We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
It would be great if we could add a multiplier based on other fields to the knn score for vector search.
We've built a little prototype here which allows a user to search by audience for products: https://twitter.com/timscullin/status/1782619381589315905
This uses an embedding for the product audience description for the vector search.
It's pretty good but I think we could get better results if we were able to use the products popularity score to increase it's ranking.
A poorly thought out example of how you could achieve this:
{ 'q': 'chair', 'query_by' : 'embedding', 'boost' : 'popularity:1,sales:2' }
In this case it would multiple the embedding knn score by 1x popularity and 2x the sales.
Thanks for all the great work!
The text was updated successfully, but these errors were encountered:
No branches or pull requests
It would be great if we could add a multiplier based on other fields to the knn score for vector search.
We've built a little prototype here which allows a user to search by audience for products:
https://twitter.com/timscullin/status/1782619381589315905
This uses an embedding for the product audience description for the vector search.
It's pretty good but I think we could get better results if we were able to use the products popularity score to increase it's ranking.
A poorly thought out example of how you could achieve this:
In this case it would multiple the embedding knn score by 1x popularity and 2x the sales.
Thanks for all the great work!
The text was updated successfully, but these errors were encountered: