Optimize Semantic Kernel LLamaSharpChatCompletion when running with StatefulExecutorBase models #671
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…y the most recent user message in SK ChatHistory instance when using StatefulExecutor models
AsakusaRinne
approved these changes
Apr 30, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Updated LLamaSharpChatCompletion Semantic Kernel inference to send only the most recent user message in SK ChatHistory instance when using StatefulExecutor models.
The current implementation allows for any Executor mode to be used with the LLamaSharpChatCompletion class. However, as discussed in issue #614, the actual inference call will pass the entire ChatHistory to the model everytime. This makes sense when using the StatelessExecutor but not when using either of the StatefulExecutors.
This PR adds a check to see which executor is being run and format the prompt accordingly. The logic is based on the ChatSession class where the entire history (i.e. system prompt + first user message) is sent when the model is first run, but only the last message on subsequent interactions.