Manjunath Janardhan

Team It would be great if it supports GPU support. We plan to use for Production which required GPU for faster processing .

@BlazJurisic Thank you for the info! Let me try batch_search experiment with diffrent batch size for our use cases as well and see if performance improves!

Yes! I would love to work on this. I have started working on this and testing the changes. https://github.com/manjunathshiva/llama-hub

@mwmeyer Few more GitLAB API changes and test needed before the MR! Once done will send open MR

I think Endpoint URL seems to be inccorect. It should be your S3 bucket end point. Example: endpoint_url: "https://s3.us-east-1.amazonaws.com/qdrant-manju"

> > I think Endpoint URL seems to be inccorect. It should be your S3 bucket end point. Example: endpoint_url: "https://s3.us-east-1.amazonaws.com/qdrant-manju" > > I have minio running on 9000 port...