AI-assisted Coding with Cody: Lessons from Context Retrieval and Evaluation for Code Recommendations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hartman, Jan, Mehrotra, Rishabh, Sagtani, Hitesh, Cooney, Dominic, Gajdulewicz, Rafal, Liu, Beyang, Tibshirani, Julie, Slack, Quinn
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911983711813632
author Hartman, Jan
Mehrotra, Rishabh
Sagtani, Hitesh
Cooney, Dominic
Gajdulewicz, Rafal
Liu, Beyang
Tibshirani, Julie
Slack, Quinn
author_facet Hartman, Jan
Mehrotra, Rishabh
Sagtani, Hitesh
Cooney, Dominic
Gajdulewicz, Rafal
Liu, Beyang
Tibshirani, Julie
Slack, Quinn
contents In this work, we discuss a recently popular type of recommender system: an LLM-based coding assistant. Connecting the task of providing code recommendations in multiple formats to traditional RecSys challenges, we outline several similarities and differences due to domain specifics. We emphasize the importance of providing relevant context to an LLM for this use case and discuss lessons learned from context enhancements & offline and online evaluation of such AI-assisted coding systems.
format Preprint
id arxiv_https___arxiv_org_abs_2408_05344
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AI-assisted Coding with Cody: Lessons from Context Retrieval and Evaluation for Code Recommendations
Hartman, Jan
Mehrotra, Rishabh
Sagtani, Hitesh
Cooney, Dominic
Gajdulewicz, Rafal
Liu, Beyang
Tibshirani, Julie
Slack, Quinn
Information Retrieval
Machine Learning
Software Engineering
In this work, we discuss a recently popular type of recommender system: an LLM-based coding assistant. Connecting the task of providing code recommendations in multiple formats to traditional RecSys challenges, we outline several similarities and differences due to domain specifics. We emphasize the importance of providing relevant context to an LLM for this use case and discuss lessons learned from context enhancements & offline and online evaluation of such AI-assisted coding systems.
title AI-assisted Coding with Cody: Lessons from Context Retrieval and Evaluation for Code Recommendations
topic Information Retrieval
Machine Learning
Software Engineering
url https://arxiv.org/abs/2408.05344