Find answers from the community

Updated 11 months ago

Right now I'm using the default

Right now I'm using the default configuration with VectorIndexRetriever, with the index being on the filesystem.
Would it bring notable performance improvements to use something dedicated like chroma or pinecone?
L
1 comment
only if you have a lot of data. Like if your saved index is over a GB, then I would consider using a vector db integration
Add a reply
Sign up and join the conversation on Discord