Switch to public RAFT numpy_serialize APIs

c/src/neighbors/brute_force.cpp

@@ -1,6 +1,6 @@
 
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -10,6 +10,7 @@
 
 #include <raft/core/error.hpp>
 #include <raft/core/mdspan_types.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/resources.hpp>
 #include <raft/core/serialize.hpp>
 
@@ -238,9 +239,13 @@ extern "C" cuvsError_t cuvsBruteForceDeserialize(cuvsResources_t res,
     // read the numpy dtype from the beginning of the file
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
+    is.close();
 
     index->dtype.bits = dtype.itemsize * 8;
     if (dtype.kind == 'f' && dtype.itemsize == 4) {

c/src/neighbors/cagra.cpp

@@ -9,6 +9,7 @@
 
 #include <raft/core/error.hpp>
 #include <raft/core/mdspan_types.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/resources.hpp>
 #include <raft/core/serialize.hpp>
 
@@ -873,9 +874,13 @@ extern "C" cuvsError_t cuvsCagraDeserialize(cuvsResources_t res,
     // read the numpy dtype from the beginning of the file
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
+    is.close();
 
     index->dtype.bits = dtype.itemsize * 8;
     if (dtype.kind == 'f' && dtype.itemsize == 4) {

c/src/neighbors/ivf_flat.cpp

@@ -1,6 +1,6 @@
 
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2024-2025, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -9,6 +9,7 @@
 
 #include <raft/core/error.hpp>
 #include <raft/core/mdspan_types.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/resources.hpp>
 #include <raft/core/serialize.hpp>
 #include <raft/util/cudart_utils.hpp>
@@ -299,9 +300,13 @@ extern "C" cuvsError_t cuvsIvfFlatDeserialize(cuvsResources_t res,
     // read the numpy dtype from the beginning of the file
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
+    is.close();
 
     index->dtype.bits = dtype.itemsize * 8;
     if (dtype.kind == 'f' && dtype.itemsize == 4) {

c/src/neighbors/mg_cagra.cpp

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -10,6 +10,7 @@
 #include <cuvs/neighbors/common.hpp>
 #include <dlpack/dlpack.h>
 #include <raft/core/error.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/serialize.hpp>
 
 #include "../core/exceptions.hpp"
@@ -399,9 +400,12 @@ extern "C" cuvsError_t cuvsMultiGpuCagraDeserialize(cuvsResources_t res,
   return cuvs::core::translate_exceptions([=] {
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
     is.close();
 
     index->dtype.bits = dtype.itemsize * 8;
@@ -430,9 +434,12 @@ extern "C" cuvsError_t cuvsMultiGpuCagraDistribute(cuvsResources_t res,
   return cuvs::core::translate_exceptions([=] {
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
     is.close();
 
     index->dtype.bits = dtype.itemsize * 8;

c/src/neighbors/mg_ivf_flat.cpp

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -10,6 +10,7 @@
 #include <cuvs/neighbors/ivf_flat.hpp>
 #include <dlpack/dlpack.h>
 #include <raft/core/error.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/serialize.hpp>
 
 #include "../core/exceptions.hpp"
@@ -396,9 +397,12 @@ extern "C" cuvsError_t cuvsMultiGpuIvfFlatDeserialize(cuvsResources_t res,
   return cuvs::core::translate_exceptions([=] {
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
     is.close();
 
     index->dtype.bits = dtype.itemsize * 8;
@@ -427,9 +431,12 @@ extern "C" cuvsError_t cuvsMultiGpuIvfFlatDistribute(cuvsResources_t res,
   return cuvs::core::translate_exceptions([=] {
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
     is.close();
 
     index->dtype.bits = dtype.itemsize * 8;

c/src/neighbors/mg_ivf_pq.cpp

@@ -1,5 +1,5 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2025, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2025-2026, NVIDIA CORPORATION.
  * SPDX-License-Identifier: Apache-2.0
  */
 
@@ -10,6 +10,7 @@
 #include <cuvs/neighbors/ivf_pq.hpp>
 #include <dlpack/dlpack.h>
 #include <raft/core/error.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/serialize.hpp>
 
 #include "../core/exceptions.hpp"
@@ -388,9 +389,12 @@ extern "C" cuvsError_t cuvsMultiGpuIvfPqDeserialize(cuvsResources_t res,
   return cuvs::core::translate_exceptions([=] {
     std::ifstream is(filename, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", filename); }
-    char dtype_string[4];
-    is.read(dtype_string, 4);
-    auto dtype = raft::detail::numpy_serializer::parse_descr(std::string(dtype_string, 4));
+    char dtype_string[4]{};
+    if (!is.read(dtype_string, sizeof(dtype_string))) {
+      RAFT_FAIL("Invalid or truncated index header in file %s", filename);
+    }
+    auto dtype =
+      raft::numpy_serializer::parse_descr(std::string(dtype_string, sizeof(dtype_string)));
     is.close();
 
     index->dtype.bits = dtype.itemsize * 8;

cpp/cmake/thirdparty/get_raft.cmake

@@ -1,13 +1,13 @@
 # =============================================================================
 # cmake-format: off
-# SPDX-FileCopyrightText: Copyright (c) 2023-2025, NVIDIA CORPORATION.
+# SPDX-FileCopyrightText: Copyright (c) 2023-2026, NVIDIA CORPORATION.
 # SPDX-License-Identifier: Apache-2.0
 # cmake-format: on
 
