-bot
Copy link

copy-pr-bot bot commented Aug 15, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@drobison00 drobison00 requested a review from nkmcalli August 15, 2025 22:07
@drobison00 drobison00 self-requested a review August 18, 2025 18:04
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants