Vector Search Quickstart

To enable your machine learning model, Vector Search uses data to be compared by similarity within a database, even if it is not explicitly defined by a connection. A vector is an array of floating point type that represents a specific object or entity.

The foundation of Vector Search lies within the embeddings, which are compact representations of text as vectors of floating-point numbers. These embeddings are generated by feeding the text through an API, which uses a neural network to transform the input into a fixed-length vector. Embeddings capture the semantic meaning of the text, providing a more nuanced understanding than traditional term-based approaches. The vector representation allows for input that is substantially similar to produce output vectors that are geometrically close; inputs that are not similar are geometrically further apart.

To enable Vector Search, a new vector data type is available in your Cassandra database with Vector Search.

Prerequisites

There are no prerequisite tasks.

In general, to use Vector Search with Apache Cassandra, you’ll follow these instructions:

The embeddings were randomly generated in this quickstart. Generally, you would run both your source documents/contents through an embeddings generator, as well as the query you were asking to match. This example is simply to show the mechanics of how to use CQL to create vector search data objects.

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.

With the code examples, you have a working example of our Vector Search. Load your own data and use the search function.

Cassandra Documentation

Version: