Package de.espirit.firstspirit.ai

Interface GenerativeAIFunctionRequest.EvaluatedResponseStream

All Superinterfaces:

AutoCloseable, Closeable, GenerativeAIFunctionRequest.EvaluatedResponse, Iterator<Response>, ResponseStream

Enclosing interface:

GenerativeAIFunctionRequest

public static interface GenerativeAIFunctionRequest.EvaluatedResponseStream
extends GenerativeAIFunctionRequest.EvaluatedResponse, ResponseStream

Evaluated response stream of the generative AI, potentially containing function call requests.

Since:

5.2.250908

Method Summary

Modifier and Type	Method	Description
@NotNull Response	getResponse()	The response object returned by the generative AI.
@NotNull Optional<TokenUsage>	getTokenUsage()	Returns information about the combined token usage for the current function calling chain.

Methods inherited from interface java.io.Closeable

close

Methods inherited from interface de.espirit.firstspirit.ai.GenerativeAIFunctionRequest.EvaluatedResponse

createRequest, getFunctionCallHandles

Methods inherited from interface java.util.Iterator

forEachRemaining, hasNext, next, remove

Methods inherited from interface de.espirit.firstspirit.ai.dto.ResponseStream

stream

Method Details

getResponse

@NotNull
@NotNull Response getResponse()

The response object returned by the generative AI.

NOTE: To retrieve a combined token usage of all preceding requests use GenerativeAIFunctionRequest.EvaluatedResponse.getTokenUsage() instead of retrieving it from the returned response using Response.getTokenUsage().

This method will preload all chunks from the stream without consuming them in order to return an accumulated response.

Specified by:

getResponse in interface GenerativeAIFunctionRequest.EvaluatedResponse

Returns:

The response object.

getTokenUsage

@NotNull
@NotNull Optional<TokenUsage> getTokenUsage()

Returns information about the combined token usage for the current function calling chain. This method will preload all chunks from the stream without consuming them in order to calculate the total token usages.

Specified by:

getTokenUsage in interface GenerativeAIFunctionRequest.EvaluatedResponse

Returns:

The combined token usage information, if available.