Add support for overlap between paragraphs when using TextChunker to split text #1206
+142
−81
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
github-actions
bot
added
.NET
|
@microsoft-github-policy-service agree |
MonsterCoder
changed the title
MonsterCoder
changed the title
awakeningbyte
approved these changes
May 29, 2023
MonsterCoder
force-pushed
the
add_overlap_to_text_chunker
branch
from
bca0e94 to
367cb16
Compare
lemillermicrosoft
previously approved these changes
Jun 8, 2023
Co-authored-by: Lee Miller <lemiller@microsoft.com>
Co-authored-by: Lee Miller <lemiller@microsoft.com>
Co-authored-by: Lee Miller <lemiller@microsoft.com>
Co-authored-by: Lee Miller <lemiller@microsoft.com>
lemillermicrosoft
approved these changes
Jun 9, 2023
lemillermicrosoft
added
PR: ready for review
shawncal
pushed a commit
to shawncal/semantic-kernel
that referenced
this pull request
Jul 6, 2023
…split text (microsoft#1206) ### Motivation and Context When splitting large text into paragraphs for embedding, it is common to have overlap between chuncks to keep semantic context. This pattern can be used to improve semantic search quality ### Description 1. Added an `overlapToken` parameter to `TextChuncker.SplitPlainTextParagraphs` and `TextChuncker.SplitMarkdownParagraphs` functions. Allow max number of `overlapToken` tokens to be overlapped between neibouring paragraphs. 2. Refactoring some functions. less for loop, less side-effects ### Contribution Checklist <!-- Before submitting this PR, please make sure: --> - [x] The code builds clean without any errors or warnings - [x] The PR follows SK Contribution Guidelines (https://github.com/microsoft/semantic-kernel/blob/main/CONTRIBUTING.md) - [x] The code follows the .NET coding conventions (https://learn.microsoft.com/dotnet/csharp/fundamentals/coding-style/coding-conventions) verified with `dotnet format` - [x] All unit tests pass, and I have added new tests where possible - [x] I didn't break anyone 😄 --------- Co-authored-by: Lee Miller <lemiller@microsoft.com>
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.
Motivation and Context
When splitting large text into paragraphs for embedding, it is common to have overlap between chuncks to keep semantic context. This pattern can be used to improve semantic search quality
Description
overlapTokenparameter toTextChuncker.SplitPlainTextParagraphsandTextChuncker.SplitMarkdownParagraphsfunctions. Allow max number ofoverlapTokentokens to be overlapped between neibouring paragraphs.Contribution Checklist
dotnet format