Beef up MEVD docs: expanded conceptual article, new how-to guide, and working code snippets

[Copilot]

• Expand docs/ai/conceptual/vector-databases.md with MEVD API concepts and code samples
• Create docs/ai/how-to/use-vector-stores.md how-to guide with working code samples and snippet files
• Create compilable C# snippet project at docs/ai/how-to/snippets/use-vector-stores/csharp/VectorStoresExamples/
• Update docs/ai/toc.yml to add a new "Vector stores" top-level section
• Accessed SK vector store docs on learn.microsoft.com and ported additional content
• Address review feedback (round 1): ai-usage, .gitignore, TOC duplicate, intro sentence, phrasing, xref headings
• Address review feedback (round 2):
  • Added xref links to parameter names in all three attribute parameter tables
  • Changed GetCollection<TKey, TRecord> to use <xref:Microsoft.Extensions.VectorData.VectorStore.GetCollection*>
  • Changed UpsertAsync to use <xref:Microsoft.Extensions.VectorData.VectorStoreCollection\2.UpsertAsync*>`
  • Changed GetAsync mentions to use <xref:Microsoft.Extensions.VectorData.VectorStoreCollection\2.GetAsync*>`
  • Changed VectorSearchOptions<TRecord> to use <xref:Microsoft.Extensions.VectorData.VectorSearchOptions\1>`

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Beef up MEVD docs</issue_title>
<issue_description>### Describe the issue or suggestion

Port vector DB docs from What are Semantic Kernel Vector Stores? (Preview) | Microsoft Learn to this repo, but review and make improvements as well. MEVD has evolved since the docs were written.

We already have https://learn.microsoft.com/en-us/dotnet/ai/conceptual/vector-databases but it's woefully short (not a single code sample etc.). We might add a new top-level section (at the level of tokenization, evaluation...) to house the new content.

---

Associated WorkItem - 550641</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Beef up MEVD docs #51443

---

🔒 GitHub Advanced Security automatically protects Copilot coding agent pull requests. You can protect all pull requests by enabling Advanced Security for your repositories. Learn more about Advanced Security.

---

Internal previews

Toggle expand/collapse

📄 File	🔗 Preview link
docs/ai/conceptual/embeddings.md	Embeddings in .NET
docs/ai/conceptual/understanding-tokens.md	"Understanding tokens"
docs/ai/dotnet-ai-ecosystem.md	.NET + AI ecosystem tools and SDKs
docs/ai/overview.md	docs/ai/overview
docs/ai/toc.yml	docs/ai/toc
docs/ai/vector-stores/defining-your-data-model.md	Define your data model
docs/ai/vector-stores/dynamic-data-model.md	Using Vector Store abstractions without defining your own data model
docs/ai/vector-stores/embedding-generation.md	Generate embeddings for Vector Store connectors
docs/ai/vector-stores/how-to/build-vector-search-app.md	Build a .NET AI vector search app
docs/ai/vector-stores/how-to/use-vector-stores.md	docs/ai/vector-stores/how-to/use-vector-stores
docs/ai/vector-stores/how-to/vector-store-data-ingestion.md	How to ingest data into a Vector Store
docs/ai/vector-stores/hybrid-search.md	Hybrid search using Vector Store connectors
docs/ai/vector-stores/overview.md	Vector databases for .NET AI apps
docs/ai/vector-stores/schema-with-record-definition.md	Defining your storage schema using a record definition
docs/ai/vector-stores/tutorial-vector-search.md	Implement Azure OpenAI with RAG using vector search in a .NET app
docs/ai/vector-stores/vector-search.md	docs/ai/vector-stores/vector-search

[gewarren]

@copilot I added learn.microsoft.com to your allow list. Can you try to access the docs you need to port over to this repo?

[Copilot]

@copilot I added learn.microsoft.com to your allow list. Can you try to access the docs you need to port over to this repo?

Accessed the SK vector store docs at learn.microsoft.com and ported relevant content. Commit fe8c80cc adds:

• Attribute parameter tables for [VectorStoreKey], [VectorStoreData], and [VectorStoreVector] (including IndexKind, StorageName, etc.)
• Automatic embedding generation — how to use a string-typed vector property with a configured IEmbeddingGenerator so the store generates embeddings automatically
• Programmatic schema definition using VectorStoreCollectionDefinition as an alternative to attributes
• VectorSearchOptions reference table covering Filter, VectorProperty, Skip, and IncludeVectors
• Multi-vector targeting — using VectorProperty when a data model has multiple vector properties
• Hybrid search — IKeywordHybridSearchable<TRecord> and HybridSearchAsync with a note about full-text indexing requirements
• Expanded connector table — added Couchbase and Oracle, reordered alphabetically, added maintainer note

All code samples compile and run against the real Microsoft.Extensions.VectorData.Abstractions 9.7.0 / Microsoft.SemanticKernel.Connectors.InMemory 1.55.0-preview packages.

