Search

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.

Search from an embedding store.

Performs a semantic search using a query string.

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

Examples

Make a search query against an embedding store.

yaml
id: search_embeddings_flow
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: search
    type: io.kestra.plugin.langchain4j.rag.Search
    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
    query: "Feature Highlights"
    maxResults: 5
    minScore: 0.5
    fetchType: FETCH

Properties

embeddings *Elasticsearch KestraKVStore PGVector

The embedding store provider

maxResults *integerstring

Maximum number of results to return

minScore *numberstring

Minimum similarity score

provider *AmazonBedrock Anthropic AzureOpenAI DeepSeek GoogleGemini GoogleVertexAI MistralAI Ollama OpenAI

The embedding model provider

query *string

Query string to search for

fetchType string

Default NONE

Possible Values

STOREFETCHFETCH_ONENONE

Outputs

results array

SubType string

List of matching text results

size integer

The count of the fetched or stored resources

uri string

Format uri

The output files URI in Kestra's internal storage

Only available when fetchType is set to STORE

Definitions

Google VertexAI Model Provider

endpoint *string

Endpoint URL

location *string

Project location

modelName *string

Model name

project *string

Project ID

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

type *object

apiKey string

API Key

clientId string

Client ID

clientSecret string

Client secret

serviceVersion string

API version

tenantId string

Tenant ID

Deepseek Model Provider

apiKey *string

API Key

modelName *string

Model name

type *object

baseUrl string

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

API base URL

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

hosts *array

SubType string

Min items 1

List of HTTP ElasticSearch servers.

Must be an URI like https://elasticsearch.com: 9200 with scheme and port.

basicAuth Elasticsearch-ElasticsearchConnection-BasicAuth

Basic auth configuration.

headers array

SubType string

List of HTTP headers to be send on every request.

Must be a string with key value separated with : , ex: Authorization: Token XYZ.

pathPrefix string

Sets the path's prefix for every request used by the HTTP client.

For example, if this is set to /my/path, then any client request will become /my/path/ + endpoint. In essence, every request's endpoint is prefixed by this pathPrefix. The path prefix is useful for when ElasticSearch is behind a proxy that provides a base path or a proxy that requires all paths to start with '/'; it is not intended for other purposes and it should not be supplied in other scenarios.

strictDeprecationMode booleanstring

Whether the REST client should return any response containing at least one warning header as a failure.

trustAllSsl booleanstring

Trust all SSL CA certificates.

Use this if the server is using a self signed SSL certificate.

Anthropic AI Model Provider

apiKey *string

API Key

modelName *string

Model name

type *object

OpenAI Model Provider

apiKey *string

API Key

modelName *string

Model name

type *object

baseUrl string

API base URL

Ollama Model Provider

endpoint *string

Model endpoint

modelName *string

Model name

type *object

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

password string

Basic auth password.

username string

Basic auth username.

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

The name of the K/V entry to use

Google Gemini Model Provider

apiKey *string

API Key

modelName *string

Model name

type *object

Amazon Bedrock Model Provider

accessKeyId *string

AWS Access Key ID

modelName *string

Model name

secretAccessKey *string

AWS Secret Access Key

type *object

modelType string

Default COHERE

Possible Values

COHERETITAN

Amazon Bedrock Embedding Model Type

PGVector Embedding Store

database *string

The database name

host *string

The database server host

password *string

The database password

port *integerstring

The database server port

table *string

The table to store embeddings in

type *object

user *string

The database user

useIndex booleanstring

Default false

Whether to use use an IVFFlat index

An IVFFlat index divides vectors into lists, and then searches a subset of those lists closest to the query vector. It has faster build times and uses less memory than HNSW but has lower query performance (in terms of speed-recall tradeoff).

Mistral AI Model Provider

apiKey *string

API Key

modelName *string

Model name

type *object

baseUrl string

API base URL

Elasticsearch Embedding Store

connection *Elasticsearch-ElasticsearchConnection

indexName *string

The name of the index to store embeddings

type *object

​Search

Search