Soham Internship Pipeline#1435
Open
SohamDasgupta91 wants to merge 21 commits into
data-prep-kit:devdata-prep-kit/data-prep-kit:devfrom
SohamDasgupta91:SohamDasgupta91-patch-1SohamDasgupta91/data-prep-kit:SohamDasgupta91-patch-1Copy head branch name to clipboard
Open
Soham Internship Pipeline#1435SohamDasgupta91 wants to merge 21 commits intodata-prep-kit:devdata-prep-kit/data-prep-kit:devfrom SohamDasgupta91:SohamDasgupta91-patch-1SohamDasgupta91/data-prep-kit:SohamDasgupta91-patch-1Copy head branch name to clipboard
SohamDasgupta91 wants to merge 21 commits into
data-prep-kit:devdata-prep-kit/data-prep-kit:devfrom
SohamDasgupta91:SohamDasgupta91-patch-1SohamDasgupta91/data-prep-kit:SohamDasgupta91-patch-1Copy head branch name to clipboard
Conversation
swith005
requested changes
Aug 27, 2025
swith005
left a comment
Collaborator
There was a problem hiding this comment.
@SohamDasgupta91 thanks for submitting, but there's a lot of information that should be removed from checking in - such as username/passwords/tokens, etc. Please have these removed.
Would be better to include a markdown cell detailing where/how to retrieve this info for replicating the example
swith005
requested changes
Aug 28, 2025
swith005
left a comment
Collaborator
There was a problem hiding this comment.
As discussed, please update PR with the following changes:
- Add requirements.txt file for libraries necessary to work
- Add markdown for prerequisites before running (i.e. getting wikimiedia account + token, hugging face token, setting up venv and installing specific version of dpk + requirements, etc. )
- Add markdown for introduction and sections explaining what this notebook does, and the metrics/results
- Ensure LLMs come from public repository (i.e. hugging face)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why are these changes needed?
End to end pipeline that prompts a granite model to get article titles, passes them through the Wikimedia API and runs RAG evaluation.
Related issue number (if any).