Improve CachingChatClient's coalescing of streaming updates #5514
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
- Avoid O(N^2) memory allocation in the length of the received text - Propagate additional metadata from coalesced nodes - Propagate metadata on the coalesced TextContent, like ModelId - Expose whether to coalesce as a setting on the client
joperezr
reviewed
Oct 11, 2024
src/Libraries/Microsoft.Extensions.AI/ChatCompletion/CachingChatClient.cs
Show resolved
Hide resolved
joperezr
reviewed
Oct 11, 2024
There was a problem hiding this comment.
Code changes LGTM but not familiar with the area so I'll defer to experts. FWIW and given this is a perf-oriented change, We do have benchmark projects added here but they are only running manually for now. We could look into having these benchmarks run daily so we can track the impact of changes as time goes by.
src/Libraries/Microsoft.Extensions.AI/ChatCompletion/CachingChatClient.cs
Outdated
Show resolved
Hide resolved
src/Libraries/Microsoft.Extensions.AI/ChatCompletion/CachingChatClient.cs
Outdated
Show resolved
Hide resolved
|
Everything else looks great! |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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.
Fixes #5481
Microsoft Reviewers: Open in CodeFlow