On demand catalog

Select a session below to watch.

Back to Session CatalogBack to Session Catalog
Using your repository for RAG: Learnings from GitHub Copilot Chat
Retrieval Augmented Generation (RAG) is a tool that can enrich questions sent to AI models with relevant data from specific knowledge bases, to help models tailor their answers to that domain. But how do engineers know what's "relevant"? Or, if the knowledge base is your repo, can the model respond with a solution that follows your coding practices? In this session, Kim-Adeline Miguel, senior software engineer at GitHub, will approach RAG from an engineering perspective and walk through some lessons learned while building a RAG workflow using GitHub Copilot Chat.

, Senior Software Engineer, GitHub

Session Type: Product Demo
Key Takeaway 1: Understand the building blocks for how to implement RAG yourself, inspired by how it works in GitHub Copilot Chat in IDEs.
Key Takeaway 2: Get a behind-the-scenes peek at how GitHub retrieves local repository context in Copilot Chat.
Key Takeaway 3: Skip the hassle and learn from a few engineering challenges GitHub encountered when implementing RAG.
Topic: AI, Data Science, Software Engineering
Target Audience: Enterprise - Developers, Educators
Industry: Software & Internet
Level: Level 200: Intermediate
GitHub Product: Copilot
Delivery Format: In-person, Recorded, On-demand