Skip to content

[dotnet-ai] Vector data search + data ingestion pipeline#242

Draft
luisquintanilla wants to merge 2 commits into
dotnet:mainfrom
luisquintanilla:dotnet-ai/vector-data-ingestion
Draft

[dotnet-ai] Vector data search + data ingestion pipeline#242
luisquintanilla wants to merge 2 commits into
dotnet:mainfrom
luisquintanilla:dotnet-ai/vector-data-ingestion

Conversation

@luisquintanilla

Copy link
Copy Markdown
Contributor

Fixes #230
Part of #225

Dependencies

Merge order: This PR should be merged after #237 Plugin scaffold.

Summary

Adds two tightly related skills that form the data infrastructure layer of the RAG stack:

  • vector-data-search Microsoft.Extensions.VectorData abstractions for storing, indexing, and querying vector embeddings with connector selection (Azure AI Search, Qdrant, Milvus, Weaviate, in-memory)
  • data-ingestion-pipeline Microsoft.Extensions.DataIngestion pipeline for document loading, chunking strategies, enrichment, and integration with embeddings and vector storage

Changes

File Description
plugins/dotnet-ai/skills/vector-data-search/SKILL.md IVectorStore, record model definition, connector selection, hybrid search, provenance metadata
plugins/dotnet-ai/skills/data-ingestion-pipeline/SKILL.md Pipeline builder, document loading, chunking strategies, chunk enrichment, error handling
tests/dotnet-ai/vector-data-search/eval.yaml Eval: vector search setup scenario
tests/dotnet-ai/data-ingestion-pipeline/eval.yaml Eval: document ingestion pipeline scenario

Key Packages

  • Microsoft.Extensions.VectorData
  • Connectors: Microsoft.Extensions.VectorData.AzureAISearch, .Qdrant, etc.
  • Microsoft.Extensions.DataIngestion

Validation

  • Both SKILL.md files have valid YAML frontmatter
  • vector-data-search covers IVectorStore, record model, connector selection, hybrid search
  • data-ingestion-pipeline covers pipeline builder, chunking, enrichment, error handling
  • Both eval.yaml files have at least one scenario
  • Cross-references between the two skills are correct

Adds two tightly related skills: vector-data-search (VectorData abstractions,
connectors, hybrid search) and data-ingestion-pipeline (document ingestion,
chunking, enrichment).

Fixes dotnet#230
Part of dotnet#225

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
.NET 10 is the current LTS (released Nov 2025). .NET 8 reaches
end-of-support Nov 2026.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
@github-actions

github-actions Bot commented Apr 6, 2026

Copy link
Copy Markdown
Contributor

This PR has been automatically marked as stale because it has no activity for 30 days. It will be closed if no further activity occurs within another 7 days of this comment. If it is closed, you may reopen it anytime when you're ready again.

Generated by Close Stale Pull Requests ·

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[dotnet-ai] Vector data search + data ingestion pipeline

2 participants