You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Is your feature request related to a problem?
If user have more than one knn_vector field. vector related data structures will be still created for all the vector fields irrespective of whether user want to perform ANN search on all of them or not. This consumes a lot of memory unnecessarily. If user knows that his use case don't require ANN for some specific fields and can use exact search for them if needed. We can avoid graph file creations for those fields.
What solution would you like?
Add a field level index mapping parameter to decide the search mode for the index. refer #2368 for details.
What alternatives have you considered?
A clear and concise description of any alternative solutions or features you've considered.
Do you have any additional context?
Add any other context or screenshots about the feature request here.
The text was updated successfully, but these errors were encountered:
Is your feature request related to a problem?
If user have more than one knn_vector field. vector related data structures will be still created for all the vector fields irrespective of whether user want to perform ANN search on all of them or not. This consumes a lot of memory unnecessarily. If user knows that his use case don't require ANN for some specific fields and can use exact search for them if needed. We can avoid graph file creations for those fields.
What solution would you like?
Add a field level index mapping parameter to decide the search mode for the index. refer #2368 for details.
What alternatives have you considered?
A clear and concise description of any alternative solutions or features you've considered.
Do you have any additional context?
Add any other context or screenshots about the feature request here.
The text was updated successfully, but these errors were encountered: