Merge branch 'main' into josephine/migrate-codeowners

Author: josephine-wolf-oberholtzer

.github/workflows/pr.yaml

@@ -160,6 +160,10 @@ jobs:
           - '!.github/workflows/trigger-breaking-change-alert.yaml'
           - '!.pre-commit-config.yaml'
           - '!.shellcheckrc'
+          - '!CODEOWNERS'
+          - '!Dockerfile'
+          - '!README.md'
+          - '!SECURITY.md'
           - '!ci/build_docs.sh'
           - '!ci/build_go.sh'
           - '!ci/build_python.sh'
@@ -171,14 +175,19 @@ jobs:
           - '!ci/test_python.sh'
           - '!ci/test_wheel_cuvs.sh'
           - '!ci/validate_wheel.sh'
-          - '!Dockerfile'
+          - '!conda/environments/**'
+          - '!conda/recipes/cuvs/**'
+          - '!conda/recipes/cuvs-bench/**'
+          - '!conda/recipes/cuvs-bench-cpu/**'
           - '!docs/**'
+          - '!examples/**'
           - '!fern/**'
+          - '!go/**'
           - '!img/**'
           - '!notebooks/**'
+          - '!pyproject.toml'
           - '!python/**'
           - '!rust/**'
-          - '!go/**'
           - '!thirdparty/LICENSES/**'
         test_python_conda:
           - '**'
@@ -192,8 +201,12 @@ jobs:
           - '!.github/labeler.yml'
           - '!.github/ops-bot.yaml'
           - '!.github/release.yml'
+          - '!.github/workflows/check-c-abi.yaml'
+          - '!.github/workflows/labeler.yml'
           - '!.github/workflows/publish-rust.yaml'
+          - '!.github/workflows/store-c-abi-baseline.yaml'
           - '!.github/workflows/trigger-breaking-change-alert.yaml'
+          - '!.github/workflows/update-c-abi-baseline.yaml'
           - '!.pre-commit-config.yaml'
           - '!.shellcheckrc'
           - '!ci/build_go.sh'
@@ -210,6 +223,7 @@ jobs:
           - '!cpp/.clang-format'
           - '!cpp/.clang-tidy'
           - '!cpp/doxygen/**'
+          - '!CODEOWNERS'
           - '!Dockerfile'
           - '!README.md'
           - '!SECURITY.md'
@@ -252,6 +266,7 @@ jobs:
           - '!ci/test_python.sh'
           - '!ci/test_standalone_c.sh'
           - '!ci/validate_wheel.sh'
+          - '!CODEOWNERS'
           - '!Dockerfile'
           - '!README.md'
           - '!SECURITY.md'
@@ -283,6 +298,7 @@ jobs:
           - '!.github/workflows/trigger-breaking-change-alert.yaml'
           - '!.pre-commit-config.yaml'
           - '!.shellcheckrc'
+          - '!CODEOWNERS'
           - '!Dockerfile'
           - '!README.md'
           - '!SECURITY.md'
@@ -324,6 +340,7 @@ jobs:
           - '!.github/workflows/trigger-breaking-change-alert.yaml'
           - '!.pre-commit-config.yaml'
           - '!.shellcheckrc'
+          - '!CODEOWNERS'
           - '!Dockerfile'
           - '!README.md'
           - '!SECURITY.md'

.pre-commit-config.yaml

@@ -3,12 +3,13 @@
 
 repos:
       - repo: https://github.com/pre-commit/pre-commit-hooks
-        rev: v5.0.0
+        rev: v6.0.0
         hooks:
               - id: check-json
               - id: trailing-whitespace
               - id: end-of-file-fixer
               - id: check-symlinks
+              - id: check-xml
       - repo: https://github.com/PyCQA/isort
         rev: 5.12.0
         hooks:

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/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>
 
@@ -773,7 +774,7 @@ struct CUVS_EXPORT 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());
@@ -808,7 +809,7 @@ struct CUVS_EXPORT 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());
 
@@ -849,7 +850,7 @@ struct CUVS_EXPORT 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>
@@ -189,12 +190,12 @@ 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();