AIAgent

Call an AI Agent as a tool

This tool allows an LLM to call an AI Agent. Make sure to specify a name and a description so the LLM can understand what it does to decide if it needs to call it.

yaml
type: "io.kestra.plugin.ai.tool.AIAgent"

Examples

Call an AI agent as a tool

yaml
id: ai-agent-with-agent-tools
namespace: company.ai

inputs:
  - id: prompt
    type: STRING
    defaults: |
      Each flow can produce outputs that can be consumed by other flows. This is a list property, so that your flow can produce as many outputs as you need.
      Each output needs to have an ID (the name of the output), a type (the same types you know from inputs, e.g., STRING, URI, or JSON), and a value, which is the actual output value that will be stored in internal storage and passed to other flows when needed.
tasks:
  - id: ai-agent
    type: io.kestra.plugin.ai.agent.AIAgent
    provider:
      type: io.kestra.plugin.ai.provider.GoogleGemini
      modelName: gemini-2.5-flash
      apiKey: "{{ kv('GEMINI_API_KEY') }}"
    systemMessage: Summarize the user message, then translate it into French using the provided tool.
    prompt: "{{inputs.prompt}}"
    tools:
      - type: io.kestra.plugin.ai.tool.AIAgent
        description: Translation expert
        systemMessage: You are an expert in translating text between multiple languages
        provider:
          type: io.kestra.plugin.ai.provider.GoogleGemini
          modelName: gemini-2.5-flash-lite
          apiKey: "{{ kv('GEMINI_API_KEY') }}"

Properties

description *string

Agent description

The description will be used to instruct the LLM what the tool is doing.

provider *AmazonBedrock Anthropic AzureOpenAI DashScope DeepSeek GoogleGemini GoogleVertexAI HuggingFace LocalAI MistralAI OciGenAI Ollama OpenAI OpenRouter WorkersAI ZhiPuAI

Language model provider

configuration ChatConfiguration

Default {}

Language model configuration

contentRetrievers GoogleCustomWebSearch SqlDatabaseRetriever TavilyWebSearch

Content retrievers

Some content retrievers, like WebSearch, can also be used as tools. However, when configured as content retrievers, they will always be used, whereas tools are only invoked when the LLM decides to use them.

maxSequentialToolsInvocations integerstring

Maximum sequential tools invocations

name string

Default tool

Agent name

It must be set to a different value than the default in case you want to have multiple agents used as tools in the same task.

systemMessage string

System message

The system message for the language model

tools A2AAgent AIAgent CodeExecution DockerMcpClient GoogleCustomWebSearch KestraFlow KestraTask SseMcpClient StdioMcpClient StreamableHttpMcpClient TavilyWebSearch

Tools that the LLM may use to augment its response

Definitions

io.kestra.core.models.tasks.retrys.Constant

interval *string

Format duration

type *object

behavior string

Default RETRY_FAILED_TASK

Possible Values

RETRY_FAILED_TASKCREATE_NEW_EXECUTION

maxAttempts integer

Minimum >= 1

maxDuration string

Format duration

warningOnRetry boolean

Default false

Mistral AI Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

Model Context Protocol (MCP) Stdio client tool

command *array

SubType string

MCP client command, as a list of command parts

env object

SubType string

Environment variables

logEvents booleanstring

Default false

Log events

type object

io.kestra.core.models.tasks.retrys.Exponential

interval *string

Format duration

maxInterval *string

Format duration

type *object

behavior string

Default RETRY_FAILED_TASK

Possible Values

RETRY_FAILED_TASKCREATE_NEW_EXECUTION

delayFactor number

maxAttempts integer

Minimum >= 1

maxDuration string

Format duration

warningOnRetry boolean

Default false

ZhiPu AI Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Default https://open.bigmodel.cn/

API base URL

The base URL for ZhiPu API (defaults to https://open.bigmodel.cn/)

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

maxRetries integerstring

The maximum retry times to request

maxToken integerstring

The maximum number of tokens returned by this request

stops array

SubType string

With the stop parameter, the model will automatically stop generating text when it is about to contain the specified string or token_id

type object

Call a Kestra flow as a tool

description string

Description of the flow if not already provided inside the flow itself

Use it only if you define the flow in the tool definition. The LLM needs a tool description to identify whether to call it. If the flow has a description, the tool will use it. Otherwise, the description property must be explicitly defined.

flowId string

Flow ID of the flow that should be called

inheritLabels booleanstring

Default false

Whether the flow should inherit labels from this execution that triggered it

By default, labels are not inherited. If you set this option to true, the flow execution will inherit all labels from the agent's execution. Any labels passed by the LLM will override those defined here.

inputs object

Input values that should be passed to flow's execution

Any inputs passed by the LLM will override those defined here.

labels arrayobject

Labels that should be added to the flow's execution

Any labels passed by the LLM will override those defined here.

namespace string

Namespace of the flow that should be called

revision integerstring

Revision of the flow that should be called

scheduleDate string

Format date-time

Schedule the flow execution at a later date

If the LLM sets a scheduleDate, it will override the one defined here.

