Skip to content

Commit

Permalink
Document that the GenAI plugin is available on prem as well (#889)
Browse files Browse the repository at this point in the history
  • Loading branch information
renetapopova authored Feb 19, 2024
1 parent a3a1d70 commit fba1ab1
Show file tree
Hide file tree
Showing 3 changed files with 26 additions and 16 deletions.
Original file line number Diff line number Diff line change
Expand Up @@ -874,20 +874,20 @@ The `trackedSince` column returns the time when usage statistics tracking starte

|===

=== New features
=== New features

[cols="2", options="header"]
|===
| Feature
| Details

a|
a|
label:functionality[]
label:new[]

New operator: `AssertSameRelationship`

a|
a|
The `AssertSameRelationship` operator is used to ensure that no relationship property uniqueness constraints are violated in the slotted and interpreted runtime.
More information can be found xref:planning-and-tuning/operators/operators-detail.adoc#query-plan-assert-same-relationship[here].

Expand Down Expand Up @@ -990,7 +990,7 @@ label:functionality[]
label:new[]
[source, syntax, role=noheader]
----
CALL {
CALL {
<inner>
} IN TRANSACTIONS [ OF <num> ROWS ]
[ ON ERROR CONTINUE / BREAK / FAIL ]
Expand All @@ -1004,7 +1004,7 @@ New fine-grained control mechanism to control how an inner transaction impacts s

* `ON ERROR BREAK` - will ignore an error and stop the execution of subsequent inner transactions.

* `ON ERROR FAIL` - will fail in case of an error.
* `ON ERROR FAIL` - will fail in case of an error.

* `REPORT STATUS AS <v>` - reports the execution status of the inner transaction (a map value including the fields `started` `committed`, `transactionId`, and `errorMessage`). This flag is disallowed for `ON ERROR FAIL`.

Expand Down Expand Up @@ -1130,13 +1130,13 @@ RETURN 'val' as one, 'val' as two
| Feature
| Details

a|
a|
label:functionality[]
label:new[]

New operator: `IntersectionNodeByLabelsScan`

a|
a|
The `IntersectionNodeByLabelsScan` operator fetches all nodes that have all of the provided labels from the node label index.
More information can be found xref::planning-and-tuning/operators/operators-detail.adoc#query-plan-intersection-node-by-labels-scan[here].

Expand All @@ -1161,7 +1161,7 @@ label:updated[]
SHOW DATABASES
----
a|
Changes to the visibility of databases hosted on offline servers.
Changes to the visibility of databases hosted on offline servers.

For such databases:

Expand Down Expand Up @@ -1208,20 +1208,20 @@ The property uniqueness constraint type filter now allow both `UNIQUE` and `UNIQ

|===

=== New features
=== New features

[cols="2", options="header"]
|===
| Feature
| Details

a|
a|
label:functionality[]
label:new[]

New operator: `NodeByElementIdSeek`

a|
a|
The `NodeByElementIdSeek` operator reads one or more nodes by ID from the node store, specified via the function xref::functions/scalar.adoc#functions-elementid[elementId()].
More information can be found xref::planning-and-tuning/operators/operators-detail.adoc#query-plan-node-by-elementid-seek[here].

Expand Down
5 changes: 2 additions & 3 deletions modules/ROOT/pages/functions/index.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ This section contains information on all functions in the Cypher query language.
* LOAD CSV functions [xref::functions/index.adoc#header-query-functions-load-csv[Summary]|xref::functions/load-csv.adoc[Detail]]
* Graph functions [xref::functions/index.adoc#header-query-functions-graph[Summary]|xref::functions/graph.adoc[Detail]]
* Database functions [xref::functions/index.adoc#header-query-functions-database[Summary]|xref::functions/database.adoc[Detail]] label:new[Introduced in 5.12]
* GenAI function [xref::functions/index.adoc#header-query-functions-genai[Summary]|xref::genai-integrations.adoc#single-embedding[Detail]] label:new[Introduced in 5.16] label:aura-only[Avaliable only on Aura]
* GenAI function [xref::functions/index.adoc#header-query-functions-genai[Summary]|xref::genai-integrations.adoc#single-embedding[Detail]] label:new[Available in Aura] label:new[Introduced in 5.17]
* User-defined functions [xref::functions/index.adoc#header-query-functions-user-defined[Summary]|xref::functions/user-defined.adoc[Detail]]

Related information may be found in xref::syntax/operators.adoc[Operators].
Expand Down Expand Up @@ -799,15 +799,14 @@ label:new[Introduced in 5.12]
|===

[[header-query-functions-genai]]
**xref::genai-integrations.adoc#single-embedding[GenAI function]** label:new[Introduced in 5.16] label:aura-only[Available only on Aura]
**xref::genai-integrations.adoc#single-embedding[GenAI function]** label:new[Introduced in 5.17]

This function is used to generate a vector embedding for a single value.

[options="header"]
|===
| Function | Signature | Description
1.1+| xref:genai-integrations.adoc#single-embedding[`genai.vector.encode()`] | `genai.vector.encode(resource :: STRING, provider :: STRING, configuration :: MAP = {}) :: LIST<FLOAT>` | Encode a given resource as a vector using the named provider.
label:new[Introduced in 5.16] label:aura-only[Available only on Aura]
|===

[[header-query-functions-user-defined]]
Expand Down
15 changes: 13 additions & 2 deletions modules/ROOT/pages/genai-integrations.adoc
Original file line number Diff line number Diff line change
Expand Up @@ -2,16 +2,27 @@

:link-vector-indexes: xref:indexes/semantic-indexes/vector-indexes.adoc

[role=on-aura]
[[genai-integrations]]
= GenAI integrations

_This feature is available only in Aura._
_This feature is available from Neo4j 5.17 in both Neo4j Aura and on-prem deployments._

Neo4j provides integrations with various generative AI services using a native GenAI plugin.
This includes support for transforming text data into vector embeddings using VertexAI, OpenAI, or Amazon Bedrock.
The resulting vector embeddings can be used together with Neo4j's {link-vector-indexes}[vector search indexes].

== Prerequisites

To use the GenAI plugin, you need to have the following:

* A Neo4j DBMS running Neo4j 5.17 or later.
* A GenAI provider account, such as VertexAI, OpenAI, or Amazon Bedrock.
* API credentials for the provider you want to use.
* (On-prem only) the Neo4j GenAI plugin installed in your Neo4j deployment.
The plugin JAR is located in the _<NEO4J_HOME>/products_ directory of the Neo4j installation.
For more information on how to install and configure the plugin, see link:{neo4j-docs-base-uri}/operations-manual/{page-version}/configuration/plugins/[Operations Manual -> Configure plugins].
The plugin is enabled by default in Neo4j Aura.

[[vector-embeddings]]
== Vector embeddings

Expand Down

0 comments on commit fba1ab1

Please sign in to comment.