 # Use RAPIDS_VERSION_MAJOR_MINOR from rapids_config.cmake
 set(RAFT_VERSION "${RAPIDS_VERSION_MAJOR_MINOR}")
-set(RAFT_FORK "rapidsai")
-set(RAFT_PINNED_TAG "${rapids-cmake-checkout-tag}")
+set(RAFT_FORK "julianmi")
+set(RAFT_PINNED_TAG "expose-public-npy-helpers")
 
 function(find_and_configure_raft)
     set(oneValueArgs VERSION FORK PINNED_TAG BUILD_STATIC_DEPS ENABLE_NVTX ENABLE_MNMG_DEPENDENCIES CLONE_ON_PIN)

cpp/include/cuvs/neighbors/cagra.hpp

@@ -16,6 +16,7 @@
 #include <raft/core/host_mdspan.hpp>
 #include <raft/core/mdspan.hpp>
 #include <raft/core/mdspan_types.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/resource/stream_view.hpp>
 #include <raft/core/serialize.hpp>
 
@@ -764,7 +765,7 @@ struct index : cuvs::neighbors::index {
     if (lseek(fd.get(), 0, SEEK_SET) == -1) {
       RAFT_FAIL("Failed to seek to beginning of dataset file");
     }
-    auto header = raft::detail::numpy_serializer::read_header(stream);
+    auto header = raft::numpy_serializer::read_header(stream);
     RAFT_EXPECTS(header.shape.size() == 2,
                  "Dataset file should be 2D, got %zu dimensions",
                  header.shape.size());
@@ -799,7 +800,7 @@ struct index : cuvs::neighbors::index {
     if (lseek(fd.get(), 0, SEEK_SET) == -1) {
       RAFT_FAIL("Failed to seek to beginning of graph file");
     }
-    auto header = raft::detail::numpy_serializer::read_header(stream);
+    auto header = raft::numpy_serializer::read_header(stream);
     RAFT_EXPECTS(
       header.shape.size() == 2, "Graph file should be 2D, got %zu dimensions", header.shape.size());
 
@@ -840,7 +841,7 @@ struct index : cuvs::neighbors::index {
     if (lseek(fd.get(), 0, SEEK_SET) == -1) {
       RAFT_FAIL("Failed to seek to beginning of mapping file");
     }
-    auto header = raft::detail::numpy_serializer::read_header(stream);
+    auto header = raft::numpy_serializer::read_header(stream);
     RAFT_EXPECTS(header.shape.size() == 1,
                  "Mapping file should be 1D, got %zu dimensions",
                  header.shape.size());

cpp/include/cuvs/util/file_io.hpp

@@ -5,6 +5,7 @@
 #pragma once
 
 #include <raft/core/error.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/serialize.hpp>
 
 #include <algorithm>
@@ -187,12 +188,12 @@ std::pair<file_descriptor, size_t> create_numpy_file(const std::string& path,
   file_descriptor fd(path, O_CREAT | O_RDWR | O_TRUNC, 0644);
 
   // Build header
-  const auto dtype         = raft::detail::numpy_serializer::get_numpy_dtype<T>();
-  const bool fortran_order = false;
-  const raft::detail::numpy_serializer::header_t header = {dtype, fortran_order, shape};
+  const auto dtype                              = raft::numpy_serializer::get_numpy_dtype<T>();
+  const bool fortran_order                      = false;
+  const raft::numpy_serializer::header_t header = {dtype, fortran_order, shape};
 
   std::stringstream ss;
-  raft::detail::numpy_serializer::write_header(ss, header);
+  raft::numpy_serializer::write_header(ss, header);
   std::string header_str = ss.str();
   size_t header_size     = header_str.size();
 

cpp/src/neighbors/brute_force_serialize.cu

@@ -1,11 +1,12 @@
 /*
- * SPDX-FileCopyrightText: Copyright (c) 2024, NVIDIA CORPORATION.
+ * SPDX-FileCopyrightText: Copyright (c) 2024-2026, NVIDIA CORPORATION.
  * SPDX-License-Identifier: Apache-2.0
  */
 
 #include <cuvs/neighbors/brute_force.hpp>
 #include <raft/core/copy.cuh>
 #include <raft/core/host_mdarray.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/resources.hpp>
 #include <raft/core/serialize.hpp>
 
@@ -24,7 +25,7 @@ void serialize(raft::resources const& handle,
   RAFT_LOG_DEBUG(
     "Saving brute force index, size %zu, dim %u", static_cast<size_t>(index.size()), index.dim());
 
