Introduction to vector indexes

A vector index is a data structure designed to let the VECTOR_SEARCH function and AI.SEARCH function execute more efficiently, especially on large datasets.

Use cases

Vector indexes improve the efficiency of vector search, which is typically performed on text or multimodal embeddings of your data. BigQuery vector indexes help you perform the following tasks more efficiently:

  • Perform semantic search
  • Detect similar or duplicate images, audio, or videos
  • Perform clustering, targeting, or classification
  • Build recommendation systems
  • Find the top K most similar images or reviews to a given input

For more information, see the Introduction to vector search.

Pricing

The CREATE VECTOR INDEX statement uses BigQuery compute pricing. There is no charge for the processing required to build and refresh your vector indexes as long as the total size of the indexed table data is below your per-organization limit. To support indexing beyond this limit, you must provide your own reservation for handling the index management jobs.

Storage is also a consideration for indexes. The amount of bytes stored as an index is subject to active storage costs.

  • Vector indexes incur storage costs when they are active.
  • You can find the index storage size by using the INFORMATION_SCHEMA.VECTOR_INDEXES view. If the vector index is not yet at 100% coverage, you are still charged for whatever has been indexed. You can check index coverage by using the INFORMATION_SCHEMA.VECTOR_INDEXES view.

Quotas and limits

For more information, see Vector index limits.

What's next