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 this your first time submitting a feature request?
I have searched the existing issues, and I could not find an existing issue for this feature
I am requesting a straightforward extension of existing functionality
Describe the feature
Currently, we can only fit the sparse encoder once at the beginning. There should be an ability to update an existing index as more documents are added.
Describe alternatives you've considered
There are no straightforward alternatives. I've thought about creating a custom index that could allow updating existing index.
Who will this benefit?
This will benefit anyone who has continuous documents coming in (like users uploading documents). Especially when you do not have a set of enough documents in the beginning for fitting the encoder.
But as the pipeline begins, users can upload their org-specific documents and update their index.
Are you interested in contributing this feature?
Not currently
Anything else?
No response
The text was updated successfully, but these errors were encountered:
Is this your first time submitting a feature request?
Describe the feature
Currently, we can only fit the sparse encoder once at the beginning. There should be an ability to update an existing index as more documents are added.
Describe alternatives you've considered
There are no straightforward alternatives. I've thought about creating a custom index that could allow updating existing index.
Who will this benefit?
This will benefit anyone who has continuous documents coming in (like users uploading documents). Especially when you do not have a set of enough documents in the beginning for fitting the encoder.
But as the pipeline begins, users can upload their org-specific documents and update their index.
Are you interested in contributing this feature?
Not currently
Anything else?
No response
The text was updated successfully, but these errors were encountered: