RecursiveCharacterTextSplitter #36
Merged
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
…ning only ["text'] key ignoring OutputKey. This was causing an error when used with SequentialChain
- had to create and use TextSplitterBase class and Document class to match structure of original python implementation - i have not implemented methods which are relying on external source of information(from_huggingface_tokenizer,from_tiktoken_encoder) - added comments which are explaining logic behind implementation. it should help new people to understand what it does(original python implementation kind of hard to understand in some moments)
This reverts commit 9c340d4.
added tests
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Outdated suggestions cannot be applied.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.
Ported RecursiveCharacterTextSplitter together with tests.
Had to change MergeSplits method to older version.
New version of MergeSplits from langchain repo works incorrectly(does not include separator length) causing test to fail.
Closes #7