RAG Data Input Files

This directory contains input data files used in the RAG tutorials.

Available Data Files

  • Various text documents and datasets for RAG pipeline processing

  • Sample questions and answers for testing

  • Configuration files for data processing

File Types

  • .txt: Raw text documents

  • .csv: Structured data files

  • .json: Configuration and metadata files

  • .rst.txt: ReStructuredText documentation samples

Usage

These files are used in the notebooks to demonstrate:

  • Data loading and preprocessing

  • Document chunking

  • Vector embedding generation

  • Retrieval augmented generation workflows

Source

The data includes samples from various domains to demonstrate RAG capabilities with different types of content.