Microsoft Dev Blogs

Announcing Hybrid Search with Semantic Kernel for .NET

## Hybrid Search with Semantic Kernel for .NET

### What is Hybrid Search?
Hybrid search combines vector similarity search and keyword search in a vector database to provide better RAG performance than regular vector similarity search alone.

### Using Hybrid Search:
To use Hybrid Search with the Semantic Kernel Vector Stores in .NET, ensure your schema includes a vector field for similarity search and a text field for keyword search. Mark the text field as FullTextSearchable for indexing. Some databases may not support hybrid search with keyword search, so use connectors that implement this feature.

### Documentation & Samples:
- Detailed documentation: [Hybrid Search Documentation](https://learn.microsoft.com/semantic-kernel/concepts/vector-store-connectors/hybrid-search)
- Sample with Azure AI Search: [Hybrid Search Sample](https://github.com/microsoft/semantic-kernel/blob/main/dotnet/samples/Concepts/Memory/VectorStore_HybridSearch_Simple_AzureAISearch.cs)
- Check connector compatibility: [Connector Compatibility](https://learn.microsoft.com/semantic-kernel/concepts/vector-store-connectors/out-of-the-box-connectors)

### Coming Soon:
Stay tuned for Python support for hybrid search.