Skip to main content
Pinecone is designed to find vectors that are similar to a given set of conditions, either by comparing a new vector to the ones in the index or by comparing a vector in the index to all of the others using the query by ID feature. Because the Pinecone query function relies on performing this similarity search, there isn’t a way to return all of the vectors currently stored in the index with a single query. To work through every record in a serverless index instead, list the record IDs in a namespace and fetch them in batches. For a static copy of a whole index rather than a query, create a backup.