dev.langchain4j.model.azure

Class AzureOpenAiLanguageModel

java.lang.Object

dev.langchain4j.model.azure.AzureOpenAiLanguageModel

All Implemented Interfaces:

dev.langchain4j.model.language.LanguageModel, dev.langchain4j.model.language.TokenCountEstimator

public class AzureOpenAiLanguageModel
extends Object
implements dev.langchain4j.model.language.LanguageModel, dev.langchain4j.model.language.TokenCountEstimator

Represents an OpenAI language model, hosted on Azure, such as gpt-3.5-turbo-instruct. However, it's recommended to use AzureOpenAiChatModel instead, as it offers more advanced features like function calling, multi-turn conversations, etc.

Mandatory parameters for initialization are: endpoint, serviceVersion, apikey (or an alternate authentication method, see below for more information) and deploymentName. You can also provide your own OpenAIClient instance, if you need more flexibility.

There are 3 authentication methods:

1. Azure OpenAI API Key Authentication: this is the most common method, using an Azure OpenAI API key. You need to provide the OpenAI API Key as a parameter, using the apiKey() method in the Builder, or the apiKey parameter in the constructor: For example, you would use `builder.apiKey("{key}")`.

2. non-Azure OpenAI API Key Authentication: this method allows to use the OpenAI service, instead of Azure OpenAI. You can use the nonAzureApiKey() method in the Builder, which will also automatically set the endpoint to "https://api.openai.com/v1". For example, you would use `builder.nonAzureApiKey("{key}")`. The constructor requires a KeyCredential instance, which can be created using `new AzureKeyCredential("{key}")`, and doesn't set up the endpoint.

3. Azure OpenAI client with Microsoft Entra ID (formerly Azure Active Directory) credentials. - This requires to add the `com.azure:azure-identity` dependency to your project, which is an optional dependency to this library. - You need to provide a TokenCredential instance, using the tokenCredential() method in the Builder, or the tokenCredential parameter in the constructor. As an example, DefaultAzureCredential can be used to authenticate the client: Set the values of the client ID, tenant ID, and client secret of the AAD application as environment variables: AZURE_CLIENT_ID, AZURE_TENANT_ID, AZURE_CLIENT_SECRET. Then, provide the DefaultAzureCredential instance to the builder: `builder.tokenCredential(new DefaultAzureCredentialBuilder().build())`.

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AzureOpenAiLanguageModel.Builder

Constructor Summary

Constructors

Constructor and Description
AzureOpenAiLanguageModel(com.azure.ai.openai.OpenAIClient client, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, Double presencePenalty, Double frequencyPenalty)
AzureOpenAiLanguageModel(String endpoint, String serviceVersion, com.azure.core.credential.KeyCredential keyCredential, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, Double presencePenalty, Double frequencyPenalty, Duration timeout, Integer maxRetries, com.azure.core.http.ProxyOptions proxyOptions, boolean logRequestsAndResponses)
AzureOpenAiLanguageModel(String endpoint, String serviceVersion, String apiKey, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, Double presencePenalty, Double frequencyPenalty, Duration timeout, Integer maxRetries, com.azure.core.http.ProxyOptions proxyOptions, boolean logRequestsAndResponses)
AzureOpenAiLanguageModel(String endpoint, String serviceVersion, com.azure.core.credential.TokenCredential tokenCredential, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, Double presencePenalty, Double frequencyPenalty, Duration timeout, Integer maxRetries, com.azure.core.http.ProxyOptions proxyOptions, boolean logRequestsAndResponses)

Method Summary

Modifier and Type	Method and Description
static AzureOpenAiLanguageModel.Builder	builder()
int	estimateTokenCount(String prompt)
dev.langchain4j.model.output.Response<String>	generate(String prompt)

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.language.LanguageModel

generate

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

estimateTokenCount, estimateTokenCount

Constructor Detail

AzureOpenAiLanguageModel

public AzureOpenAiLanguageModel(com.azure.ai.openai.OpenAIClient client,
                                String deploymentName,
                                dev.langchain4j.model.Tokenizer tokenizer,
                                Double temperature,
                                Double topP,
                                Integer maxTokens,
                                Double presencePenalty,
                                Double frequencyPenalty)

AzureOpenAiLanguageModel

public AzureOpenAiLanguageModel(String endpoint,
                                String serviceVersion,
                                String apiKey,
                                String deploymentName,
                                dev.langchain4j.model.Tokenizer tokenizer,
                                Double temperature,
                                Double topP,
                                Integer maxTokens,
                                Double presencePenalty,
                                Double frequencyPenalty,
                                Duration timeout,
                                Integer maxRetries,
                                com.azure.core.http.ProxyOptions proxyOptions,
                                boolean logRequestsAndResponses)

AzureOpenAiLanguageModel

public AzureOpenAiLanguageModel(String endpoint,
                                String serviceVersion,
                                com.azure.core.credential.KeyCredential keyCredential,
                                String deploymentName,
                                dev.langchain4j.model.Tokenizer tokenizer,
                                Double temperature,
                                Double topP,
                                Integer maxTokens,
                                Double presencePenalty,
                                Double frequencyPenalty,
                                Duration timeout,
                                Integer maxRetries,
                                com.azure.core.http.ProxyOptions proxyOptions,
                                boolean logRequestsAndResponses)

AzureOpenAiLanguageModel

public AzureOpenAiLanguageModel(String endpoint,
                                String serviceVersion,
                                com.azure.core.credential.TokenCredential tokenCredential,
                                String deploymentName,
                                dev.langchain4j.model.Tokenizer tokenizer,
                                Double temperature,
                                Double topP,
                                Integer maxTokens,
                                Double presencePenalty,
                                Double frequencyPenalty,
                                Duration timeout,
                                Integer maxRetries,
                                com.azure.core.http.ProxyOptions proxyOptions,
                                boolean logRequestsAndResponses)

Method Detail

generate

public dev.langchain4j.model.output.Response<String> generate(String prompt)

Specified by:

generate in interface dev.langchain4j.model.language.LanguageModel

estimateTokenCount

public int estimateTokenCount(String prompt)

Specified by:

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

builder

public static AzureOpenAiLanguageModel.Builder builder()