February 26-28, 2025
Montreal, Canada
Efficient Code Searching for Large Codebases
This session covers how embedding models can retrieve relevant method matches more effectively than traditional search. We’ll explore real-world examples, like migrating identity providers, where we can use embeddings to identify all HTTP authorization headers across libraries. Additionally, we’ll cover how the top-k selection technique improves search speed and accuracy, by leveraging code-as-data models which use Lossless Semantic Trees.
Justine Gehring
Gologic
Justine Gehring is a specialist in the field of ML for code and obtained her master's from McGill and Mila where her research focused on generating code under challenging circumstances such as library-specific code. Previously, Justine was a research engineer at Moderne, focusing on leveraging AI for large-scale code refactoring and impact analysis. Presently, she leads the AI team at Gologic, where she develops AI-driven solutions to enhance DevOps workflows and accelerate software delivery.
Sponsored by
