.Net: Added example of Azure AI Search as Plugin with custom schema and configurable search fields #5093
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Outdated suggestions cannot be applied.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.
Motivation and Context
Today, Azure AI Search connector has two limitations:
Embedding
index field to perform search, while it's possible to specify multiple vector fields with different names.In order to resolve these limitations, major refactoring on abstraction level is required, which will impact not only Azure AI Search connector, but all other memory connectors as well, and it will take some time.
This PR contains example that shows how to register Azure AI Search functionality in Kernel as Plugin and use it to perform search operations and communicate with AI based on your data. In this example, index schema is custom and can be changed when needed, as well as
searchFields
parameter is configurable viaKernelArguments
. The usage of Azure AI Search plugin is very similar to already existing approach withAzureAISearchMemoryStore
connector.Contribution Checklist