[gewarren]

@copilot please respond to all feedback

[Copilot]

@copilot please respond to all feedback

All feedback addressed in 1ddb6a13:

• Updated intro sentence (split into two, [*embeddings*] link style)
• Fixed "vector store level, collection level, or" phrasing
• Removed .gitignore from snippets folder
• Removed duplicate TOC entry
• Changed ai-usage to ai-generated
• Added xref links to all attribute parameter headings and to VectorStore, VectorStoreCollection, SearchAsync, VectorSearchResult, IKeywordHybridSearchable, DeleteAsync, and EnsureCollectionDeletedAsync

[gewarren]

@copilot Please respond to feedback

[Copilot]

@copilot Please respond to feedback

All feedback addressed in ab4c26a4: xref links added to attribute parameter names in tables, GetCollection, UpsertAsync, GetAsync, and VectorSearchOptions.

[Copilot]

Pull request overview

This PR significantly expands the vector database documentation for .NET AI applications by adding comprehensive coverage of the Microsoft.Extensions.VectorData library. The changes transform a brief conceptual overview into detailed documentation with working code examples, covering both conceptual understanding and practical implementation.

Changes:

• Expanded the vector databases conceptual article with detailed coverage of the Microsoft.Extensions.VectorData library, including API examples, data modeling patterns, and a complete list of available connectors
• Created a new how-to guide for using vector stores with step-by-step instructions for common operations like upserting, searching, and filtering
• Added a complete, compilable C# snippet project with working code examples demonstrating all major features

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
docs/ai/toc.yml	Reorganized TOC to create a new "Vector stores" top-level section containing both the conceptual overview and how-to guide
docs/ai/conceptual/vector-databases.md	Expanded from a brief overview to comprehensive conceptual documentation covering MEVD library features, data models, search patterns, and available connectors
docs/ai/how-to/use-vector-stores.md	New how-to guide with detailed step-by-step instructions for all vector store operations including CRUD, search, filtering, and hybrid search
docs/ai/how-to/snippets/use-vector-stores/csharp/VectorStoresExamples/VectorStoresExamples.csproj	Project file targeting net10.0 with required vector store dependencies
docs/ai/how-to/snippets/use-vector-stores/csharp/VectorStoresExamples/Hotel.cs	Data model example demonstrating vector store attributes
docs/ai/how-to/snippets/use-vector-stores/csharp/VectorStoresExamples/Program.cs	Main demonstration code with snippets for all basic operations
docs/ai/how-to/snippets/use-vector-stores/csharp/VectorStoresExamples/RecordDefinition.cs	Example of programmatic schema definition without attributes
docs/ai/how-to/snippets/use-vector-stores/csharp/VectorStoresExamples/AutoEmbedding.cs	Example of automatic embedding generation feature

[roji]

@gewarren great to see this! Just want to make sure you're aware of the vector store section in the Semantic Kernel docs (the entire section, not just that page). These are pretty high-quality docs that will go away as part of this effort, with their contents merged into the .NET docs you're working on. At least some of this content can simply be moved as-is, others can at least be a source for Copilot.

Let me know your thoughts... BTW I'm nearing the end of my coding work on MEVD, and am definitely happy to be involved in the docs side of things, as a reviewer or anything else that might be helpful.

[BillWagner]

This looks great @gewarren

I had a few questions on the code to consider.

[gewarren]

@gewarren great to see this! Just want to make sure you're aware of the vector store section in the Semantic Kernel docs (the entire section, not just that page). These are pretty high-quality docs that will go away as part of this effort, with their contents merged into the .NET docs you're working on. At least some of this content can simply be moved as-is, others can at least be a source for Copilot.

Let me know your thoughts... BTW I'm nearing the end of my coding work on MEVD, and am definitely happy to be involved in the docs side of things, as a reviewer or anything else that might be helpful.

I will add the remainder of the docs - didn't catch that Copilot hadn't done that.