TODO: Knowledge index from .zip file
TODO: Make packages for each index preparer and allow them to be installed and used separately
TODO: [🏏] Leverage the batch API and build queues @see https://platform.openai.com/docs/guides/batch
TODO: Maybe implement adapter to https://www.docupanda.io/

TODO: [🐴] Put generator warning to all intermediate knowledge sources
TODO: [🐴] Put generator warning to all .bookc files and index files
TODO: [😡] SAVE .knowledge.json file along the knowledge sources + put warning


TODO: [🧠][🌜] Should be split scrapers according to supported file (1) types OR/AND brands (2)
1) `LibreofficeScraper`, `PandocScraper`, `MarkitdownScraper`
2) `PdfScraper`, `DocumentScraper`,...