SearchModelFactory.AzureOpenAIEmbeddingSkill Method
Definition
Important
Some information relates to prerelease product that may be substantially modified before it’s released. Microsoft makes no warranties, express or implied, with respect to the information provided here.
Allows you to generate a vector embedding for a given text input using the Azure OpenAI resource.
public static Azure.Search.Documents.Indexes.Models.AzureOpenAIEmbeddingSkill AzureOpenAIEmbeddingSkill(string name = default, string description = default, string context = default, System.Collections.Generic.IEnumerable<Azure.Search.Documents.Indexes.Models.InputFieldMappingEntry> inputs = default, System.Collections.Generic.IEnumerable<Azure.Search.Documents.Indexes.Models.OutputFieldMappingEntry> outputs = default, Uri resourceUri = default, string deploymentName = default, string apiKey = default, Azure.Search.Documents.Indexes.Models.SearchIndexerDataIdentity authenticationIdentity = default, Azure.Search.Documents.Indexes.Models.AzureOpenAIModelName? modelName = default, int? dimensions = default);static member AzureOpenAIEmbeddingSkill : string * string * string * seq<Azure.Search.Documents.Indexes.Models.InputFieldMappingEntry> * seq<Azure.Search.Documents.Indexes.Models.OutputFieldMappingEntry> * Uri * string * string * Azure.Search.Documents.Indexes.Models.SearchIndexerDataIdentity * Nullable<Azure.Search.Documents.Indexes.Models.AzureOpenAIModelName> * Nullable<int> -> Azure.Search.Documents.Indexes.Models.AzureOpenAIEmbeddingSkillPublic Shared Function AzureOpenAIEmbeddingSkill (Optional name As String = Nothing, Optional description As String = Nothing, Optional context As String = Nothing, Optional inputs As IEnumerable(Of InputFieldMappingEntry) = Nothing, Optional outputs As IEnumerable(Of OutputFieldMappingEntry) = Nothing, Optional resourceUri As Uri = Nothing, Optional deploymentName As String = Nothing, Optional apiKey As String = Nothing, Optional authenticationIdentity As SearchIndexerDataIdentity = Nothing, Optional modelName As Nullable(Of AzureOpenAIModelName) = Nothing, Optional dimensions As Nullable(Of Integer) = Nothing) As AzureOpenAIEmbeddingSkillParameters
- name
- String
The name of the skill which uniquely identifies it within the skillset. A skill with no name defined will be given a default name of its 1-based index in the skills array, prefixed with the character '#'.
- description
- String
The description of the skill which describes the inputs, outputs, and usage of the skill.
- context
- String
Represents the level at which operations take place, such as the document root or document content (for example, /document or /document/content). The default is /document.
- inputs
- IEnumerable<InputFieldMappingEntry>
Inputs of the skills could be a column in the source data set, or the output of an upstream skill.
- outputs
- IEnumerable<OutputFieldMappingEntry>
The output of a skill is either a field in a search index, or a value that can be consumed as an input by another skill.
- resourceUri
- Uri
The resource URI of the Azure OpenAI resource.
- deploymentName
- String
ID of the Azure OpenAI model deployment on the designated resource.
- apiKey
- String
API key of the designated Azure OpenAI resource.
- authenticationIdentity
- SearchIndexerDataIdentity
The user-assigned managed identity used for outbound connections.
- modelName
- Nullable<AzureOpenAIModelName>
The name of the embedding model that is deployed at the provided deploymentId path.
The number of dimensions the resulting output embeddings should have. Only supported in text-embedding-3 and later models.
Returns
A new AzureOpenAIEmbeddingSkill instance for mocking.
