Port 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): xref links for attribute parameters in tables, GetCollection, UpsertAsync, GetAsync, VectorSearchOptions
• Address CI/automated review feedback: typo fix, localhost link style, field type corrections, FileStream disposal, package version alignment, broken TOC link
• Address review feedback (round 3):
  • Removed explicit Microsoft.Extensions.VectorData.Abstractions from install instructions in use-vector-stores.md and build-vector-search-app.md; it's a transitive dependency of any provider package
  • Added a minimal Hotel data model snippet after the "Define a data model" section in use-vector-stores.md
  • Reordered embedding-generation.md so "Generate embeddings yourself" appears before "Let the vector store generate embeddings", showing the manual approach first so users understand the value of auto-generation
  • Added a "Search with auto-generated embeddings" section to vector-search.md with a new VectorSearchWithAutoEmbedding snippet demonstrating passing a string directly to SearchAsync when an IEmbeddingGenerator is configured
  • Fixed Microsoft.Extensions.VectorData.Abstractions version from 10.0.1 to 10.1.0 in VectorStoreSnippets.csproj to resolve a package downgrade build error

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 Port MEVD docs from SK repo #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/data-ingestion.md	Data ingestion
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/index.yml	[linkListType: architecture
docs/ai/overview.md	docs/ai/overview
docs/ai/quickstarts/process-data.md	Process custom data for AI applications
docs/ai/toc.yml	docs/ai/toc
docs/ai/vector-stores/define-your-data-model.md	Define your data model
docs/ai/vector-stores/embedding-generation.md	Generate embeddings for vector store providers
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 providers
docs/ai/vector-stores/overview.md	Vector databases for .NET AI apps
docs/ai/vector-stores/tutorial-vector-search.md	Tutorial - Integrate OpenAI with the RAG pattern and vector search using Azure Cosmos DB for MongoDB
docs/ai/vector-stores/vector-search.md	Vector search using vector store providers
docs/core/extensions/dependency-injection/basics.md	Quickstart: Dependency injection basics in .NET

[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.

[roji]

Thanks for doing this @gewarren and sorry for taking so long with the reviewing.

See all kinds of comments below. Some of these are probably require some specialized context that you don't have - I'm happy to jump on those (so please treat my comments as stuff I think we can/should fix, rather than necessarily stuff you should do yourself!). Let me know your thoughts on it all. Once this is merged I'll likely also do another pass and refine some things in any case.

BTW we seem to be lacking a page documenting CRUD operations (insert/update, delete, get-by-id, get-by-filter). The "generate embedding" page happens to show UpsertAsync, but we should have a dedicated page for "Inserting, deleting and retrieving data" (probably before the generate embeddings page). @gewarren I'm happy to add that afterwards if you're lacking context etc.

[gewarren]

BTW we seem to be lacking a page documenting CRUD operations (insert/update, delete, get-by-id, get-by-filter). The "generate embedding" page happens to show UpsertAsync, but we should have a dedicated page for "Inserting, deleting and retrieving data" (probably before the generate embeddings page). @gewarren I'm happy to add that afterwards if you're lacking context etc.

I logged #52610 and assigned it to you @roji.

[roji]

Thanks @gewarren - LGTM! Once this is merged I'll be in touch with the Semantic Kernel team to remove the docs on their side (and to link to these instead), and will likely do a few rounds of refinement here too.

Thanks for your help!