Package ai.extend.types

Class ArrayStrategy.Builder

java.lang.Object

ai.extend.types.ArrayStrategy.Builder

All Implemented Interfaces:

ArrayStrategy._FinalStage, ArrayStrategy.TypeStage

Enclosing class:

ArrayStrategy

public static final class ArrayStrategy.Builder
extends java.lang.Object
implements ArrayStrategy.TypeStage, ArrayStrategy._FinalStage

Method Summary

Modifier and Type	Method	Description
ArrayStrategy	build()
ArrayStrategy.Builder	from(ArrayStrategy other)
ArrayStrategy._FinalStage	type(ArrayStrategyType type)	The strategy type for handling large array use cases.

Methods inherited from class java.lang.Object

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

Method Detail

from

public ArrayStrategy.Builder from(ArrayStrategy other)

Specified by:

from in interface ArrayStrategy.TypeStage

type

public ArrayStrategy._FinalStage type(@NotNull
                                      ArrayStrategyType type)

The strategy type for handling large array use cases. For most use cases this should be left null, or should be set to large_array_heuristics. If you're unsure of what your use case needs, reach out to the Extend team for help.

• large_array_heuristics: Optimized for documents with very large arrays, but where latency matters.

  This strategy uses specialized heuristics around chunking, tables, and merging to handle large arrays efficiently over large documents.

• large_array_max_context: Optimizes for accuracy over latency in documents with very large arrays.

  This strategy will do multiple passes through the entire document to ensure there is no context loss across any chunks/pages, maximizing accuracy for complex array extraction, but adding material latency. This strategy incurs additional extraction credits when enabled.

• large_array_overlap_context: Balances accuracy and latency in documents with very large arrays.

  This strategy will always maintain surrounding/overlapping page context for every chunk/page that is extracted, eliminating array failure modes from context loss across page boundaries.

The strategy type for handling large array use cases. For most use cases this should be left null, or should be set to large_array_heuristics. If you're unsure of what your use case needs, reach out to the Extend team for help.

• large_array_heuristics: Optimized for documents with very large arrays, but where latency matters.

  This strategy uses specialized heuristics around chunking, tables, and merging to handle large arrays efficiently over large documents.

• large_array_max_context: Optimizes for accuracy over latency in documents with very large arrays.

  This strategy will do multiple passes through the entire document to ensure there is no context loss across any chunks/pages, maximizing accuracy for complex array extraction, but adding material latency. This strategy incurs additional extraction credits when enabled.

• large_array_overlap_context: Balances accuracy and latency in documents with very large arrays.

  This strategy will always maintain surrounding/overlapping page context for every chunk/page that is extracted, eliminating array failure modes from context loss across page boundaries.

Specified by:

type in interface ArrayStrategy.TypeStage

Returns:

Reference to this so that method calls can be chained together.

build

public ArrayStrategy build()

Specified by:

build in interface ArrayStrategy._FinalStage