Use GitHub Models in code #186
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
👋 Thanks for contributing @flcdrg! We will review the pull request and get back to you soon. |
Check Broken PathsWe have automatically detected the following broken relative paths in your files. Check the file paths and associated broken paths inside them.
|
The documentation suggests that the code is using GitHub Models, but the current implementation appears to rely on Ollama being present. This change updates the code to use GitHub Models
Check Broken PathsWe have automatically detected the following broken relative paths in your files. Check the file paths and associated broken paths inside them.
|
Check Broken URLsWe have automatically detected the following broken URLs in your files. Review and fix the paths to resolve this issue. Check the file paths and associated broken URLs inside them.
|
1 similar comment
Check Broken URLsWe have automatically detected the following broken URLs in your files. Review and fix the paths to resolve this issue. Check the file paths and associated broken URLs inside them.
|
There was a problem hiding this comment.
Pull Request Overview
This PR replaces the Ollama-based embedding generator with the GitHub Models inference API via the Azure AI Inference client and updates documentation to match.
- Swap out the Microsoft.Extensions.AI.Ollama package for AzureAIInference
- Update
Program.csto useEmbeddingsClientwith a GitHub token - Refresh the markdown guide to show the new setup
Reviewed Changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| 03-CoreGenerativeAITechniques/src/RAGSimple-02MEAIVectorsMemory/RAGSimple-02MEAIVectorsMemory.csproj | Change package reference from Ollama to AzureAIInference |
| 03-CoreGenerativeAITechniques/src/RAGSimple-02MEAIVectorsMemory/Program.cs | Use EmbeddingsClient and AzureKeyCredential instead of OllamaEmbeddingGenerator |
| 03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md | Update example to match new AzureAIInference code |
Comments suppressed due to low confidence (2)
03-CoreGenerativeAITechniques/02-retrieval-augmented-generation.md:88
- [nitpick] It would be helpful to add a brief note before this snippet instructing readers to set the
GITHUB_TOKENenvironment variable and include theusing Azure.Core;andusing Azure.AI.Inference;directives in their code.
var githubToken = Environment.GetEnvironmentVariable("GITHUB_TOKEN") ?? throw new InvalidOperationException("GITHUB_TOKEN environment variable is not set.");
03-CoreGenerativeAITechniques/src/RAGSimple-02MEAIVectorsMemory/Program.cs:1
- The code uses
AzureKeyCredentialbut only importsAzure. You should addusing Azure.Core;(or replaceusing Azure;withusing Azure.Core;) so the compiler can resolveAzureKeyCredential.
using Azure;
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The documentation suggests that the code is using GitHub Models, but the current implementation appears to rely on Ollama being present. This change updates the code to use GitHub Models.
Without this change, the existing code doesn't work on the regular "C# (.NET)" devcontainer and you need to use the "C# (.NET) - Ollama" as a workaround (which takes longer to load).
This is also a partial fix for #122