-  auto dtype_string = raft::detail::numpy_serializer::get_numpy_dtype<T>().to_string();
+  auto dtype_string = raft::numpy_serializer::get_numpy_dtype<T>().to_string();
   dtype_string.resize(4);
   os << dtype_string;
 

cpp/src/neighbors/detail/cagra/cagra_build.cuh

@@ -16,6 +16,7 @@
 #include <raft/core/host_mdarray.hpp>
 #include <raft/core/host_mdspan.hpp>
 #include <raft/core/logger.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/resource/cuda_stream.hpp>
 #include <raft/util/integer_utils.hpp>
 
@@ -726,14 +727,14 @@ void ace_load_partition_dataset_from_disk(
     std::ifstream is(reordered_dataset_path, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", reordered_dataset_path.c_str()); }
     auto start_pos = is.tellg();
-    raft::detail::numpy_serializer::read_header(is);
+    raft::numpy_serializer::read_header(is);
     core_header_size = static_cast<size_t>(is.tellg() - start_pos);
   }
   {
     std::ifstream is(augmented_dataset_path, std::ios::in | std::ios::binary);
     if (!is) { RAFT_FAIL("Cannot open file %s", augmented_dataset_path.c_str()); }
     auto start_pos = is.tellg();
-    raft::detail::numpy_serializer::read_header(is);
+    raft::numpy_serializer::read_header(is);
     augmented_header_size = static_cast<size_t>(is.tellg() - start_pos);
   }
 

cpp/src/neighbors/detail/cagra/cagra_serialize.cuh

@@ -11,6 +11,7 @@
 #include <raft/core/logger.hpp>
 #include <raft/core/mdarray.hpp>
 #include <raft/core/mdspan_types.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/resource/cuda_stream.hpp>
 #include <raft/core/serialize.hpp>
 #include <raft/util/cudart_utils.hpp>
@@ -54,7 +55,7 @@ void serialize(raft::resources const& res,
   RAFT_LOG_DEBUG(
     "Saving CAGRA index, size %zu, dim %u", static_cast<size_t>(index_.size()), index_.dim());
 
-  std::string dtype_string = raft::detail::numpy_serializer::get_numpy_dtype<T>().to_string();
+  std::string dtype_string = raft::numpy_serializer::get_numpy_dtype<T>().to_string();
   dtype_string.resize(4);
   os << dtype_string;
 

cpp/src/neighbors/detail/hnsw.hpp

@@ -14,9 +14,9 @@
 #include <cuvs/util/file_io.hpp>
 
 #include <raft/core/copy.cuh>
-#include <raft/core/detail/mdspan_numpy_serializer.hpp>
 #include <raft/core/host_mdspan.hpp>
 #include <raft/core/logger.hpp>
+#include <raft/core/numpy_serializer.hpp>
 #include <raft/core/pinned_mdarray.hpp>
 #include <raft/util/cudart_utils.hpp>
 
@@ -399,7 +399,7 @@ void serialize_to_hnswlib_from_disk(raft::resources const& res,
     std::ifstream graph_stream(graph_path, std::ios::binary);
     RAFT_EXPECTS(graph_stream.good(), "Failed to open graph file: %s", graph_path.c_str());
 
-    auto header       = raft::detail::numpy_serializer::read_header(graph_stream);
+    auto header       = raft::numpy_serializer::read_header(graph_stream);
     graph_header_size = static_cast<size_t>(graph_stream.tellg());
     RAFT_EXPECTS(
       header.shape.size() == 2, "Graph file should be 2D, got %zu dimensions", header.shape.size());
@@ -419,7 +419,7 @@ void serialize_to_hnswlib_from_disk(raft::resources const& res,
     std::ifstream dataset_stream(dataset_path, std::ios::binary);
     RAFT_EXPECTS(dataset_stream.good(), "Failed to open dataset file: %s", dataset_path.c_str());
 
-    auto header         = raft::detail::numpy_serializer::read_header(dataset_stream);
+    auto header         = raft::numpy_serializer::read_header(dataset_stream);
     dataset_header_size = static_cast<size_t>(dataset_stream.tellg());
     RAFT_EXPECTS(header.shape.size() == 2,
                  "Dataset file should be 2D, got %zu dimensions",
@@ -439,7 +439,7 @@ void serialize_to_hnswlib_from_disk(raft::resources const& res,
     std::ifstream mapping_stream(mapping_path, std::ios::binary);
     RAFT_EXPECTS(mapping_stream.good(), "Failed to open mapping file: %s", mapping_path.c_str());
 
-    auto header       = raft::detail::numpy_serializer::read_header(mapping_stream);
+    auto header       = raft::numpy_serializer::read_header(mapping_stream);
     label_header_size = static_cast<size_t>(mapping_stream.tellg());
     RAFT_EXPECTS(header.shape.size() == 1,
                  "Mapping file should be 1D, got %zu dimensions",