Find answers from the community

Updated 2 months ago

When setting up my vector database (

When setting up my vector database (qdrant) I didn't use enable_hybrid=True, and I would like to compare the differences in quality. Is there a way to do this after the fact with llama index, or would I need to rebuild the entire vector db from scratch?
L
s
5 comments
you'd have to rebuild it, since you need to be embedding your data with sparse embeddings as its built for hybrid to work
You could always turn it off later, but if it wasn't turned on to begin with, then it needs a rebuild
Yeah. looks like it's false by default. :/
At least my GPUs are getting exercise
yeaaa, making it true by default would break a lot of setups (downloading and running models locally is not always expected)

Give that GPU a run for its money lol
Add a reply
Sign up and join the conversation on Discord