Module: OpenAI::Models::Beta::ThreadCreateAndRunParams::Thread::ToolResources::FileSearch::VectorStore::ChunkingStrategy

Extended by:
Internal::Type::Union
Defined in:
lib/openai/models/beta/thread_create_and_run_params.rb,
sig/openai/models/beta/thread_create_and_run_params.rbs

Overview

The chunking strategy used to chunk the file(s). If not set, will use the auto strategy.

See Also:

  • OpenAI::Models::Beta::ThreadCreateAndRunParams::Thread::ToolResources::FileSearch::VectorStore#chunking_strategy

Defined Under Namespace

Classes: Auto, Static

Instance Method Summary collapse

Methods included from Internal::Type::Union

==, ===, coerce, derefed_variants, dump, hash, inspect, to_sorbet_type, variants, variants

Methods included from Internal::Util::SorbetRuntimeSupport

#const_missing, #define_sorbet_constant!, #sorbet_constant_defined?, #to_sorbet_type, to_sorbet_type

Methods included from Internal::Type::Converter

#coerce, coerce, #dump, dump, #inspect, inspect, meta_info, new_coerce_state, type_info

Instance Method Details

#initialize(type: :auto) ⇒ Object

The default strategy. This strategy currently uses a max_chunk_size_tokens of 800 and chunk_overlap_tokens of 400.

Parameters:

  • type (Symbol, :auto) (defaults to: :auto) —

    Always auto.




# File 'lib/openai/models/beta/thread_create_and_run_params.rb', line 534

#self?.variants ⇒ ::Array[OpenAI::Models::Beta::ThreadCreateAndRunParams::Thread::ToolResources::FileSearch::VectorStore::chunking_strategy]

Returns:

  • (::Array[OpenAI::Models::Beta::ThreadCreateAndRunParams::Thread::ToolResources::FileSearch::VectorStore::chunking_strategy]) 


404
 
# File 'sig/openai/models/beta/thread_create_and_run_params.rbs', line 404

def self?.variants: -> ::Array[OpenAI::Models::Beta::ThreadCreateAndRunParams::Thread::ToolResources::FileSearch::VectorStore::chunking_strategy]