Class CohereEmbeddingModel
java.lang.Object
dev.langchain4j.model.embedding.DimensionAwareEmbeddingModel
dev.langchain4j.model.cohere.CohereEmbeddingModel
- All Implemented Interfaces:
EmbeddingModel
An implementation of an
EmbeddingModel that uses
Cohere Embed API.-
Nested Class Summary
Nested Classes -
Field Summary
Fields inherited from class DimensionAwareEmbeddingModel
dimension -
Constructor Summary
Constructors -
Method Summary
Modifier and TypeMethodDescriptionbuilder()doEmbed(EmbeddingRequest request) Embeds via Cohere's v2 embed endpoint (/v2/embed), which handles both text and images (Embed v4).embedAll(List<TextSegment> textSegments) Embeds the text content of a list ofTextSegments.TheEmbeddingModelListeners that are notified aroundEmbeddingModel.embed(EmbeddingRequest).Returns the name of the underlying embedding model.provider()TheModelProviderof this embedding model (for exampleModelProvider.OPEN_AI).The inputcontent typesthis model can embed.The per-callparametersthis model honors.static CohereEmbeddingModelwithApiKey(String apiKey) Deprecated, for removal: This API element is subject to removal in a future version.Methods inherited from class DimensionAwareEmbeddingModel
dimension, knownDimensionMethods inherited from class Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitMethods inherited from interface EmbeddingModel
addListener, addListeners, defaultRequestParameters, embed, embed, embed
-
Constructor Details
-
CohereEmbeddingModel
@Deprecated(forRemoval=true, since="1.4.0") public CohereEmbeddingModel(String baseUrl, String apiKey, String modelName, String inputType, Duration timeout, Boolean logRequests, Boolean logResponses, Integer maxSegmentsPerBatch) Deprecated, for removal: This API element is subject to removal in a future version. -
CohereEmbeddingModel
-
-
Method Details
-
listeners
Description copied from interface:EmbeddingModelTheEmbeddingModelListeners that are notified aroundEmbeddingModel.embed(EmbeddingRequest). Configure them on the model's builder (vialisteners(...)). Defaults to an empty list. -
provider
Description copied from interface:EmbeddingModelTheModelProviderof this embedding model (for exampleModelProvider.OPEN_AI). It is made available tolistenersthrough the request, response and error contexts. Defaults toModelProvider.OTHER. -
withApiKey
Deprecated, for removal: This API element is subject to removal in a future version.Please usebuilder()instead, and explicitly set the model name and, if necessary, other parameters. -
builder
-
embedAll
Description copied from interface:EmbeddingModelEmbeds the text content of a list ofTextSegments.This is a convenience method over
EmbeddingModel.embed(EmbeddingRequest), solistenersare notified and the model's default per-call parameters are applied here too. A provider implements its embedding logic by overridingEmbeddingModel.doEmbed(EmbeddingRequest)(preferred); it may still override this method for batch-specific behavior that the request/response API does not carry (for example applying a document title fromTextSegmentmetadata).- Parameters:
textSegments- the text segments to embed.- Returns:
- the embeddings.
-
modelName
Description copied from interface:EmbeddingModelReturns 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.- Returns:
- the model name or a fallback value if not provided
-
supportedContentTypes
Description copied from interface:EmbeddingModelThe inputcontent typesthis model can embed. A request whose inputs use a content type outside this set is rejected byEmbeddingModel.embed(EmbeddingRequest)with anUnsupportedFeatureException. Defaults to{TEXT}; a multimodal model overrides this to also accept, for example,images. -
supportedParameters
Description copied from interface:EmbeddingModelThe per-callparametersthis model honors. A request that populates a parameter outside this set is rejected byEmbeddingModel.embed(EmbeddingRequest)with anUnsupportedFeatureException, so a parameter a model cannot apply is never silently ignored. Defaults to an empty set (the model accepts no per-call parameters). -
doEmbed
Embeds via Cohere's v2 embed endpoint (/v2/embed), which handles both text and images (Embed v4). EachEmbeddingInputmay interleave text and image parts into a single embedding.- Parameters:
request- the request, with parameters already merged and validated.- Returns:
- the response.
-
builder()instead, and explicitly set the model name and, if necessary, other parameters.