Package dev.langchain4j.adaptiverag

Class RetrievalGrader

java.lang.Object

dev.langchain4j.adaptiverag.RetrievalGrader

All Implemented Interfaces:

Function<RetrievalGrader.Arguments,RetrievalGrader.Score>

public class RetrievalGrader
extends Object
implements Function<RetrievalGrader.Arguments,RetrievalGrader.Score>

The RetrievalGrader class implements a function to assess the relevance of a retrieved document to a user's question. It uses an AI service to generate a binary score ('yes' or 'no') indicating relevance. This class relies on external services for processing and grading documents, making it dependent on network availability and the stability of the used API.

Nested Class Summary

Nested Classes

Modifier and Type	Class	Description
static class	RetrievalGrader.Arguments	Represents a structure for holding the arguments needed to process a user's query.
static class	RetrievalGrader.Score	A static class that represents a score in a binary format.

Constructor Summary

Constructors

Constructor	Description
RetrievalGrader()

Method Summary

Modifier and Type	Method	Description
RetrievalGrader.Score	apply(RetrievalGrader.Arguments args)	Applies the provided arguments to generate a score using a chat language model.

Methods inherited from class java.lang.Object

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

Methods inherited from interface java.util.function.Function

andThen, compose

Constructor Details

RetrievalGrader

public RetrievalGrader()

Method Details

apply

public RetrievalGrader.Score apply(RetrievalGrader.Arguments args)

Applies the provided arguments to generate a score using a chat language model.

Specified by:

apply in interface Function<RetrievalGrader.Arguments,RetrievalGrader.Score>

Parameters:

args - The arguments containing the necessary information for processing.

Returns:

A RetrievalGrader.Score object representing the result of the processing.