cheshire-cat-ai / core

Production ready AI agent framework

https://cheshirecat.ai

GNU General Public License v3.0

2.14k stars 282 forks source link

Replace equals with levenshtein method #862

Closed lucagobbi closed 1 week ago

lucagobbi commented 1 week ago

Description

As discussed in issue #859, we should avoid strict equality checks for classified strings and instead use a fuzzy approach like the Levenshtein distance. To prevent outliers from being forced into the nearest label, a threshold is set at 0.5. This is fairly permissive but should be suitable for most use cases.

Let's try it out

Type of change

[X] Bug fix (non-breaking change which fixes an issue)
[ ] New feature (non-breaking change which adds functionality)
[ ] Breaking change (fix or feature that would cause existing functionality to not work as expected)
[ ] This change requires a documentation update

Checklist:

[X] My code follows the style guidelines of this project
[X] I have performed a self-review of my own code
[X] I have commented my code, particularly in hard-to-understand areas

pieroit commented 1 week ago

Looks reasonable I'll test thanks @lucagobbi !