This PR addresses the mismatch between the RAG tutorial documentation and the actual code samples in the repository.

Changes Made

• Added a clear note at the beginning of the RAG tutorial explaining that while the tutorial demonstrates concepts using GitHub Models (with the https://models.inference.ai.azure.com endpoint), all the actual code samples in the repository use Ollama with local models (connecting to http://localhost:11434)
• Updated the code examples to show both approaches - the GitHub Models approach (as was already in the tutorial) and the Ollama approach (as is in the actual code samples)
• Added notes about how to run the code samples, including the requirement to have Ollama set up and the correct models pulled
• Fixed a typo in the tutorial: "instatiated" -> "instantiated"
• Added detailed notes explaining that the actual code samples use different approaches than the simplified examples in the tutorial

These changes help users understand the differences between the tutorial examples and the actual code samples, and provide clear guidance on how to run the samples correctly.

Fixes #122.

💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.