I am planning on converting my data currently stored in SQL to Pinecone documents
Before converting my data to vectors and passing it to pinecone, my data will look like this:
The vendor of the purchase is: ${vendor}
The line item of the purchase is: ${line_item}
The category of the purchase is: ${category}
The reason I’m jumbling multiple fields into one is because I’m under the assumption that I am only able to store one vector for each record.
However, given how my data is structured, how can I query for data but add weights to certain attributes when they’re all just essentially merged into 1 field?
I want to look for similar purchases, but I want the line_item
to have the most influence over the search results.
Is this possible to do?