If you've ever built RAG ingestion, a search index, or any "read a pile of documents" feature in . NET, you know the annoying part isn't the embeddings or the vector store. It's step zero: getting clean text out of a messy folder of PDFs, Word docs, spreadsheets, emails, and whatever else landed...
Source: [Dev.to](https://dev.to/jjopensoftworksblip/scrubkit-point-it-at-a-folder-get-clean-text-metadata-back-100-offline-13ai)