byte_pair_encoding.hpp

Go to the documentation of this file.

/*
 * SPDX-FileCopyrightText: Copyright (c) 2022-2026, NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: Apache-2.0
 */
#pragma once
 
#include <cudf/column/column.hpp>
#include <cudf/column/column_view.hpp>
#include <cudf/scalar/scalar.hpp>
#include <cudf/strings/strings_column_view.hpp>
#include <cudf/utilities/default_stream.hpp>
#include <cudf/utilities/export.hpp>
#include <cudf/utilities/memory_resource.hpp>
 
namespace CUDF_EXPORT nvtext {
 
struct bpe_merge_pairs {
  struct bpe_merge_pairs_impl;
 
  bpe_merge_pairs(std::unique_ptr<cudf::column>&& input,
                  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
                  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
  bpe_merge_pairs(cudf::strings_column_view const& input,
                  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
                  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
  ~bpe_merge_pairs();
  bpe_merge_pairs();
 
 private:
  friend bpe_merge_pairs_impl const* get_bpe_merge_pairs_impl(bpe_merge_pairs const&);
  bpe_merge_pairs_impl* impl{};  
};
 
std::unique_ptr<bpe_merge_pairs> load_merge_pairs(
  cudf::strings_column_view const& merge_pairs,
  rmm::cuda_stream_view stream      = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr = cudf::get_current_device_resource_ref());
 
std::unique_ptr<cudf::column> byte_pair_encoding(
  cudf::strings_column_view const& input,
  bpe_merge_pairs const& merges_pairs,
  cudf::string_scalar const& separator = cudf::string_scalar(" "),
  rmm::cuda_stream_view stream         = cudf::get_default_stream(),
  rmm::device_async_resource_ref mr    = cudf::get_current_device_resource_ref());
  // end of group
}  // namespace CUDF_EXPORT nvtext