dev.langchain4j.model.azure

Class AzureOpenAiStreamingChatModel

java.lang.Object

dev.langchain4j.model.azure.AzureOpenAiStreamingChatModel

All Implemented Interfaces:

dev.langchain4j.model.chat.StreamingChatLanguageModel, dev.langchain4j.model.chat.TokenCountEstimator

public class AzureOpenAiStreamingChatModel
extends Object
implements dev.langchain4j.model.chat.StreamingChatLanguageModel, dev.langchain4j.model.chat.TokenCountEstimator

Represents an OpenAI language model, hosted on Azure, that has a chat completion interface, such as gpt-3.5-turbo. The model's response is streamed token by token and should be handled with StreamingResponseHandler.

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	AzureOpenAiStreamingChatModel.Builder

Constructor Summary

Constructors

Constructor and Description
AzureOpenAiStreamingChatModel(com.azure.ai.openai.OpenAIClient client, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, List<String> stop, Double presencePenalty, Double frequencyPenalty)
AzureOpenAiStreamingChatModel(String endpoint, String serviceVersion, com.azure.core.credential.KeyCredential keyCredential, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, List<String> stop, Double presencePenalty, Double frequencyPenalty, Duration timeout, Integer maxRetries, com.azure.core.http.ProxyOptions proxyOptions, boolean logRequestsAndResponses)
AzureOpenAiStreamingChatModel(String endpoint, String serviceVersion, String apiKey, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, List<String> stop, Double presencePenalty, Double frequencyPenalty, Duration timeout, Integer maxRetries, com.azure.core.http.ProxyOptions proxyOptions, boolean logRequestsAndResponses)
AzureOpenAiStreamingChatModel(String endpoint, String serviceVersion, com.azure.core.credential.TokenCredential tokenCredential, String deploymentName, dev.langchain4j.model.Tokenizer tokenizer, Double temperature, Double topP, Integer maxTokens, List<String> stop, 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 AzureOpenAiStreamingChatModel.Builder	builder()
int	estimateTokenCount(List<dev.langchain4j.data.message.ChatMessage> messages)
void	generate(List<dev.langchain4j.data.message.ChatMessage> messages, List<dev.langchain4j.agent.tool.ToolSpecification> toolSpecifications, dev.langchain4j.model.StreamingResponseHandler<dev.langchain4j.data.message.AiMessage> handler)
void	generate(List<dev.langchain4j.data.message.ChatMessage> messages, dev.langchain4j.model.StreamingResponseHandler<dev.langchain4j.data.message.AiMessage> handler)
void	generate(List<dev.langchain4j.data.message.ChatMessage> messages, dev.langchain4j.agent.tool.ToolSpecification toolSpecification, dev.langchain4j.model.StreamingResponseHandler<dev.langchain4j.data.message.AiMessage> handler)

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.chat.StreamingChatLanguageModel

generate

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

estimateTokenCount, estimateTokenCount, estimateTokenCount, estimateTokenCount

Constructor Detail

AzureOpenAiStreamingChatModel

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

AzureOpenAiStreamingChatModel

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

AzureOpenAiStreamingChatModel

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

AzureOpenAiStreamingChatModel

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

Method Detail

generate

public void generate(List<dev.langchain4j.data.message.ChatMessage> messages,
                     dev.langchain4j.model.StreamingResponseHandler<dev.langchain4j.data.message.AiMessage> handler)

Specified by:

generate in interface dev.langchain4j.model.chat.StreamingChatLanguageModel

generate

public void generate(List<dev.langchain4j.data.message.ChatMessage> messages,
                     List<dev.langchain4j.agent.tool.ToolSpecification> toolSpecifications,
                     dev.langchain4j.model.StreamingResponseHandler<dev.langchain4j.data.message.AiMessage> handler)

Specified by:

generate in interface dev.langchain4j.model.chat.StreamingChatLanguageModel

generate

public void generate(List<dev.langchain4j.data.message.ChatMessage> messages,
                     dev.langchain4j.agent.tool.ToolSpecification toolSpecification,
                     dev.langchain4j.model.StreamingResponseHandler<dev.langchain4j.data.message.AiMessage> handler)

Specified by:

generate in interface dev.langchain4j.model.chat.StreamingChatLanguageModel

estimateTokenCount

public int estimateTokenCount(List<dev.langchain4j.data.message.ChatMessage> messages)

Specified by:

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

builder

public static AzureOpenAiStreamingChatModel.Builder builder()