Working with Vector Search

Create vector keyspace

Create the keyspace you want to use for your Vector Search table. This example uses cycling as the keyspace name:

CREATE KEYSPACE IF NOT EXISTS cycling
   WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' : '1' };

Use vector keyspace

Select the keyspace you want to use for your Vector Search table. This example uses cycling as the keyspace name:

USE cycling;

Create vector table

Create a new table in your keyspace, including the comments_vector column for vector. The code below creates a vector with five values:

CREATE TABLE IF NOT EXISTS cycling.comments_vs (
  record_id timeuuid,
  id uuid,
  commenter text,
  comment text,
  comment_vector VECTOR <FLOAT, 5>,
  created_at timestamp,
  PRIMARY KEY (id, created_at)
)
WITH CLUSTERING ORDER BY (created_at DESC);

Optionally, you can alter an existing table to add a vector column:

ALTER TABLE cycling.comments_vs
   ADD comment_vector VECTOR <FLOAT, 5>(1)

Create vector index

Create the custom index with Storage Attached Indexing (SAI):

CREATE INDEX IF NOT EXISTS ann_index
  ON cycling.comments_vs(comment_vector) USING 'sai';

For more about SAI, see the Storage Attached Indexing documentation.

The index can be created with options that define the similarity function:

CREATE INDEX IF NOT EXISTS ann_index
    ON vsearch.com(item_vector) USING 'sai'
WITH OPTIONS = { 'similarity_function': 'DOT_PRODUCT' };

Valid values for the similarity_function are DOT_PRODUCT, COSINE, or EUCLIDEAN.

Load vector data into your database

Insert data into the table using the new type:

INSERT INTO cycling.comments_vs (record_id, id, created_at, comment, commenter, comment_vector)
   VALUES (
      now(),
      e7ae5cf3-d358-4d99-b900-85902fda9bb0,
      '2017-02-14 12:43:20-0800',
      'Raining too hard should have postponed',
      'Alex',
      [0.45, 0.09, 0.01, 0.2, 0.11]
);
INSERT INTO cycling.comments_vs (record_id, id, created_at, comment, commenter, comment_vector)
   VALUES (
      now(),
      e7ae5cf3-d358-4d99-b900-85902fda9bb0,
      '2017-03-21 13:11:09.999-0800',
      'Second rest stop was out of water',
      'Alex',
      [0.99, 0.5, 0.99, 0.1, 0.34]
);
INSERT INTO cycling.comments_vs (record_id, id, created_at, comment, commenter, comment_vector)
   VALUES (
      now(),
      e7ae5cf3-d358-4d99-b900-85902fda9bb0,
      '2017-04-01 06:33:02.16-0800',
      'LATE RIDERS SHOULD NOT DELAY THE START',
      'Alex',
      [0.9, 0.54, 0.12, 0.1, 0.95]
);

INSERT INTO cycling.comments_vs (record_id, id, created_at, comment, commenter, comment_vector)
   VALUES (
      now(),
      c7fceba0-c141-4207-9494-a29f9809de6f,
      totimestamp(now()),
      'The gift certificate for winning was the best',
      'Amy',
      [0.13, 0.8, 0.35, 0.17, 0.03]
);

INSERT INTO cycling.comments_vs (record_id, id, created_at, comment, commenter, comment_vector)
   VALUES (
      now(),
      c7fceba0-c141-4207-9494-a29f9809de6f,
      '2017-02-17 12:43:20.234+0400',
      'Glad you ran the race in the rain',
      'Amy',
      [0.3, 0.34, 0.2, 0.78, 0.25]
);

INSERT INTO cycling.comments_vs (record_id, id, created_at, comment, commenter, comment_vector)
   VALUES (
      now(),
      c7fceba0-c141-4207-9494-a29f9809de6f,
      '2017-03-22 5:16:59.001+0400',
      'Great snacks at all reststops',
      'Amy',
      [0.1, 0.4, 0.1, 0.52, 0.09]
);
INSERT INTO cycling.comments_vs (record_id, id, created_at, comment, commenter, comment_vector)
   VALUES (
      now(),
      c7fceba0-c141-4207-9494-a29f9809de6f,
      '2017-04-01 17:43:08.030+0400',
      'Last climb was a killer',
      'Amy',
      [0.3, 0.75, 0.2, 0.2, 0.5]
);

Query vector data with CQL

To query data using Vector Search, use a SELECT query:

SELECT * FROM cycling.comments_vs
    ORDER BY comment_vector ANN OF [0.15, 0.1, 0.1, 0.35, 0.55]
    LIMIT 3;

To obtain the similarity calculation of the best scoring node closest to the query data as part of the results, use a SELECT query:

SELECT comment, similarity_cosine(comment_vector, [0.2, 0.15, 0.3, 0.2, 0.05])
    FROM cycling.comments_vs
    ORDER BY comment_vector ANN OF [0.1, 0.15, 0.3, 0.12, 0.05]
    LIMIT 1;

The supported functions for this type of query are:

similarity_dot_product
similarity_cosine
similarity_euclidean

with the parameters of (<vector_column>, <embedding_value>). Both parameters represent vectors.

The limit must be 1,000 or fewer.
Vector Search utilizes Approximate Nearest Neighbor (ANN) that in most cases yields results almost as good as the exact match. The scaling is superior to Exact Nearest Neighbor (KNN).
Least-similar searches are not supported.
Vector Search works optimally on tables with no overwrites or deletions of the item_vector column. For an item_vector column with changes, expect slower search results.

Cassandra Documentation

Version: