1. Learn
    2. /
  2. Courses
    3. /
  3. Vector Databases for Embeddings with Pinecone
Connected

Exercise

Deleting vectors

Deleting vectors isn't just about tidying up our databases; it's about optimizing performance. As your indexes grow, unnecessary or outdated vectors can clutter your storage and slow down query performance. By removing redundant data, you streamline your operations, leading to faster responses and better resource utilization.

In this exercise, you'll practice deleting vectors from the 'datacamp-index' Pinecone index. You'll check the index metrics to verify the deletion took place.

If you accidentally delete the vectors but don't pass the exercise for a different reason, add the following code before your .delete() code to re-upsert the vectors for deletion:

index.upsert(vectors=vectors)

Instructions

100 XP
  • Initialize the Pinecone connection using your API key.
  • Delete the vectors with IDs "3" and "4".
  • Retrieve the metrics of the datacamp-index Pinecone index to check that the number of stored vectors has decreased.