Chat completion with AI models.

pluginsplugin-langchain4j

This plugin is currently in beta. While it is considered safe for use, please be aware that its API could change in ways that are not compatible with earlier versions in future releases, or it might become unsupported.

Handles chat interactions using AI models (OpenAI, Ollama, Gemini, Anthropic, MistralAI, Deepseek).

yaml
type: "io.kestra.plugin.langchain4j.chatcompletion"

Chat completion with Google Gemini

yaml
id: chat_completion
namespace: company.team

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion
    type: io.kestra.core.plugin.langchain4j.ChatCompletion
    provider:
        type: io.kestra.plugin.langchain4j.provider.GoogleGemini
        apiKey: "{{secret('GOOGLE_API_KEY')}}"
        modelName: gemini-2.0-flash
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{inputs.prompt}}"

Chat Completion with Google Gemini and a WebSearch tool

yaml
id: chat_completion_with_tools
namespace: company.team

inputs:
  - id: prompt
    type: STRING

tasks:
  - id: chat_completion_with_tools
    type: io.kestra.core.plugin.langchain4j.ChatCompletion
    provider:
        type: io.kestra.plugin.langchain4j.provider.GoogleGemini
        apiKey: "{{secret('GOOGLE_API_KEY')}}"
        modelName: gemini-2.0-flash
    messages:
      - type: SYSTEM
        content: You are a helpful assistant, answer concisely, avoid overly casual language or unnecessary verbosity.
      - type: USER
        content: "{{inputs.prompt}}
    tools:
    - type: io.kestra.plugin.langchain4j.tool.GoogleCustomWebSearch
      apiKey: "{{ secret('GOOGLE_SEARCH_API_KEY') }}"
      csi: "{{ secret('GOOGLE_SEARCH_CSI') }}"

SubType

Chat Messages

The list of chat messages for the current conversation. There can be only one system message and the last message must be a user message

Language Model Provider

Default {}

Chat configuration

Tools that the LLM may use to augment its response

AI Response

The generated response from the AI

Possible Values

STOPLENGTHTOOL_EXECUTIONCONTENT_FILTEROTHER

Finish reason

Token usage

Endpoint URL

Project location

Model name

Project ID

Possible Values

SYSTEMAIUSER

API endpoint

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

Model name

API Key

Client ID

Client secret

API version

Tenant ID

API Key

Model name

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

API base URL

API Key

Model name

API Key

Model name

API base URL

API Key

Model endpoint

Model name

seed

Temperature

topK

topP

API Key

Model name

AWS Access Key ID

Model name

AWS Secret Access Key

Default COHERE

Possible Values

COHERETITAN

Amazon Bedrock Embedding Model Type

API Key

Model name

API base URL

SubType string

The MCP client command, as a list of command parts.

SubType string

Environment variables

API Key

SSE URL to the MCP server

Format duration

Connection timeout