Class OpenAiChatModel

java.lang.Object

dev.langchain4j.model.openai.OpenAiChatModel

All Implemented Interfaces:

ChatModel

public class OpenAiChatModel
extends Object
implements ChatModel

Represents an OpenAI language model with a chat completion interface, such as gpt-4o-mini and o3. You can find description of parameters here.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	OpenAiChatModel.OpenAiChatModelBuilder

Constructor Summary

Constructors

Constructor	Description
OpenAiChatModel(OpenAiChatModel.OpenAiChatModelBuilder builder)

Method Summary

Modifier and Type	Method	Description
static OpenAiChatModel.OpenAiChatModelBuilder	builder()
OpenAiChatRequestParameters	defaultRequestParameters()
ChatResponse	doChat(ChatRequest chatRequest)
CompletableFuture<ChatResponse>	doChatAsync(ChatRequest chatRequest)	SPI hook for a genuinely non-blocking chat implementation, invoked by ChatModel.chatAsync(ChatRequest).
List<ChatModelListener>	listeners()
ModelProvider	provider()
Set<Capability>	supportedCapabilities()

Methods inherited from class Object

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

Methods inherited from interface ChatModel

chat, chat, chat, chat, chat, chatAsync, chatAsync, chatAsync, chatAsync, chatAsync

Constructor Details

OpenAiChatModel

public OpenAiChatModel(OpenAiChatModel.OpenAiChatModelBuilder builder)

Method Details

defaultRequestParameters

public OpenAiChatRequestParameters defaultRequestParameters()

Specified by:

defaultRequestParameters in interface ChatModel

supportedCapabilities

public Set<Capability> supportedCapabilities()

Specified by:

supportedCapabilities in interface ChatModel

doChat

public ChatResponse doChat(ChatRequest chatRequest)

Specified by:

doChat in interface ChatModel

doChatAsync

public CompletableFuture<ChatResponse> doChatAsync(ChatRequest chatRequest)

Description copied from interface: ChatModel

SPI hook for a genuinely non-blocking chat implementation, invoked by ChatModel.chatAsync(ChatRequest).

The default returns a failed future carrying AsyncNotSupportedException to signal that this model has no native asynchronous implementation. Callers on the asynchronous and reactive path (for example the non-blocking RAG stages) detect this and either offload the blocking ChatModel.doChat(ChatRequest) or fail loudly with an actionable message. A model backed by remote HTTP I/O overrides this with a genuinely asynchronous call (no thread parked).

Specified by:

doChatAsync in interface ChatModel

Parameters:

chatRequest - a ChatRequest, containing all the inputs to the LLM

Returns:

a CompletableFuture of the ChatResponse

listeners

public List<ChatModelListener> listeners()

Specified by:

listeners in interface ChatModel

provider

public ModelProvider provider()

Specified by:

provider in interface ChatModel

builder

public static OpenAiChatModel.OpenAiChatModelBuilder builder()