type object

Model Context Protocol (MCP) SSE client tool

url *string

URL of the MCP server

headers object

SubType string

Custom headers

Useful, for example, for adding authentication tokens via the Authorization header.

logRequests booleanstring

Default false

Log requests

logResponses booleanstring

Default false

Log responses

timeout string

Format duration

Connection timeout duration

type object

Call a Kestra runnable task as a tool

tasks *array

SubType

List of Kestra runnable tasks

type object

Deepseek Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Default https://api.deepseek.com/v1

API base URL

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

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

jsonSchema object

JSON Schema (used when type = JSON)

Provide a JSON Schema describing the expected structure of the response. In Kestra flows, define the schema in YAML (it is still a JSON Schema object). Example (YAML):

text

responseFormat: 
    type: JSON
    jsonSchema: 
      type: object
      required: ["category", "priority"]
      properties: 
        category: 
          type: string
          enum: ["ACCOUNT", "BILLING", "TECHNICAL", "GENERAL"]
        priority: 
          type: string
          enum: ["LOW", "MEDIUM", "HIGH"]

Note: Provider support for strict schema enforcement varies. If unsupported, guide the model about the expected output structure via the prompt and validate downstream.

jsonSchemaDescription string

Schema description (optional)

Natural-language description of the schema to help the model produce the right fields. Example: "Classify a customer ticket into category and priority."

type string

Default TEXT

Possible Values

TEXTJSON

Response format type

Specifies how the LLM should return output. Allowed values:

TEXT (default): free-form natural language.
JSON: structured output validated against a JSON Schema.

OpenRouter Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

io.kestra.core.models.tasks.retrys.Random

maxInterval *string

Format duration

minInterval *string

Format duration

type *object

behavior string

Default RETRY_FAILED_TASK

Possible Values

RETRY_FAILED_TASKCREATE_NEW_EXECUTION

maxAttempts integer

Minimum >= 1

maxDuration string

Format duration

warningOnRetry boolean

Default false

Model Context Protocol (MCP) Docker client tool

image *string

Container image

apiVersion string

API version

binds array

SubType string

Volume binds

command array

SubType string

MCP client command, as a list of command parts

dockerCertPath string

Docker certificate path

dockerConfig string

Docker configuration

dockerContext string

Docker context

dockerHost string

Docker host

dockerTlsVerify booleanstring

Whether Docker should verify TLS certificates

env object

SubType string

Environment variables

logEvents booleanstring

Default false

Whether to log events

registryEmail string

Container registry email

registryPassword string

Container registry password

registryUrl string

Container registry URL

registryUsername string

Container registry username

type object

Google Custom Search web tool

apiKey *string

API key

csi *string

Custom search engine ID (cx)

type object

Ollama Model Provider

endpoint *string

Model endpoint

modelName *string

Model name

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

Code execution tool using Judge0

apiKey *string

RapidAPI key for Judge0

You can obtain it from the RapidAPI website.

type object

OpenAI Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Default https://api.openai.com/v1

API base URL

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

SQL Database content retriever using LangChain4j experimental SqlDatabaseContentRetriever. ⚠ IMPORTANT: the database user should have READ-ONLY permissions.

databaseType *string

Possible Values

POSTGRESQLMYSQLH2

Type of database to connect to (PostgreSQL, MySQL, or H2)

Determines the default JDBC driver and connection format.

password *string

Database password

provider *AmazonBedrock Anthropic AzureOpenAI DashScope DeepSeek GoogleGemini GoogleVertexAI HuggingFace LocalAI MistralAI OciGenAI Ollama OpenAI OpenRouter WorkersAI ZhiPuAI

Language model provider

username *string

Database username

configuration ChatConfiguration

Default {}

Language model configuration

driver string

Optional JDBC driver class name – automatically resolved if not provided.

jdbcUrl string

JDBC connection URL to the target database

maxPoolSize integerstring

Default 2

Maximum number of database connections in the pool

type object

Web search content retriever for Google Custom Search

apiKey *string

API key

csi *string

Custom search engine ID (cx)

maxResults integerstring

Default 3

Maximum number of results

type object

io.kestra.plugin.ai.domain.ChatConfiguration

logRequests booleanstring

Log LLM requests

If true, prompts and configuration sent to the LLM will be logged at INFO level.

logResponses booleanstring

Log LLM responses

If true, raw responses from the LLM will be logged at INFO level.

maxToken integerstring

Maximum number of tokens the model can generate in the completion (response). This limits the length of the output.

responseFormat ChatConfiguration-ResponseFormat

Response format

Defines the expected output format. Default is plain text. Some providers allow requesting JSON or schema-constrained outputs, but support varies and may be incompatible with tool use. When using a JSON schema, the output will be returned under the key jsonOutput.

returnThinking booleanstring

Return Thinking

Controls whether to return the model's internal reasoning or 'thinking' text, if available. When enabled, the reasoning content is extracted from the response and made available in the AiMessage object. It Does not trigger the thinking process itself—only affects whether the output is parsed and returned.

