Skip to content

docs: add simple usage example for retrieval_core task #32

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

Open
AviralAv03 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

docs: add simple usage example for retrieval_core task #32

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
0d1984d
docs: add simple usage example for retrieval_core task
AviralAv03 Apr 11, 2026
a21e2db
docs: clarify probabilistic wording based on review
AviralAv03 Apr 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions docs/usage/retrieval_core.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,14 @@
# Retrieval Core Task Usage
## What it does
The `retrieval_core` task acts like a mini search engine. It generates a bunch of fake text documents and then calculates how many times specific words appear across those documents.
Instead of checking every single file, it uses math to sample just a few of them to estimate the final results. This is great for testing probabilistic search approximations.
## Example Script

@Aaryan-Dadu Aaryan-Dadu Apr 11, 2026

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

Please add demo screenshot of this script in the PR

Here's how you can run the task in Python to generate some fake data and solve it:
```python
from chuck.tasks import retrieval_core
# 1. Generate 100 fake documents
payload = retrieval_core.generate(count=100, seed=42)
# 2. Run the task to search through them
solution = retrieval_core.solve(payload)
# 3. Check the results
print(solution)
Loading