This page describes vector indexing best practices that optimize your vector indexes and improve approximate nearest neighbor (ANN) query results.
Tune the vector search options
The most optimal values for your vector index options depend on your use case,
vector dataset, and on the query vectors. You can set and tune these values
by creating a new vector index and setting the index_option_list
in the CREATE VECTOR INDEX
statement. You might need to perform iterative
tuning to find the best values for your specific workload.
Here are some helpful guidelines to follow when picking appropriate values:
tree_depth
(tree level): If the table you're indexing has fewer than 10 million rows, use atree_depth
of2
. Otherwise, atree_depth
of3
supports tables of up to about 10 billion rows.num_leaves
: Use the square root of the number of rows in the dataset. A larger value can increase vector index build time. Avoid settingnum_leaves
larger than thetable_row_count
divided by 1000 as this results in overly small leaves and poor performance.num_leaves_to_search
: This option specifies how many leaf nodes of the index are searched. Increasingnum_leaves_to_search
improves recall but also increases latency and cost. We recommend using a number that is 1% the total number of leaves defined in theCREATE VECTOR INDEX
statement as the value fornum_leaves_to_search
. If you're using a filter clause, increase this value to widen the search.
If acceptable recall is achieved, but the cost of querying is too high,
resulting in low maximum QPS, try increasing num_leaves
by following these
steps:
- Set
num_leaves
to some multiple k of its original value (for example,2 * sqrt(table_row_count)
). - Set
num_leaves_to_search
to be the same multiple k of its original value. - Experiment with reducing
num_leaves_to_search
to improve cost and QPS while maintaining recall.
Improve recall
To improve recall, consider tuning the num_leaves_to_search
value or
rebuilding your vector index.
Increase the num_leaves_to_search
value
If the num_leaves_to_search
value is too small, you might find it more
challenging to find the nearest neighbors for some query vectors. Creating a new
vector index with an increased num_leaves_to_search
value can help improve
recall by searching more leaves. Recent queries might contain more of these
challenging vectors.
Rebuild the vector index
The tree structure of the vector index is optimized for the dataset at the time of creation, and is static thereafter. Therefore, if significantly different vectors are added after creating the initial vector index, then the tree structure might be sub-optimal, leading to poorer recall.
To rebuild your vector index without downtime:
- Create a new vector index on the same embedding column as the current vector
index, updating parameters (for example,
OPTIONS
) as appropriate. - After the index creation completes, use the
FORCE_INDEX
hint to point at the new index to update the vector search query. This ensures that the query uses the new vector index. You might also need to retunenum_leaves_to_search
in your new query. - Drop the outdated vector index.
What's next
Learn more about Spanner vector indexes.
Learn more about Spanner approximate nearest neighbors.
Learn more about the GoogleSQL
APPROXIMATE_COSINE_DISTANCE()
,APPROXIMATE_EUCLIDEAN_DISTANCE()
,APPROXIMATE_DOT_PRODUCT()
functions.Learn more about the GoogleSQL
VECTOR INDEX
statements.