Package dev.agenor.adapters.knowledge.openai

Class OpenAIEmbeddingProvider

java.lang.Object

dev.agenor.adapters.knowledge.openai.OpenAIEmbeddingProvider

All Implemented Interfaces:

EmbeddingProvider

public class OpenAIEmbeddingProvider
extends Object
implements EmbeddingProvider

EmbeddingProvider backed by the OpenAI Embeddings API.

Default model: text-embedding-3-small (1536 dimensions). Use text-embedding-3-large (3072 dimensions) for higher accuracy at the cost of increased storage and latency.

embedAll(java.util.List<java.lang.String>) sends one batched request, which is what the API is for; embed(java.lang.String) is that call with a single element.

Obtain instances via EmbeddingProviderFactory.openAI(apiKey).

Constructor Summary

Constructors

Constructor	Description
OpenAIEmbeddingProvider(String apiKey)	Creates a provider using text-embedding-3-small (1536 dimensions).
OpenAIEmbeddingProvider(String apiKey, String model, int dimensions)	Creates a provider with an explicit model and dimension count.

Method Summary

Modifier and Type	Method	Description
int	dimensions()	Returns the dimensionality of the vectors produced by this provider.
CompletableFuture<float[]>	embed(String text)	Generates a dense embedding vector for the given text.
CompletableFuture<List<float[]>>	embedAll(List<String> texts)	Generates embedding vectors for a batch of texts.
String	modelId()	Returns the model identifier used by this provider instance.

Methods inherited from class java.lang.Object

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

Constructor Details

OpenAIEmbeddingProvider

public OpenAIEmbeddingProvider(String apiKey)

Creates a provider using text-embedding-3-small (1536 dimensions).

Parameters:

apiKey - OpenAI API key (non-null, non-blank)

OpenAIEmbeddingProvider

public OpenAIEmbeddingProvider(String apiKey,
 String model,
 int dimensions)

Creates a provider with an explicit model and dimension count.

Parameters:

apiKey - OpenAI API key (non-null, non-blank)

model - model identifier (e.g. "text-embedding-3-large")

dimensions - vector dimensionality produced by the model

Method Details

embed

public CompletableFuture<float[]> embed(String text)

Description copied from interface: EmbeddingProvider

Generates a dense embedding vector for the given text.

Specified by:

embed in interface EmbeddingProvider

Parameters:

text - input text (non-null, non-blank)

Returns:

a CompletableFuture that resolves to the embedding vector; the array length equals EmbeddingProvider.dimensions()

embedAll

public CompletableFuture<List<float[]>> embedAll(List<String> texts)

Description copied from interface: EmbeddingProvider

Generates embedding vectors for a batch of texts.

The default implementation delegates to EmbeddingProvider.embed(String) for each element sequentially. Provider implementations should override this method to use a single batched HTTP request where the API supports it (e.g. OpenAI /v1/embeddings with an array input).

Specified by:

embedAll in interface EmbeddingProvider

Parameters:

texts - list of input texts (non-null, non-empty)

Returns:

a CompletableFuture resolving to an ordered list of embedding vectors, one per input text

dimensions

public int dimensions()

Description copied from interface: EmbeddingProvider

Returns the dimensionality of the vectors produced by this provider.

All vectors returned by EmbeddingProvider.embed(java.lang.String) and EmbeddingProvider.embedAll(java.util.List<java.lang.String>) have exactly this many elements. Callers must use this value when allocating vector stores or computing similarity scores.

Specified by:

dimensions in interface EmbeddingProvider

Returns:

positive integer (e.g. 1536 for text-embedding-3-small)

modelId

public String modelId()

Description copied from interface: EmbeddingProvider

Returns the model identifier used by this provider instance.

The format is provider-specific (e.g. "text-embedding-3-small" for OpenAI, "nomic-embed-text" for Ollama).

Specified by:

modelId in interface EmbeddingProvider

Returns:

non-null, non-blank model identifier