Open
Description
Description
We still have a significant number of queries that are affected by the per document context length limitation.
LangChain has addressed this with a header preserving chunk implementation here:
https://github.com/finnless/langchain/blob/master/libs/langchain/langchain/text_splitter.py#L332
Test with and without nested header line ("Frontend v4 > Upgrade notes > Breaking changes")
Additional Information
No response
Activity