Classification

yaml
type: "io.kestra.plugin.ai.completion.Classification"

Examples

yaml
id: text_categorization
namespace: company.ai

tasks:
  - id: categorize
    type: io.kestra.plugin.ai.completion.Classification
    prompt: "Categorize the sentiment of: I love this product!"
    classes:
      - positive
      - negative
      - neutral
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      apiKey: "{{ kv('GEMINI_API_KEY') }}"
      modelName: gemini-2.5-flash

Properties

classes *array

SubTypestring

prompt *string

provider *

Definitions

Use Amazon Bedrock models

accessKeyId*string

modelName*string

secretAccessKey*string

type*object

Possible Values

io.kestra.plugin.ai.provider.AmazonBedrockio.kestra.plugin.langchain4j.provider.AmazonBedrock

baseUrlstring

caPemstring

clientPemstring

modelTypestring

DefaultCOHERE

Possible Values

COHERETITAN

Use Anthropic Claude models

apiKey*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.Anthropicio.kestra.plugin.langchain4j.provider.Anthropic

baseUrlstring

caPemstring

clientPemstring

maxTokensintegerstring

Use Azure OpenAI deployments

endpoint*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.AzureOpenAIio.kestra.plugin.langchain4j.provider.AzureOpenAI

apiKeystring

baseUrlstring

caPemstring

clientIdstring

clientPemstring

clientSecretstring

serviceVersionstring

tenantIdstring

Use DashScope (Qwen) models

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://dashscope-intl.aliyuncs.com/api/v1

caPemstring

clientPemstring

enableSearchbooleanstring

maxTokensintegerstring

repetitionPenaltynumberstring

Use DeepSeek models

apiKey*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.DeepSeekio.kestra.plugin.langchain4j.provider.DeepSeek

baseUrlstring

Defaulthttps://api.deepseek.com/v1

caPemstring

clientPemstring

Use GitHub Models via Azure AI Inference

gitHubToken*string

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

Use Google Gemini models

apiKey*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.GoogleGeminiio.kestra.plugin.langchain4j.provider.GoogleGemini

baseUrlstring

caPemstring

clientPemstring

embeddingModelConfiguration

io.kestra.plugin.ai.provider.GoogleGemini-EmbeddingModelConfiguration

maxRetriesintegerstring

outputDimensionalityintegerstring

taskTypestring

Possible Values

RETRIEVAL_QUERYRETRIEVAL_DOCUMENTSEMANTIC_SIMILARITYCLASSIFICATIONCLUSTERINGQUESTION_ANSWERINGFACT_VERIFICATION

timeoutstring

titleMetadataKeystring

Use Google Vertex AI models

endpoint*string

location*string

modelName*string

project*string

type*object

Possible Values

io.kestra.plugin.ai.provider.GoogleVertexAIio.kestra.plugin.langchain4j.provider.GoogleVertexAI

baseUrlstring

caPemstring

clientPemstring

Use Hugging Face Inference endpoints

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://router.huggingface.co/v1

caPemstring

clientPemstring

Use LocalAI OpenAI-compatible server

baseUrl*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.LocalAIio.kestra.plugin.langchain4j.provider.LocalAI

caPemstring

clientPemstring

Use Mistral models

apiKey*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.MistralAIio.kestra.plugin.langchain4j.provider.MistralAI

baseUrlstring

caPemstring

clientPemstring

Use OCI Generative AI models

compartmentId*string

modelName*string

region*string

type*object

authProviderstring

baseUrlstring

caPemstring

clientPemstring

Use local Ollama models

endpoint*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.Ollamaio.kestra.plugin.langchain4j.provider.Ollama

baseUrlstring

caPemstring

clientPemstring

Use OpenAI models

apiKey*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.OpenAIio.kestra.plugin.langchain4j.provider.OpenAI

baseUrlstring

Defaulthttps://api.openai.com/v1

caPemstring

clientPemstring

Use OpenRouter models

apiKey*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.OpenRouterio.kestra.plugin.langchain4j.provider.OpenRouter

baseUrlstring

caPemstring

clientPemstring

Use IBM watsonx.ai models

apiKey*string

modelName*string

projectId*string

type*object

baseUrlstring

caPemstring

clientPemstring

Use Cloudflare Workers AI models

accountId*string

apiKey*string

modelName*string

type*object

Possible Values

io.kestra.plugin.ai.provider.WorkersAIio.kestra.plugin.langchain4j.provider.WorkersAI

baseUrlstring

caPemstring

clientPemstring

Use ZhiPu AI models

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://open.bigmodel.cn/

caPemstring

clientPemstring

maxRetriesintegerstring

maxTokenintegerstring

stopsarray

SubTypestring

configuration

Default{}

Definitions

io.kestra.plugin.ai.domain.ChatConfiguration

logRequestsbooleanstring

logResponsesbooleanstring

maxTokenintegerstring

responseFormat

io.kestra.plugin.ai.domain.ChatConfiguration-ResponseFormat

jsonSchemaobject

jsonSchemaDescriptionstring

typestring

DefaultTEXT

Possible Values

TEXTJSON

returnThinkingbooleanstring

seedintegerstring

temperaturenumberstring

thinkingBudgetTokensintegerstring

thinkingEnabledbooleanstring

topKintegerstring

topPnumberstring

systemMessage string

DefaultRespond by only one of the following classes by typing just the exact class name: {{ classes }}

Outputs

classification string

finishReason string

Possible Values

STOPLENGTHTOOL_EXECUTIONCONTENT_FILTEROTHER

tokenUsage

Definitions

io.kestra.plugin.ai.domain.TokenUsage

inputTokenCountinteger

outputTokenCountinteger

totalTokenCountinteger

Metrics

input.token.count counter

Unittoken

output.token.count counter

Unittoken

total.token.count counter

Unittoken

Run DeepSeek chat and JSON completions

Tasks that call DeepSeek chat models for conversational or schema-guided JSON responses.

Perplexity

Tasks that request chat completions from Perplexity models.

Google Cloud

Execute tasks and orchestrate workflows across Google Cloud Platform services. Centralize authentication and resource management for seamless GCP integration.

CloudDataInfrastructureAI

Classification

More Plugins in this Category

Run DeepSeek chat and JSON completions

Perplexity

Google Cloud

1.6.0