RAGLight supports two main data sources:
- local folder: Documents can be imported in PDF, text file and other formats. Configuration requires the use of
FolderSourceSpecify the folder path, e.g.FolderSource(path="/path/to/your/folder/knowledge_base")The - GitHub Repositories: Support for extracting documents from public repositories. Configuration requires the use of the
GitHubSourceand provide the repository URL, e.g.GitHubSource(url="https://github.com/Bessouat40/RAGLight")The
Users can add these data sources to the RAG pipeline when initializing the knowledge_base list, RAGLight automatically processes the document and generates the vector store.
This answer comes from the articleRAGLight: Lightweight Retrieval Augmentation Generation Python LibraryThe
May not be reproduced without permission:AI productivity tools " What data sources does RAGLight support? How to configure these data sources?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil