Skip to content

.Net: fix: count text chunker orphan glue by tokens #14002

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
he-yufeng wants to merge 1 commit into
base: main
Choose a base branch
from
+14 −7
Open

.Net: fix: count text chunker orphan glue by tokens #14002

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 3 additions & 7 deletions dotnet/src/SemanticKernel.Core/Text/TextChunker.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -195,15 +195,11 @@ private static List<string> ProcessParagraphs(List<string> paragraphs, int adjus
var lastParagraphTokens = lastParagraph.Split(s_spaceChar, StringSplitOptions.RemoveEmptyEntries);
var secondLastParagraphTokens = secondLastParagraph.Split(s_spaceChar, StringSplitOptions.RemoveEmptyEntries);

var lastParagraphTokensCount = lastParagraphTokens.Length;
var secondLastParagraphTokensCount = secondLastParagraphTokens.Length;
var combinedParagraph = string.Join(" ", secondLastParagraphTokens.Concat(lastParagraphTokens));

if (lastParagraphTokensCount + secondLastParagraphTokensCount <= adjustedMaxTokensPerParagraph)
if (GetTokenCount(combinedParagraph, tokenCounter) <= adjustedMaxTokensPerParagraph)
{
var newSecondLastParagraph = string.Join(" ", secondLastParagraphTokens);
var newLastParagraph = string.Join(" ", lastParagraphTokens);

paragraphs[paragraphs.Count - 2] = $"{newSecondLastParagraph} {newLastParagraph}";
paragraphs[paragraphs.Count - 2] = combinedParagraph;
paragraphs.RemoveAt(paragraphs.Count - 1);
}
}
Expand Down
11 changes: 11 additions & 0 deletions dotnet/src/SemanticKernel.UnitTests/Text/TextChunkerTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -819,4 +819,15 @@ public void SplitPlainTextParagraphsSplitsWhenExceedingTokenLimit()
Assert.Contains("Second line", combined);
Assert.Contains("Third line", combined);
}

[Fact]
public void SplitPlainTextParagraphsDoesNotGlueLastParagraphPastTokenLimit()
{
var lines = new[] { new string('a', 14), "bbb" };

var result = TextChunker.SplitPlainTextParagraphs(lines, 16, tokenCounter: input => input.Length);

Assert.Equal(2, result.Count);
Assert.All(result, paragraph => Assert.True(paragraph.Length <= 16));
}
}
Loading