In an Excel file, when there is a line break in a cell, a row is divided into multiple segments. #4610
Open
4 tasks done
Labels
💪 enhancement
New feature or request
Self Checks
1. Is this request related to a challenge you're experiencing?
I want to convert an Excel file into a dataset and build a Q&A chatbot. In the file, the questions are in column 1, and the answers are in column 2. The content of each row should be treated as a single segment, but if a cell in a row contains line breaks, that row should be split into multiple segments.
![4df454b135a266b6b4ff771e7e9c0cf](https://private-user-images.githubusercontent.com/126169959/333064251-050e7358-b997-42e1-abca-58eae482b00d.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTg5Mjc5MTgsIm5iZiI6MTcxODkyNzYxOCwicGF0aCI6Ii8xMjYxNjk5NTkvMzMzMDY0MjUxLTA1MGU3MzU4LWI5OTctNDJlMS1hYmNhLTU4ZWFlNDgyYjAwZC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNjIwJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDYyMFQyMzUzMzhaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT05NTBlYWY2MTRkM2UxMmIwMmViMmMyNjZkMzJkYWRiZGM4YWFiODgzOGNkZGRkYzM2MTNjNDlmNjMxYmJmZmYyJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.BnaC9tjpQz5-hi8mriaojEUNS1298G1dtRMm7UQNYO8)
2. Describe the feature you'd like to see
If the system detects that the uploaded file is an Excel file (XLSX, CSV, XLS), it should provide an option to "Remove line breaks in cells". If the user selects this option, the line breaks in the Excel document will be removed during the cleaning process.
3. How will this feature improve your workflow or experience?
With this feature, when our common Q&A data file is uploaded, it can automatically split a row into a chunk, improving the accuracy of the Q&A chatbot's responses.
4. Additional context or comments
No response
5. Can you help us with this feature?
The text was updated successfully, but these errors were encountered: