
Azure Embeddings
CertifiedGenerate vector embeddings from text input
Azure Embeddings
Generate vector embeddings from text input
Use Azure AI Foundry to generate embeddings using a deployed model endpoint.
type: io.kestra.plugin.azure.aifoundry.EmbeddingsExamples
Generate embeddings and log the result
id: azure_ai_embeddings
namespace: company.team
tasks:
- id: embed
type: io.kestra.plugin.azure.aifoundry.Embeddings
endpoint: "{{ secret('AZURE_AI_FOUNDRY_ENDPOINT') }}"
apiKey: "{{ secret('AZURE_AI_FOUNDRY_API_KEY') }}"
deploymentName: text-embedding-3-small
inputs:
- "The quick brown fox jumps over the lazy dog."
- id: log_result
type: io.kestra.plugin.core.log.Log
message: "Embedding vector length: {{ outputs.embed.embeddings[0] | length }}"
Properties
deploymentName *Requiredstring
The name of the deployment to use
endpoint *Requiredstring
Azure AI Foundry endpoint
The Azure AI Foundry project or model endpoint URL.
inputs *Requiredarray
The text inputs to generate embeddings for
apiKey string
Azure AI Foundry API key
API key for API-key authentication. When omitted, DefaultAzureCredential (Entra ID) is used instead.
clientId string
Azure client ID
Client ID of the Azure app registration used with tenantId and clientSecret.
clientSecret string
Azure client secret
Client secret of the Azure app registration used with tenantId and clientId.
pluginDefaultsRef Non-dynamicstring
Reference (ref) of the pluginDefaults to apply to this task.
tenantId string
Azure tenant ID
Azure Entra tenant ID used with clientId and clientSecret for service principal authentication.
Outputs
embeddings array
The generated embeddings, one list of floats per input text