.Net: Memory Plugin Package - Initial Copy #2278
Closed
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Outdated suggestions cannot be applied.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.
Merging into FEATURE BRANCH
Memory is already a "skill" (TextMemorySkill) in Semantic Kernel. It also has many classes, interfaces, and extensions baked into, and exposed by, various layers of the SDK. This can be problematic, as the interfaces we specify are just one perspective of what "Memory" and a memory plugin could be. Other implementations may treat memory storage and retrieval very differently, and the Kernel core layer (orchestration, execution) should be none the wiser.
This PR seeks to decouple this implementation of a memory skill (plugin) from the Kernel Core by introducing it as a new package. Note: this package, being one of our recommended set, will be included in the "Microsoft.SemanticKernel" metapackage, so developers and AIs will continue to have access to it as they currently do.
Description
This is the first of a multi-stage PR. First:
TextMemorySkill
from Skills.CoreEmbeddings:
Next steps: