[
https://issues.apache.org/jira/browse/CASSANDRA-19030?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jackson Fleming updated CASSANDRA-19030:
----------------------------------------
Description:
The Documentation here
[https://cassandra.apache.org/doc/latest/cassandra/getting-started/vector-search-quickstart.html]
doesn't work.
Some example errors, when creating the comments_vs table
{code:java}
instaclustr@cqlsh:cycling> CREATE TABLE IF NOT EXISTS cycling.comments_vs (
... record_id timeuuid,
... id uuid,
... commenter text,
... comment text,
... comment_vector VECTOR <FLOAT, 5>;
SyntaxException: line 6:34 mismatched input ';' expecting ')'
(...comment_vector VECTOR <FLOAT, 5>[;])
instaclustr@cqlsh:cycling> created_at timestamp,
... PRIMARY KEY (id, created_at)
... )
... WITH CLUSTERING ORDER BY (created_at DESC);
SyntaxException: line 1:0 no viable alternative at input 'created_at'
([created_at]...)
instaclustr@cqlsh:cycling> {code}
Which then breaks all the subsequent commands, some of the later inserts and
SELECTS need work even after repairing.
There's a few errors in the CQL commands and table definitions, I managed to
get it working in the below CQL.
{code:java}
CREATE KEYSPACE IF NOT EXISTS demo
WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' : '1'
};
CREATE TABLE IF NOT EXISTS demo.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);CREATE INDEX IF NOT EXISTS ann_index
ON demo.comments_vs(comment_vector) USING 'sai';
INSERT INTO demo.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 demo.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 demo.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 demo.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 demo.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 demo.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]
);SELECT * FROM demo.comments_vs
ORDER BY comment_vector ANN OF [0.15, 0.1, 0.1, 0.35, 0.55]
LIMIT 3;
SELECT comment, similarity_cosine(comment_vector, [0.2, 0.15, 0.3, 0.2, 0.05])
FROM demo.comments_vs
ORDER BY comment_vector ANN OF [0.1, 0.15, 0.3, 0.12, 0.05]
LIMIT 1; {code}
Just raising a ticket to link for a website PR.
was:
The Documentation here
[https://cassandra.apache.org/doc/latest/cassandra/getting-started/vector-search-quickstart.html]
doesn't work.
There's a few errors in the CQL commands and table definitions, I managed to
get it working in the below CQL.
{code:java}
CREATE KEYSPACE IF NOT EXISTS cycling
WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' : '1'
};
CREATE TABLE IF NOT EXISTS demo.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);CREATE INDEX IF NOT EXISTS ann_index
ON demo.comments_vs(comment_vector) USING 'sai';
INSERT INTO demo.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 demo.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 demo.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 demo.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 demo.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 demo.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]
);SELECT * FROM demo.comments_vs
ORDER BY comment_vector ANN OF [0.15, 0.1, 0.1, 0.35, 0.55]
LIMIT 3;
SELECT comment, similarity_cosine(comment_vector, [0.2, 0.15, 0.3, 0.2, 0.05])
FROM demo.comments_vs
ORDER BY comment_vector ANN OF [0.1, 0.15, 0.3, 0.12, 0.05]
LIMIT 1; {code}
Just raising a ticket to link for a website PR.
> Vector Quickstart Documentation does not work
> ---------------------------------------------
>
> Key: CASSANDRA-19030
> URL: https://issues.apache.org/jira/browse/CASSANDRA-19030
> Project: Cassandra
> Issue Type: Improvement
> Reporter: Jackson Fleming
> Assignee: Jackson Fleming
> Priority: Normal
>
> The Documentation here
> [https://cassandra.apache.org/doc/latest/cassandra/getting-started/vector-search-quickstart.html]
> doesn't work.
> Some example errors, when creating the comments_vs table
> {code:java}
> instaclustr@cqlsh:cycling> CREATE TABLE IF NOT EXISTS cycling.comments_vs (
> ... record_id timeuuid,
> ... id uuid,
> ... commenter text,
> ... comment text,
> ... comment_vector VECTOR <FLOAT, 5>;
> SyntaxException: line 6:34 mismatched input ';' expecting ')'
> (...comment_vector VECTOR <FLOAT, 5>[;])
> instaclustr@cqlsh:cycling> created_at timestamp,
> ... PRIMARY KEY (id, created_at)
> ... )
> ... WITH CLUSTERING ORDER BY (created_at DESC);
> SyntaxException: line 1:0 no viable alternative at input 'created_at'
> ([created_at]...)
> instaclustr@cqlsh:cycling> {code}
> Which then breaks all the subsequent commands, some of the later inserts and
> SELECTS need work even after repairing.
> There's a few errors in the CQL commands and table definitions, I managed to
> get it working in the below CQL.
> {code:java}
> CREATE KEYSPACE IF NOT EXISTS demo
> WITH REPLICATION = { 'class' : 'SimpleStrategy', 'replication_factor' :
> '1' };
>
> CREATE TABLE IF NOT EXISTS demo.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);CREATE INDEX IF NOT EXISTS
> ann_index
> ON demo.comments_vs(comment_vector) USING 'sai';
>
>
> INSERT INTO demo.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 demo.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 demo.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 demo.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 demo.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 demo.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]
> );SELECT * FROM demo.comments_vs
> ORDER BY comment_vector ANN OF [0.15, 0.1, 0.1, 0.35, 0.55]
> LIMIT 3;
>
> SELECT comment, similarity_cosine(comment_vector, [0.2, 0.15, 0.3, 0.2, 0.05])
> FROM demo.comments_vs
> ORDER BY comment_vector ANN OF [0.1, 0.15, 0.3, 0.12, 0.05]
> LIMIT 1; {code}
> Just raising a ticket to link for a website PR.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
