text-splitters: fix bug in TextSplitter's create_documents method #29504
+1
−1
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
dosubot
bot
added
the
size:XS
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Skipped Deployment
|
dosubot
bot
added
Ɑ: text splitters
ccurme
reviewed
Jan 31, 2025
There was a problem hiding this comment.
Thanks for this. I think the index is intended to be in characters as opposed to units of the custom length function:
indexis calculated withtext.find, which is counting charactersself._chunk_overlapalso appears in the calculation, and this is documented as"Overlap in characters between chunks".
Closing for now but let me know if I've misunderstood this or if you can add a test case.
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Outdated suggestions cannot be applied.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.
Description:
Fixed a bug in the
TextSplitterclass within thecreate_documentsmethod. When_add_start_indexis set toTrue, the length of the chunk was measured using thelen()function (which counts characters) instead of the user-definedself.length_function(). This inconsistency could lead to incorrect values inmetadata['start_index'].Solution:
Replaced
len(chunk)withself.length_function(chunk)to ensure that the chunk length is measured consistently using the user-provided function, thereby maintaining the correctness ofmetadata['start_index'].