Merged
Conversation
added 7 commits
May 5, 2025 14:05
pswierad-src
previously approved these changes
May 8, 2025
Collaborator
pswierad-src
left a comment
There was a problem hiding this comment.
With suggestions ;)
| public bool Translate { get; init; } | ||
| public InferenceParamsDocument? InferenceParams { get; init; } | ||
| public MemoryParamsDocument? MemoryParams { get; init; } | ||
| public object? ConvState { get; init; } |
Collaborator
There was a problem hiding this comment.
No explicit type here?
Contributor
Author
There was a problem hiding this comment.
Conversation.State given by LLamaSharp is abstract type, therefore cannot be serialized by itself, we can create our own object type individually for that but atm maybe we dont have enough reason for that imo, atm its object because its easy to store it that way :p
|
|
||
| public async Task<Agent> CreateAgent(Agent agent, bool flow = false, bool interactiveResponse = false, | ||
| InferenceParams? inferenceParams = null, MemoryParams? memoryParams = null) | ||
| InferenceParams? inferenceParams = null, MemoryParams? memoryParams = null, bool useCache = false) |
Collaborator
There was a problem hiding this comment.
If the caching is for memory maybe we should default it to true? For sake of backwards compatibility
Contributor
Author
There was a problem hiding this comment.
Fair point, though caching make it more resource heavy, but users now have a choice to disable it at least. I will update thanks!
pswierad-src
previously approved these changes
May 8, 2025
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Mostly performance improvements, with few extensions and helper methods
Also new example (conversation agent) that was helpful while debugging performance and context size changes