Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: add question generation for imagine la and bem dataset #144

Merged
merged 1 commit into from
Dec 2, 2024
Merged

feat: add question generation for imagine la and bem dataset #144

merged 1 commit into from
Dec 2, 2024

Conversation

ccheng26
Copy link
Contributor

Ticket

https://navalabs.atlassian.net/browse/DST-588

Changes

Updated notebook with following
add dataset key with multiselect widget
change chunk/document selection to radio widget

Testing

Run make notebook
navigate to http://localhost:8888/
copy and paste token in URL found in terminal
run notebook file in notebooks/question_answer_generator/q_a_generation.ipynb
question_answer_pairs.csv should be created with question, answer, document_name, document_source, dataset, document_id, and chunk_id fields

@ccheng26 ccheng26 requested a review from KevinJBoyer November 26, 2024 22:01
@ccheng26 ccheng26 marked this pull request as ready for review November 26, 2024 22:01
@github-actions GitHub Actions
Copy link

☂️ Python Coverage

current status: ✅

Overall Coverage

Lines Covered Coverage Threshold Status
3266 2921 89% 80% 🟢

New Files

No new covered files...

Modified Files

No covered modified files...

updated for commit: 83be073 by action🐍

KevinJBoyer
KevinJBoyer approved these changes Dec 2, 2024
View reviewed changes
Copy link
Contributor

@KevinJBoyer KevinJBoyer left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Works great, thank you! Left one comment where I think there might be a bug -- and don't forget to add a title to this PR (it's currently just feat:) before merging :)

app/notebooks/question_answer_generator/q_a_generation.ipynb
"question_gen_selection = input(\"Generate questions by chunk or document?\")"
"question_dataset = widgets.SelectMultiple(\n",
" options=['Imagine LA', 'CA EDD', 'BEM'],\n",
" value=['Imagine LA', 'CA EDD' ],\n",
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
" value=['Imagine LA', 'CA EDD' ],\n",
" value=['Imagine LA', 'CA EDD', 'BEM' ],\n",

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

For the value assignment here, it's what's selected by default, did we also want the BEM option selected too?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Oops I misunderstood, no, the code as you've written makes sense to me in that case!

@ccheng26 ccheng26 changed the title feat: feat: add question generation for imagine la dataset Dec 2, 2024
@ccheng26 ccheng26 changed the title feat: add question generation for imagine la dataset feat: add question generation for imagine la and bem dataset Dec 2, 2024
@ccheng26 ccheng26 merged commit 3803803 into main Dec 2, 2024
4 checks passed
@ccheng26 ccheng26 deleted the q_a_benefit_hub branch December 2, 2024 15:00
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@KevinJBoyer KevinJBoyer KevinJBoyer approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@ccheng26 @KevinJBoyer