Skip to content

Add ExcelHLoader for loading Excel files with header detection#501

Open
harikrishnancj wants to merge 1 commit intolangchain-ai:mainfrom
harikrishnancj:main
Open

Add ExcelHLoader for loading Excel files with header detection#501
harikrishnancj wants to merge 1 commit intolangchain-ai:mainfrom
harikrishnancj:main

Conversation

@harikrishnancj
Copy link

Description

This PR adds ExcelHLoader, a document loader for Excel files (.xlsx, .xls) with intelligent row-by-row data extraction.

Features

  • Loads Excel files and converts each row to a LangChain Document
  • Handles different data types (numbers, dates, missing values)
  • Supports column selection
  • Metadata includes row index

Implementation

  • Created excel_h_loader.py with the ExcelHLoader class
  • Added proper imports to __init__.py
  • Added to __all__ exports

Testing

  • Tested with sample Excel files containing various data types
  • Verified proper Document creation and metadata

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant