JSONStructuredExtraction

JSONStructuredExtraction

Extract JSON fields from text

yaml
type: io.kestra.plugin.ai.completion.JSONStructuredExtraction

Examples

yaml
id: json_structured_extraction
namespace: company.ai

tasks:
  - id: extract_person
    type: io.kestra.plugin.ai.completion.JSONStructuredExtraction
    schemaName: Person
    jsonFields:
      - name
      - city
      - country
      - email
    prompt: |
      From the text below, extract the person's name, city, and email.
      If a field is missing, leave it blank.

      Text:
      "Hi! I'm John Smith from Paris, France. You can reach me at john.smith@example.com."
    systemMessage: You extract structured data in JSON format.
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
      modelName: gemini-2.5-flash

yaml
id: json_structured_extraction_order
namespace: company.ai

tasks:
  - id: extract_order
    type: io.kestra.plugin.ai.completion.JSONStructuredExtraction
    schemaName: Order
    jsonFields:
      - order_id
      - customer_name
      - city
      - total_amount
    prompt: |
      Extract the order_id, customer_name, city, and total_amount from the message.
      For the total amount, keep only the number without the currency symbol.
      Return only JSON with the requested keys.

      Message:
      "Order #A-1043 for Jane Doe, shipped to Berlin. Total: 249.99 EUR."
    systemMessage: You are a precise JSON data extraction assistant.
    provider:
      type: io.kestra.plugin.ai.provider.OpenAI
      apiKey: "{{ secret('OPENAI_API_KEY') }}"
      modelName: gpt-5-mini
    guardrails:
      input:
        - expression: "{{ message.length < 10000 }}"
          message: "Message too long"
      output:
        - expression: "{{ not (response contains 'CONFIDENTIAL') }}"
          message: "Response contains confidential information"

Properties

jsonFields *array

SubTypestring

provider *

Definitions

Use Amazon Bedrock models

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.AmazonBedrock
      accessKeyId: "{{ secret('AWS_ACCESS_KEY') }}"
      secretAccessKey: "{{ secret('AWS_SECRET_KEY') }}"
      modelName: anthropic.claude-3-sonnet-20240229-v1:0
      thinkingBudgetTokens: 1024
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.Anthropic
      apiKey: "{{ secret('ANTHROPIC_API_KEY') }}"
      modelName: claude-3-haiku-20240307
      thinkingEnabled: true
      thinkingBudgetTokens: 1024
      returnThinking: false
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.AzureOpenAI
      apiKey: "{{ secret('AZURE_API_KEY') }}"
      endpoint: https://your-resource.openai.azure.com/
      modelName: anthropic.claude-3-sonnet-20240229-v1:0
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.DashScope
      apiKey: "{{ secret('DASHSCOPE_API_KEY') }}"
      modelName: qwen-plus
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

apiKey*string

modelName*string

type*object

baseUrlstring

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

caPemstring

clientPemstring

enableSearchbooleanstring

maxTokensintegerstring

repetitionPenaltynumberstring

Use DeepSeek models

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.DeepSeek
      apiKey: "{{ secret('DEEPSEEK_API_KEY') }}"
      modelName: deepseek-chat
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.GitHubModels
      gitHubToken: "{{ secret('GITHUB_TOKEN') }}"
      modelName: gpt-4o-mini
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely.
      - type: USER
        content: "{{ inputs.prompt }}"

gitHubToken*string

modelName*string

type*object

baseUrlstring

caPemstring

clientPemstring

Use Google Gemini models

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      apiKey: "{{ secret('GOOGLE_API_KEY') }}"
      modelName: gemini-2.5-flash
      thinkingEnabled: true
      thinkingBudgetTokens: 1024
      returnThinking: true
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      apiKey: "{{ secret('GOOGLE_API_KEY') }}"
      modelName: gemini-2.5-flash
      clientPem: "{{ secret('CLIENT_PEM') }}"
      caPem: "{{ secret('CA_PEM') }}"
      baseUrl: "https://internal.gemini.company.com/endpoint"
      thinkingEnabled: true
      thinkingBudgetTokens: 1024
      returnThinking: true
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.GoogleVertexAI
      endpoint: your-vertex-ai-endpoint
      location: your-google-cloud-region
      project: your-google-cloud-project-id
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.HuggingFace
      apiKey: "{{ secret('HUGGING_FACE_API_KEY') }}"
      modelName: HuggingFaceTB/SmolLM3-3B:hf-inference
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://router.huggingface.co/v1

caPemstring

clientPemstring

Use LocalAI OpenAI-compatible server

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.LocalAI
      modelName: gemma-3-1b-it
      baseUrl: http://localhost:8080/v1
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

baseUrl*string

modelName*string

type*object

Possible Values

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

caPemstring

clientPemstring

Use Mistral models

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.MistralAI
      apiKey: "{{ secret('MISTRAL_API_KEY') }}"
      modelName: mistral:7b
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.OciGenAI
      region: "{{ secret('OCI_GENAI_MODEL_REGION_PROPERTY') }}"
      compartmentId: "{{ secret('OCI_GENAI_COMPARTMENT_ID_PROPERTY') }}"
      authProvider: "{{ secret('OCI_GENAI_CONFIG_PROFILE_PROPERTY') }}"
      modelName: oracle.chat.gpt-3.5
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

compartmentId*string

modelName*string

region*string

type*object

authProviderstring

baseUrlstring

caPemstring

clientPemstring

Use local Ollama models

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.Ollama
      modelName: llama3
      endpoint: http://localhost:11434
      thinkingEnabled: true
      returnThinking: true
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.OpenAI
      apiKey: "{{ secret('OPENAI_API_KEY') }}"
      modelName: gpt-5-mini
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.OpenRouter
      apiKey: "{{ secret('OPENROUTER_API_KEY') }}"
      baseUrl: https://openrouter.ai/api/v1
      modelName: x-ai/grok-beta
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.completion.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.WatsonxAI
      apiKey: "{{ secret('WATSONX_API_KEY') }}"
      projectId: "{{ secret('WATSONX_PROJECT_ID') }}"
      modelName: ibm/granite-3-3-8b-instruct
      baseUrl : "https://api.eu-de.dataplatform.cloud.ibm.com/wx"
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

apiKey*string

modelName*string

projectId*string

type*object

baseUrlstring

caPemstring

clientPemstring

Use Cloudflare Workers AI models

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.WorkersAI
      accountId: "{{ secret('WORKERS_AI_ACCOUNT_ID') }}"
      apiKey: "{{ secret('WORKERS_AI_API_KEY') }}"
      modelName: @cf/meta/llama-2-7b-chat-fp16
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

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

Example

yaml
id: chat_completion
namespace: company.ai

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.plugin.ai.ChatCompletion
    provider:
      type: io.kestra.plugin.ai.provider.ZhiPuAI
      apiKey: "{{ secret('ZHIPU_API_KEY') }}"
      modelName: glm-4.5-flash
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{ inputs.prompt }}"

apiKey*string

modelName*string

type*object

baseUrlstring

Defaulthttps://open.bigmodel.cn/

caPemstring

clientPemstring

maxRetriesintegerstring

maxTokenintegerstring

stopsarray

SubTypestring

schemaName *string

configuration

Default{}

Definitions

io.kestra.plugin.ai.domain.ChatConfiguration

logRequestsbooleanstring

logResponsesbooleanstring

maxTokenintegerstring

promptCachingbooleanstring

responseFormat

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

jsonSchemaobject

jsonSchemaDescriptionstring

strictJsonbooleanstring

Defaultfalse

typestring

DefaultTEXT

Possible Values

TEXTJSON

returnThinkingbooleanstring

seedintegerstring

temperaturenumberstring

thinkingBudgetTokensintegerstring

thinkingEnabledbooleanstring

topKintegerstring

topPnumberstring

contentBlocks array

Definitions

io.kestra.plugin.ai.domain.ChatMessage-ContentBlock

textstring

typestring

Possible Values

TEXTIMAGEPDF

uristring

guardrails

Definitions

io.kestra.plugin.ai.domain.Guardrails

inputarray

io.kestra.plugin.ai.domain.GuardrailRule

expression*string

Min length1

message*string

Min length1

outputarray

io.kestra.plugin.ai.domain.GuardrailRule

expression*string

Min length1

message*string

Min length1

prompt string

systemMessage string

DefaultYou are a structured JSON extraction assistant. Always respond with valid JSON.

Outputs

extractedJson string

finishReason string

Possible Values

STOPLENGTHTOOL_EXECUTIONCONTENT_FILTEROTHER

guardrailViolated boolean

Defaultfalse

guardrailViolationMessage string

schemaName string

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

Plugin Weaviate for Kestra

Integrate Google Cloud Platform services with Kestra data workflows.

Gemini Plugin for Kestra

JSONStructuredExtraction Extract JSON fields from text

More Plugins in this Category

JSONStructuredExtraction

Extract JSON fields from text