When using the Supabase Vector Store node to embed data, is there a setting or way to import columns other than the content and metadata such a integer for priority? It seems like there is no way to map other columns?
Hey @innov8te hope all is well, welcome to the community.
If this information is related to the chunk, why wouldn’t you want to include this information in the metadata?
Thanks for the reply.
In my supabase table i have id, content, metadata, source, priority, embedding.
I am embedding and inserting fine if I only put the content and metadata. But I cannot see where in the workflow I can add data for the source and priority columns. If I code this into the input of the vector store tool with a code node that information does not seem to be used in the vector store tool.
You are right, the default node only uses the content, metadata and embedding fields, I don’t think there is a way around it, you may need to restructure/rethink your scheme if you want to use the node and don’t want to embed additional fields into metadata jsonb.
1 Like
Thank you for the advice
This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.