Class OpenAiStreamingChatModel

java.lang.Object

dev.langchain4j.model.openai.OpenAiStreamingChatModel

All Implemented Interfaces:

StreamingChatModel

public class OpenAiStreamingChatModel
extends Object
implements StreamingChatModel

Represents an OpenAI language model with a chat completion interface, such as gpt-4o-mini and o3. The model's response is streamed token by token and should be handled with StreamingResponseHandler. You can find description of parameters here.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	OpenAiStreamingChatModel.OpenAiStreamingChatModelBuilder

Constructor Summary

Constructors

Constructor	Description
OpenAiStreamingChatModel(OpenAiStreamingChatModel.OpenAiStreamingChatModelBuilder builder)

Method Summary

Modifier and Type	Method	Description
static OpenAiStreamingChatModel.OpenAiStreamingChatModelBuilder	builder()
OpenAiChatRequestParameters	defaultRequestParameters()
Flow.Publisher<ChatModelStreamingEvent>	doChat(ChatRequest chatRequest)	Provider-specific implementation of the reactive stream returned by StreamingChatModel.chat(ChatRequest) (which wraps it with ChatModelListener invocation).
void	doChat(ChatRequest chatRequest, StreamingChatResponseHandler handler)
List<ChatModelListener>	listeners()
ModelProvider	provider()

Methods inherited from class Object

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

Methods inherited from interface StreamingChatModel

chat, chat, chat, chat, chat, chat, chat, chat, supportedCapabilities

Constructor Details

OpenAiStreamingChatModel

public OpenAiStreamingChatModel(OpenAiStreamingChatModel.OpenAiStreamingChatModelBuilder builder)

Method Details

defaultRequestParameters

public OpenAiChatRequestParameters defaultRequestParameters()

Specified by:

defaultRequestParameters in interface StreamingChatModel

doChat

public void doChat(ChatRequest chatRequest,
 StreamingChatResponseHandler handler)

Specified by:

doChat in interface StreamingChatModel

doChat

public Flow.Publisher<ChatModelStreamingEvent> doChat(ChatRequest chatRequest)

Description copied from interface: StreamingChatModel

Provider-specific implementation of the reactive stream returned by StreamingChatModel.chat(ChatRequest) (which wraps it with ChatModelListener invocation). Implementations must honor the event ordering and the demand / back-pressure expectations documented on StreamingChatModel.chat(ChatRequest) — in particular, they typically consume the response eagerly and relay ChatModelStreamingEvents through a bounded buffer rather than propagating subscriber demand to the model.

The default implementation returns an immediately-failing Publisher carrying AsyncNotSupportedException to signal that this model has no native reactive-streaming implementation; a provider that does not support reactive streaming leaves it unimplemented (consistent with ChatModel#doChatAsync and the other async defaults).

Specified by:

doChat in interface StreamingChatModel

listeners

public List<ChatModelListener> listeners()

Specified by:

listeners in interface StreamingChatModel

provider

public ModelProvider provider()

Specified by:

provider in interface StreamingChatModel

builder

public static OpenAiStreamingChatModel.OpenAiStreamingChatModelBuilder builder()