On: Vector indexing all of Wikipedia on a laptop

[thomasfromcdnjs]

Thanks for the answer.

Wikipedia has a lot of tables so I was wondering if content-aware sentence chunking would be good enough for Wikipedia.

https://www.pinecone.io/learn/chunking-strategies/

[gfourfour → thomasfromcdnjs]

mwparserfromhell can parse the text content without including tables