[D] Is there any way to filter searches by metadata over current vector DBs like Pinecone?

So, I'm thinking of building an application that enables organizations to query their documents with natural language. The basic solution would be to upload all documents to the vector DB and then query for the nearest neighbors. The issue is that not all users in the organization have access to all documents. Ideally, we can limit the search over documents from the vector DB based on the role of the user. Is this possible? Are there any vector DB providers …

application building dbs documents filter issue language machinelearning metadata natural natural language neighbors organizations pinecone query solution thinking vector