TL;DR I built a small RAG assistant with Docker Agent using a folder of documents, an agent instruction, and a retrieval configuration. The project does not need a Python application, custom ingestion service, web UI, or separate vector database. RAG projects can grow quickly. For this build, Docker Agent’s native RAG capabilities were enough to create a document assistant backed by a local folder. ...
Why Use Custom Instructions? Custom instructions help Copilot follow your coding, documentation, and team workflow preferences more consistently. Why Use Custom Instructions? Consistency: Ensure everyone follows the same standards for commits, docs, and more. Productivity: Automate repetitive tasks and reduce manual errors. AI Readiness: Make your workflow friendly for Copilot, ChatGPT, and other AI tools. Personalization: Tailor Copilot’s suggestions to your coding style and team practices. Quick Start Follow these steps to create your first custom instructions file: Open the Command Palette (Cmd+Shift+P or Ctrl+Shift+P). Run Chat: New Instructions File to create a .instructions.md file in .github/instructions at the root of your repository. Add your guidelines in Markdown format. Example: # Custom instructions for Copilot ## Project context This project is a web application built with React and Node.js. ## Indentation We use tabs, not spaces. ## Coding style Use camelCase for variable names and prefer arrow functions over traditional function expressions. ## Testing We use Jest for unit testing and Playwright for end-to-end testing. Optionally, use the applyTo metadata to target specific files: --- applyTo: "**/*.ts" --- Coding practices for TypeScript files. ... ...