seed integerstring

Seed

Optional random seed for reproducibility. Provide a positive integer (e.g., 42, 1234). Using the same seed with identical settings produces repeatable outputs.

temperature numberstring

Temperature

Controls randomness in generation. Typical range is 0.0–1.0. Lower values (e.g., 0.2) make outputs more focused and deterministic, while higher values (e.g., 0.7–1.0) increase creativity and variability.

thinkingBudgetTokens integerstring

Thinking Token Budget

Specifies the maximum number of tokens allocated as a budget for internal reasoning processes, such as generating intermediate thoughts or chain-of-thought sequences, allowing the model to perform multi-step reasoning before producing the final output.

thinkingEnabled booleanstring

Enable Thinking

Enables internal reasoning ('thinking') in supported language models, allowing the model to perform intermediate reasoning steps before producing a final output; this is useful for complex tasks like multi-step problem solving or decision making, but may increase token usage and response time, and is only applicable to compatible models.

topK integerstring

Top-K

Limits sampling to the top K most likely tokens at each step. Typical values are between 20 and 100. Smaller values reduce randomness; larger values allow more diverse outputs.

topP numberstring

Top-P (nucleus sampling)

Selects from the smallest set of tokens whose cumulative probability is ≤ topP. Typical values are 0.8–0.95. Lower values make the output more focused, higher values increase diversity.

io.kestra.core.models.tasks.Cache

enabled *boolean

ttl string

Format duration

io.kestra.core.models.tasks.WorkerGroup

fallback string

Possible Values

FAILWAITCANCEL

key string

WorkersAI Model Provider

accountId *string

Account Identifier

Unique identifier assigned to an account

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

Azure OpenAI Model Provider

endpoint *string

API endpoint

The Azure OpenAI endpoint in the format: https://{resource}.openai.azure.com/

modelName *string

Model name

apiKey string

API Key

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientId string

Client ID

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

clientSecret string

Client secret

serviceVersion string

API version

tenantId string

Tenant ID

type object

Google VertexAI Model Provider

endpoint *string

Endpoint URL

location *string

Project location

modelName *string

Model name

project *string

Project ID

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

Google Gemini Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

OciGenAI Model Provider

compartmentId *string

OCID of OCI Compartment with the model

modelName *string

Model name

region *string

OCI Region to connect the client to

authProvider string

OCI SDK Authentication provider

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

Call a remote AI agent via the A2A protocol.

description *string

Agent description

The description will be used to instruct the LLM what the tool is doing.

serverUrl *string

Server URL

The URL of the remote agent A2A server

name string

Default tool

Agent name

It must be set to a different value than the default in case you want to have multiple agents used as tools in the same task.

type object

Model Context Protocol (MCP) SSE client tool

sseUrl *string

SSE URL of the MCP server

headers object

SubType string

Custom headers

Could be useful, for example, to add authentication tokens via the Authorization header.

logRequests booleanstring

Default false

Log requests

logResponses booleanstring

Default false

Log responses

timeout string

Format duration

Connection timeout duration

type object

WebSearch content retriever for Tavily Search

apiKey *string

API Key

maxResults integerstring

Default 3

Maximum number of results to return

type object

Anthropic AI Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

maxTokens integerstring

Maximum Tokens

Specifies the maximum number of tokens that the model is allowed to generate in its response.

type object

WebSearch tool for Tavily Search

apiKey *string

Tavily API Key - you can obtain one from the Tavily website

type object

DashScope (Qwen) Model Provider from Alibaba Cloud

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Default https://dashscope-intl.aliyuncs.com/api/v1

API base URL

text

If you use a model in the China (Beijing) region, you need to replace the URL with: https://dashscope.aliyuncs.com/api/v1,
otherwise use the Singapore region of: "https://dashscope-intl.aliyuncs.com/api/v1.
The default value is computed based on the system timezone.

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

enableSearch booleanstring

Whether the model uses Internet search results for reference when generating text or not

maxTokens integerstring

The maximum number of tokens returned by this request

repetitionPenalty numberstring

Repetition in a continuous sequence during model generation

text

Increasing repetition_penalty reduces the repetition in model generation,
1.0 means no penalty. Value range: (0, +inf)

type object

LocalAI Model Provider

baseUrl *string

API base URL

modelName *string

Model name

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

Amazon Bedrock Model Provider

accessKeyId *string

AWS Access Key ID

modelName *string

Model name

secretAccessKey *string

AWS Secret Access Key

baseUrl string

Base URL

Custom base URL to override the default endpoint (useful for local tests, WireMock, or enterprise gateways).

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

modelType string

Default COHERE

Possible Values

COHERETITAN

Amazon Bedrock Embedding Model Type

type object

HuggingFace Model Provider

apiKey *string

API Key

modelName *string

Model name

baseUrl string

Default https://router.huggingface.co/v1

API base URL

caPem string

CA PEM certificate content

CA certificate as text, used to verify SSL/TLS connections when using custom endpoints.

clientPem string

Client PEM certificate content

PEM client certificate as text, used to authenticate the connection to enterprise AI endpoints.

type object

​A​I​Agent

AIAgent