Class WatsonxEmbeddingModel

java.lang.Object

dev.langchain4j.model.watsonx.WatsonxEmbeddingModel

All Implemented Interfaces:

EmbeddingModel

public class WatsonxEmbeddingModel
extends Object
implements EmbeddingModel

A EmbeddingModel implementation that integrates IBM watsonx.ai with LangChain4j.

Example usage:

EmbeddingModel embeddingModel = WatsonxEmbeddingModel.builder()
    .baseUrl("https://...") // or use CloudRegion
    .apiKey("...")
    .projectId("...")
    .modelName("ibm/granite-embedding-278m-multilingual")
    .build();

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	WatsonxEmbeddingModel.Builder	Builder class for constructing WatsonxEmbeddingModel instances with configurable parameters.

Method Summary

Modifier and Type	Method	Description
static WatsonxEmbeddingModel.Builder	builder()	Returns a new WatsonxEmbeddingModel.Builder instance.
EmbeddingResponse	doEmbed(EmbeddingRequest request)	Performs the embedding for EmbeddingModel.embed(EmbeddingRequest).
Response<List<Embedding>>	embedAll(List<TextSegment> textSegments, com.ibm.watsonx.ai.embedding.EmbeddingParameters parameters)	Embeds the text content of a list of TextSegment using the specified EmbeddingParameters.
List<EmbeddingModelListener>	listeners()	The EmbeddingModelListeners that are notified around EmbeddingModel.embed(EmbeddingRequest).
String	modelName()	Returns the name of the underlying embedding model.
ModelProvider	provider()	The ModelProvider of this embedding model (for example ModelProvider.OPEN_AI).

Methods inherited from class Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Methods inherited from interface EmbeddingModel

addListener, addListeners, defaultRequestParameters, dimension, doEmbedAsync, embed, embed, embed, embedAll, embedAsync, supportedContentTypes, supportedParameters

Method Details

listeners

public List<EmbeddingModelListener> listeners()

Description copied from interface: EmbeddingModel

The EmbeddingModelListeners that are notified around EmbeddingModel.embed(EmbeddingRequest). Configure them on the model's builder (via listeners(...)). Defaults to an empty list.

Specified by:

listeners in interface EmbeddingModel

provider

public ModelProvider provider()

Description copied from interface: EmbeddingModel

The ModelProvider of this embedding model (for example ModelProvider.OPEN_AI). It is made available to listeners through the request, response and error contexts. Defaults to ModelProvider.OTHER.

Specified by:

provider in interface EmbeddingModel

modelName

public String modelName()

Description copied from interface: EmbeddingModel

Returns the name of the underlying embedding model.

Implementations are encouraged to override this method and provide the actual model name. The default implementation returns "unknown", which indicates that the model name is unknown.

Specified by:

modelName in interface EmbeddingModel

Returns:

the model name or a fallback value if not provided

doEmbed

public EmbeddingResponse doEmbed(EmbeddingRequest request)

Description copied from interface: EmbeddingModel

Performs the embedding for EmbeddingModel.embed(EmbeddingRequest). This is the low-level method a provider overrides to build the actual API call; EmbeddingModel.embed(EmbeddingRequest) handles per-call parameter validation and listener dispatch around it.

An implementation must override either this method (preferred) or EmbeddingModel.embedAll(List) — the two have mutually-recursive defaults, so overriding neither leads to infinite recursion. The default implementation embeds the text of each input via EmbeddingModel.embedAll(List), which keeps implementations that only provide EmbeddingModel.embedAll(List) working.

When this method is called, the request's parameters have already been merged with EmbeddingModel.defaultRequestParameters() and validated against EmbeddingModel.supportedParameters() and EmbeddingModel.supportedContentTypes().

Specified by:

doEmbed in interface EmbeddingModel

Parameters:

request - the request, with parameters already merged and validated.

Returns:

the response.

embedAll

public Response<List<Embedding>> embedAll(List<TextSegment> textSegments,
 com.ibm.watsonx.ai.embedding.EmbeddingParameters parameters)

Embeds the text content of a list of TextSegment using the specified EmbeddingParameters.

The registered EmbeddingModelListeners are notified around the call, as they are for every other embedding method.

Parameters:

textSegments - the text segments to embed.

parameters - the embedding parameters to use.

Returns:

the embeddings.

builder

public static WatsonxEmbeddingModel.Builder builder()

Returns a new WatsonxEmbeddingModel.Builder instance.

Example usage:

EmbeddingModel embeddingModel = WatsonxEmbeddingModel.builder()
    .baseUrl("https://...") // or use CloudRegion
    .apiKey("...")
    .projectId("...")
    .modelName("ibm/granite-embedding-278m-multilingual")
    .build();

Returns:

WatsonxEmbeddingModel.Builder instance.