Functions and procedures
Syntax |
|
||
Description |
Encode a given resource as a vector using the named provider. |
||
Input arguments |
Name |
Type |
Description |
|
|
The object to transform into an embedding. |
|
|
|
The identifier of the provider: ("VertexAI", "OpenAI", "AzureOpenAI", "Bedrock"). |
|
|
|
The provider specific settings. |
|
Returns |
|
||
Syntax |
|
||
Description |
Encode a given batch of resources as vectors using the named provider. |
||
Input arguments |
Name |
Type |
Description |
|
|
The object to transform into an embedding. |
|
|
|
An optional list of selectors to filter out changes. |
|
|
|
The provider specific settings. |
|
Return arguments |
Name |
Type |
Description |
|
|
The index of the corresponding element in the input list. |
|
|
|
The name of the input resource. |
|
|
|
The generated vector embedding for the resource. |
|
To store the embeddings created by the encoding functions as node/relationship properties, use the built-in procedures db.create.setNodeVectorProperty and
db.create.setRelationshipVectorProperty.
Once stored as properties, they can be queried using vector indexes.
|
Syntax |
|
||
Description |
Lists the available vector embedding providers. |
||
Return arguments |
Name |
Type |
Description |
|
|
The name of the GenAI provider. |
|
|
|
The signature of the required config map. |
|
|
|
"The signature of the optional config map. |
|
|
|
The default values for the GenAI provider. |
|