Skip to content

Conversation

@Negiiiin
Copy link
Collaborator

@Negiiiin Negiiiin commented Oct 21, 2025

PR Type

[Feature]

Short Description

Adding the wikipedia capabilities and comparing them with our own generated capabilities.


This change is Reviewable

@Negiiiin Negiiiin requested a review from afkanpour October 28, 2025 16:38
Copy link
Collaborator

@afkanpour afkanpour left a comment

Choose a reason for hiding this comment

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

Please update the codebase README describing the new scripts and a sample command to run each one

@afkanpour reviewed 5 of 5 files at r1, all commit messages.
Reviewable status: all files reviewed, 3 unresolved discussions (waiting on @Negiiiin)


wikipedia/wikipedia_scraper.py line 174 at r1 (raw file):

    user_prompt = f"Please categorize this mathematical concept into one of the 10 areas listed above:\n\n{description}"
    

Please remove instances of trailing whitespace in all scripts.

Code quote:

···

wikipedia/wikipedia_scraper.py line 539 at r1 (raw file):

                if self.save_entry_to_file(entry):
                    saved_count += 1
                    logger.info(f"✅ Successfully saved {entry['name']}")

Please remove this and similar items.

Code quote:


wikipedia/static_vs_generated.py line 336 at r1 (raw file):

        area_bullets = [f"- {area.name}" for area in areas]
        
        sys_prompt = (

Please move all prompts to a separate script.

Code quote:

ys_prompt

Copy link
Collaborator

@afkanpour afkanpour left a comment

Choose a reason for hiding this comment

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

:lgtm:

@afkanpour reviewed 5 of 5 files at r2, all commit messages.
Reviewable status: all files reviewed, 3 unresolved discussions (waiting on @Negiiiin)

@Negiiiin Negiiiin merged commit 5735f3f into VectorInstitute:main Nov 7, 2025
1 of 2 checks passed
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