Indexing all of Wikipedia, on a laptop
Friends of OpenJDK Today
DataStax
Performance
Tools
May 29, 2024
Unique Views: 6,871sinceMay, 2024
Jonathan Ellis
Jonathan is the co-founder and CTO of DataStax. Before DataStax, he spent six years as project chair of Apache Cassandra, where he built the project and community into an open-source ... Learn more
In November, Cohere released a dataset containing all of Wikipedia, chunked and embedded to vectors with their multilingual-v3 model.
Computing this many embeddings yourself would cost in ...
Read more at foojay.io