An open-source collection of embeddings datasets for your LLM apps

hi

@louis030195 here

launching embedbase hub, a collection of embeddings datasets that you can use to easily customise your llms

for example i embedded my obsidian vault (about 1m words, built over the years) in the dataset ‘AI-clone’

see the hub here: Vector Hub

feel free to check out the doc: Embedbase Documentation