ChatCompletion

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.

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

Examples

yaml
id: rag
namespace: company.team

tasks:
  - id: ingest
    type: io.kestra.plugin.langchain4j.rag.IngestDocument
    provider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-embedding-exp-03-07
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    embeddings:
      type: io.kestra.plugin.langchain4j.embeddings.KestraKVStore
    drop: true
    fromExternalURLs:
      - https://raw.githubusercontent.com/kestra-io/docs/refs/heads/main/content/blogs/release-0-22.md

  - id: chat_without_rag
    type: io.kestra.plugin.langchain4j.ChatCompletion
    provider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-2.0-flash
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    messages:
    - type: user
      content: Which features were released in Kestra 0.22?

  - id: chat_with_rag
    type: io.kestra.plugin.langchain4j.rag.ChatCompletion
    chatProvider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-2.0-flash
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    embeddingProvider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-embedding-exp-03-07
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    embeddings:
      type: io.kestra.plugin.langchain4j.embeddings.KestraKVStore
    prompt: Which features were released in Kestra 0.22?

yaml
id: rag
namespace: company.team

tasks:
  - id: chat_with_rag_and_websearch_content_retriever
    type: io.kestra.plugin.langchain4j.rag.ChatCompletion
    chatProvider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-2.0-flash
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    contentRetrievers:
    - type: io.kestra.plugin.langchain4j.retriever.GoogleCustomWebSearch
      apiKey: "{{ secret('GOOGLE_SEARCH_API_KEY') }}"
      csi: "{{ secret('GOOGLE_SEARCH_CSI') }}"
    prompt: What is the latest release of Kestra?

yaml
id: rag
namespace: company.team

tasks:
  - id: ingest
    type: io.kestra.plugin.langchain4j.rag.IngestDocument
    provider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-embedding-exp-03-07
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    embeddings:
      type: io.kestra.plugin.langchain4j.embeddings.KestraKVStore
    drop: true
    fromExternalURLs:
      - https://raw.githubusercontent.com/kestra-io/docs/refs/heads/main/content/blogs/release-0-22.md

  - id: chat_with_rag_and_tool
    type: io.kestra.plugin.langchain4j.rag.ChatCompletion
    chatProvider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-2.0-flash
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    embeddingProvider:
      type: io.kestra.plugin.langchain4j.provider.GoogleGemini
      modelName: gemini-embedding-exp-03-07
      apiKey: "{{ secret('GEMINI_API_KEY') }}"
    embeddings:
      type: io.kestra.plugin.langchain4j.embeddings.KestraKVStore
    tools:
    - type: io.kestra.plugin.langchain4j.tool.GoogleCustomWebSearch
      apiKey: "{{ secret('GOOGLE_SEARCH_API_KEY') }}"
      csi: "{{ secret('GOOGLE_SEARCH_CSI') }}"
    prompt: What is the latest release of Kestra?

Properties

chatProvider *AmazonBedrock Anthropic AzureOpenAI DeepSeek GoogleGemini GoogleVertexAI MistralAI Ollama OpenAI

prompt *string

chatConfiguration ChatConfiguration

Default {}

contentRetrieverConfiguration ChatCompletion-ContentRetrieverConfiguration

Default

{
  "maxResults": 3,
  "minScore": 0
}

contentRetrievers GoogleCustomWebSearch TavilyWebSearch

embeddingProvider AmazonBedrock Anthropic AzureOpenAI DeepSeek GoogleGemini GoogleVertexAI MistralAI Ollama OpenAI

embeddings Elasticsearch KestraKVStore PGVector

tools GoogleCustomWebSearch HttpMcpClient StdioMcpClient TavilyWebSearch

Outputs

completion string

finishReason string

Possible Values

STOPLENGTHTOOL_EXECUTIONCONTENT_FILTEROTHER

tokenUsage TokenUsage

Definitions

io.kestra.plugin.langchain4j.rag.ChatCompletion-ContentRetrieverConfiguration

maxResults integer

Default 3

minScore number

Default 0

Google VertexAI Model Provider

endpoint *string

location *string

modelName *string

project *string

type *object

Azure OpenAI Model Provider

endpoint *string

modelName *string

type *object

apiKey string

clientId string

clientSecret string

serviceVersion string

tenantId string

Deepseek Model Provider

apiKey *string

modelName *string

type *object

baseUrl string

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

WebSearch content retriever for Tavily Search

apiKey *string

type *object

maxResults integerstring

Default 3

io.kestra.plugin.langchain4j.embeddings.Elasticsearch-ElasticsearchConnection

hosts *array

SubType string

Min items 1

basicAuth Elasticsearch-ElasticsearchConnection-BasicAuth

headers array

SubType string

pathPrefix string

strictDeprecationMode booleanstring

trustAllSsl booleanstring

Anthropic AI Model Provider

apiKey *string

modelName *string

type *object

OpenAI Model Provider

apiKey *string

modelName *string

type *object

baseUrl string

WebSearch tool for Tavily Search

apiKey *string

type *object

Ollama Model Provider

endpoint *string

modelName *string

type *object

io.kestra.plugin.langchain4j.embeddings.Elasticsearch-ElasticsearchConnection-BasicAuth

password string

username string

io.kestra.plugin.langchain4j.domain.ChatConfiguration

seed integerstring

temperature numberstring

topK integerstring

topP numberstring

In-memory Embedding Store that then store its serialization form as a Kestra K/V pair

type *object

kvName string

Default {{flow.id}}-embedding-store

Google Gemini Model Provider

apiKey *string

modelName *string

type *object

Amazon Bedrock Model Provider

accessKeyId *string

modelName *string

secretAccessKey *string

type *object

modelType string

Default COHERE

Possible Values

COHERETITAN

PGVector Embedding Store

database *string

host *string

password *string

port *integerstring

table *string

type *object

user *string

useIndex booleanstring

Default false

Mistral AI Model Provider

apiKey *string

modelName *string

type *object

baseUrl string

WebSearch content retriever for Google Custom Search

apiKey *string

csi *string

type *object

maxResults integerstring

Default 3

Model Context Protocol (MCP) HTTP client tool

command *array

SubType string

type *object

environment object

SubType string

WebSearch tool for Google Custom Search

apiKey *string

csi *string

type *object

Model Context Protocol (MCP) HTTP client tool

sseUrl *string

type *object

timeout string

Format duration

io.kestra.plugin.langchain4j.domain.TokenUsage

inputTokenCount integer

outputTokenCount integer

totalTokenCount integer

Elasticsearch Embedding Store

connection *Elasticsearch-ElasticsearchConnection

indexName *string

type *object

​Chat​Completion

ChatCompletion