Package dev.langchain4j.service

Class AiServiceTokenStream

java.lang.Object

dev.langchain4j.service.AiServiceTokenStream

All Implemented Interfaces:

TokenStream

public class AiServiceTokenStream
extends Object
implements TokenStream

Constructor Summary

Constructors

Constructor	Description
AiServiceTokenStream(List<ChatMessage> messages, List<ToolSpecification> toolSpecifications, Map<String,ToolExecutor> toolExecutors, List<Content> retrievedContents, AiServiceContext context, Object memoryId)

Method Summary

Modifier and Type	Method	Description
TokenStream	ignoreErrors()	All errors during streaming will be ignored (but will be logged with a WARN log level).
TokenStream	onComplete(Consumer<Response<AiMessage>> completionHandler)	The provided consumer will be invoked when a language model finishes streaming a response.
TokenStream	onError(Consumer<Throwable> errorHandler)	The provided consumer will be invoked when an error occurs during streaming.
TokenStream	onNext(Consumer<String> tokenHandler)	The provided consumer will be invoked every time a new token from a language model is available.
TokenStream	onRetrieved(Consumer<List<Content>> contentsHandler)	The provided consumer will be invoked if any Contents are retrieved using RetrievalAugmentor.
TokenStream	onToolExecuted(Consumer<ToolExecution> toolExecutionHandler)	The provided consumer will be invoked if any tool is executed.
void	start()	Completes the current token stream building and starts processing.

Methods inherited from class java.lang.Object

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

Constructor Details

AiServiceTokenStream

public AiServiceTokenStream(List<ChatMessage> messages,
 List<ToolSpecification> toolSpecifications,
 Map<String,ToolExecutor> toolExecutors,
 List<Content> retrievedContents,
 AiServiceContext context,
 Object memoryId)

Method Details

onNext

public TokenStream onNext(Consumer<String> tokenHandler)

Description copied from interface: TokenStream

The provided consumer will be invoked every time a new token from a language model is available.

Specified by:

onNext in interface TokenStream

Parameters:

tokenHandler - lambda that consumes tokens of the response

Returns:

token stream instance used to configure or start stream processing

onRetrieved

public TokenStream onRetrieved(Consumer<List<Content>> contentsHandler)

Description copied from interface: TokenStream

The provided consumer will be invoked if any Contents are retrieved using RetrievalAugmentor.

The invocation happens before any call is made to the language model.

Specified by:

onRetrieved in interface TokenStream

Parameters:

contentsHandler - lambda that consumes all retrieved contents

Returns:

token stream instance used to configure or start stream processing

onToolExecuted

public TokenStream onToolExecuted(Consumer<ToolExecution> toolExecutionHandler)

Description copied from interface: TokenStream

The provided consumer will be invoked if any tool is executed.

The invocation happens after the tool method has finished and before any other tool is executed.

Specified by:

onToolExecuted in interface TokenStream

Parameters:

toolExecutionHandler - lambda that consumes ToolExecution

Returns:

token stream instance used to configure or start stream processing

onComplete

public TokenStream onComplete(Consumer<Response<AiMessage>> completionHandler)

Description copied from interface: TokenStream

The provided consumer will be invoked when a language model finishes streaming a response.

Specified by:

onComplete in interface TokenStream

Parameters:

completionHandler - lambda that will be invoked when language model finishes streaming

Returns:

token stream instance used to configure or start stream processing

onError

public TokenStream onError(Consumer<Throwable> errorHandler)

Description copied from interface: TokenStream

The provided consumer will be invoked when an error occurs during streaming.

Specified by:

onError in interface TokenStream

Parameters:

errorHandler - lambda that will be invoked when an error occurs

Returns:

token stream instance used to configure or start stream processing

ignoreErrors

public TokenStream ignoreErrors()

Description copied from interface: TokenStream

All errors during streaming will be ignored (but will be logged with a WARN log level).

Specified by:

ignoreErrors in interface TokenStream

Returns:

token stream instance used to configure or start stream processing

start

public void start()

Description copied from interface: TokenStream

Completes the current token stream building and starts processing.

Will send a request to LLM and start response streaming.

Specified by:

start in interface TokenStream