text-splitters: bug fix for incorrect start_index if the chunk is substring of another chunk #21477
+7
−4
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
Sample code:
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.docstore.document import Document
splitter = RecursiveCharacterTextSplitter(chunk_size=5, chunk_overlap=5, separators=[" ", ""], add_start_index=True)
splitter.split_documents([Document(page_content="chunk chunk")])
Before this commit:
[Document(page_content='chunk', metadata={'start_index': 0}),
Document(page_content='chun', metadata={'start_index': 0}),
Document(page_content='chunk', metadata={'start_index': 0})]
After this commit:
[Document(page_content='chunk', metadata={'start_index': 0}),
Document(page_content='chun', metadata={'start_index': 6}),
Document(page_content='chunk', metadata={'start_index': 6})]
This resolves langchain-ai#21475
|
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
dosubot
bot
added
size:S
|
@baskaryan / @efriis : can one of you please take a look at this PR and linked issue? |
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Outdated suggestions cannot be applied.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: Bug fix to find correct value of start_index if chunk is substring of another chunk.
Issue: #21475
Sample code:
Before this commit:
After this commit: