Package io.quarkiverse.langchain4j.azure.openai

Class AzureOpenAiEmbeddingModel

java.lang.Object

io.quarkiverse.langchain4j.azure.openai.AzureOpenAiEmbeddingModel

All Implemented Interfaces:

dev.langchain4j.model.embedding.EmbeddingModel, dev.langchain4j.model.embedding.TokenCountEstimator

public class AzureOpenAiEmbeddingModel
extends Object
implements dev.langchain4j.model.embedding.EmbeddingModel, dev.langchain4j.model.embedding.TokenCountEstimator

Represents an OpenAI embedding model, hosted on Azure, such as text-embedding-ada-002.

Mandatory parameters for initialization are: apiVersion, apiKey, and either endpoint OR resourceName and deploymentName.

There are two primary authentication methods to access Azure OpenAI:

1. API Key Authentication: For this type of authentication, HTTP requests must include the API Key in the "api-key" HTTP header.

2. Azure Active Directory Authentication: For this type of authentication, HTTP requests must include the authentication/access token in the "Authorization" HTTP header.

More information

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	AzureOpenAiEmbeddingModel.Builder

Constructor Summary

Constructors

Constructor	Description
AzureOpenAiEmbeddingModel(String endpoint, String apiVersion, String apiKey, String adToken, dev.langchain4j.model.Tokenizer tokenizer, Duration timeout, Integer maxRetries, Proxy proxy, Boolean logRequests, Boolean logResponses, String configName)

Method Summary

Modifier and Type	Method	Description
static AzureOpenAiEmbeddingModel.Builder	builder()
dev.langchain4j.model.output.Response<List<dev.langchain4j.data.embedding.Embedding>>	embedAll(List<dev.langchain4j.data.segment.TextSegment> textSegments)	Embeds the provided text segments, processing a maximum of 16 segments at a time.
int	estimateTokenCount(String text)

Methods inherited from class java.lang.Object

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

Methods inherited from interface dev.langchain4j.model.embedding.EmbeddingModel

dimension, embed, embed

Methods inherited from interface dev.langchain4j.model.embedding.TokenCountEstimator

estimateTokenCount, estimateTokenCount

Constructor Details

AzureOpenAiEmbeddingModel

public AzureOpenAiEmbeddingModel(String endpoint,
 String apiVersion,
 String apiKey,
 String adToken,
 dev.langchain4j.model.Tokenizer tokenizer,
 Duration timeout,
 Integer maxRetries,
 Proxy proxy,
 Boolean logRequests,
 Boolean logResponses,
 String configName)

Method Details

embedAll

public dev.langchain4j.model.output.Response<List<dev.langchain4j.data.embedding.Embedding>> embedAll(List<dev.langchain4j.data.segment.TextSegment> textSegments)

Embeds the provided text segments, processing a maximum of 16 segments at a time. For more information, refer to the documentation here.

Specified by:

embedAll in interface dev.langchain4j.model.embedding.EmbeddingModel

Parameters:

textSegments - A list of text segments.

Returns:

A list of corresponding embeddings.

estimateTokenCount

public int estimateTokenCount(String text)

Specified by:

estimateTokenCount in interface dev.langchain4j.model.embedding.TokenCountEstimator

builder

public static AzureOpenAiEmbeddingModel.Builder builder()