This package provides a simple way to process files from a directory and convert them into structured documents ready to be stored in a vector database.
It leverages the capabilities of LangChainGo to handle document parsing and transformation.
The package currently supports the following formats:
- TXT
- CSV
- HTML
- ePub (custom implementation, not included in LangChainGo)
- ePub support is implemented separately, as it is not natively supported by LangChainGo.
- The package focuses on simplicity and extensibility, making it easy to add new file types if needed.