usearch 2.8.3 → 2.8.5

package/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "usearch"
-version = "2.8.3"
+version = "2.8.5"
 authors = ["Ash Vardanian <1983160+ashvardanian@users.noreply.github.com>"]
 description = "Smaller & Faster Single-File Vector Search Engine from Unum"
 edition = "2021"

package/README.md

@@ -1,7 +1,7 @@
 <h1 align="center">USearch</h1>
 <h3 align="center">
-Faster & Smaller Single-File<br/>
-Search Engine for Vectors & Texts<br/>
+Smaller & <a href="https://www.unum.cloud/blog/2023-11-11-scaling-vector-search">Faster</a> Single-File<br/>
+Similarity Search Engine for <a href="https://github.com/ashvardanian/simsimd">Vectors</a> & 🔜 <a href="https://github.com/ashvardanian/stringzilla">Texts</a>
 </h3>
 <br/>
 
@@ -18,7 +18,7 @@ Search Engine for Vectors & Texts<br/>
 </p>
 
 <p align="center">
-Euclidean • Angular • Bitwise • Haversine • User-Defined Metrics
+Spatial • Binary • Probabilistic • User-Defined Metrics
 <br/>
 <a href="https://unum-cloud.github.io/usearch/cpp">C++ 11</a> •
 <a href="https://unum-cloud.github.io/usearch/python">Python 3</a> •
@@ -32,54 +32,72 @@ Euclidean • Angular • Bitwise • Haversine • User-Defined Metrics
 <a href="https://unum-cloud.github.io/usearch/golang">GoLang</a> •
 <a href="https://unum-cloud.github.io/usearch/wolfram">Wolfram</a>
 <br/>
-Linux • MacOS • Windows • iOS • Docker • WebAssembly
+Linux • MacOS • Windows • iOS • WebAssembly
 </p>
 
 <div align="center">
-<a href="https://pypi.org/project/usearch/"> <img alt="PyPI - Downloads" src="https://img.shields.io/pypi/dm/usearch?label=pypi%20downloads"> </a>
-<a href="https://www.npmjs.com/package/usearch"> <img alt="npm" src="https://img.shields.io/npm/dy/usearch?label=npm%20dowloads"> </a>
-<a href="https://crates.io/crates/usearch"> <img alt="Crates.io" src="https://img.shields.io/crates/d/usearch?label=crate%20downloads"> </a>
-<a href="https://www.nuget.org/packages/Cloud.Unum.USearch"> <img alt="Nuget" src="https://img.shields.io/nuget/dt/Cloud.Unum.USearch?label=NuGet"> </a>
-<a href="https://hub.docker.com/r/unum/usearch"> <img alt="Docker Pulls" src="https://img.shields.io/docker/pulls/unum/usearch?label=Docker"> </a>
-<img alt="GitHub code size in bytes" src="https://img.shields.io/github/languages/code-size/unum-cloud/usearch">
+<a href="https://pypi.org/project/usearch/"> <img alt="PyPI" src="https://img.shields.io/pypi/dm/usearch?label=PyPi%20pulls"> </a>
+<a href="https://www.npmjs.com/package/usearch"> <img alt="NPM" src="https://img.shields.io/npm/dy/usearch?label=NPM%20pulls"> </a>
+<a href="https://crates.io/crates/usearch"> <img alt="Crate" src="https://img.shields.io/crates/d/usearch?label=Crate%20pulls"> </a>
+<a href="https://www.nuget.org/packages/Cloud.Unum.USearch"> <img alt="NuGet" src="https://img.shields.io/nuget/dt/Cloud.Unum.USearch?label=NuGet%20pulls"> </a>
+<a href="https://central.sonatype.com/artifact/cloud.unum/usearch/overview"> <img alt="Maven" src="https://img.shields.io/nexus/r/cloud.unum/usearch?server=https%3A%2F%2Fs01.oss.sonatype.org%2F&label=Maven%20version"> </a>
+<a href="https://hub.docker.com/r/unum/usearch"> <img alt="Docker" src="https://img.shields.io/docker/pulls/unum/usearch?label=Docker%20pulls"> </a>
+<img alt="GitHub code size in bytes" src="https://img.shields.io/github/languages/code-size/unum-cloud/usearch?label=Repo%20size">
 </div>
 
 ---
 
-- ✅ Benchmark-topping performance.
+- ✅ 10x faster than [FAISS][faiss] implementation of [HNSW algorithm][hnsw-algorithm].
 - ✅ Simple and extensible [single C++11 header][usearch-header] implementation.
-- ✅ SIMD-optimized and [user-defined metrics](#user-defined-functions) with JIT compilation.
-- ✅ Variable dimensionality vectors for unique applications, including search over compressed data.
-- ✅ Bitwise Tanimoto and Sorensen coefficients for [Genomics and Chemistry applications](#usearch--rdkit--molecular-search).
+- ✅ Compatible with a dozen programming languages out of the box.
+- ✅ [SIMD][simd]-optimized and [user-defined metrics](#user-defined-functions) with JIT compilation.
 - ✅ Hardware-agnostic `f16` & `i8` - [half-precision & quarter-precision support](#memory-efficiency-downcasting-and-quantization).
 - ✅ [View large indexes from disk](#serving-index-from-disk) without loading into RAM.
+- ✅ Heterogeneous lookups, renaming/relabeling, and on-the-fly deletions.
+- ✅ Variable dimensionality vectors for unique applications, including search over compressed data.
+- ✅ Binary Tanimoto and Sorensen coefficients for [Genomics and Chemistry applications](#usearch--rdkit--molecular-search).
 - ✅ Space-efficient point-clouds with `uint40_t`, accommodating 4B+ size.
 - ✅ Compatible with OpenMP and custom "executors", for fine-grained control over CPU utilization.
-- ✅ Heterogeneous lookups, renaming/relabeling, and on-the-fly deletions.
-- ✅ Near-real-time [clustering and sub-clusterings](#clustering) for Tens or Millions of clusters.
+- ✅ Near-real-time [clustering and sub-clustering](#clustering) for Tens or Millions of clusters.
 - ✅ [Semantic Search](#usearch--ai--multi-modal-semantic-search) and [Joins](#joins).
 
+[faiss]: https://github.com/facebookresearch/faiss
 [usearch-header]: https://github.com/unum-cloud/usearch/blob/main/include/usearch/index.hpp
 [obscure-use-cases]: https://ashvardanian.com/posts/abusing-vector-search
+[hnsw-algorithm]: https://arxiv.org/abs/1603.09320
+[simd]: https://en.wikipedia.org/wiki/Single_instruction,_multiple_data
 
 ## Comparison with FAISS
 
 FAISS is a widely recognized standard for high-performance vector search engines.
 USearch and FAISS both employ the same HNSW algorithm, but they differ significantly in their design principles.
-USearch is compact and broadly compatible without sacrificing performance, with a primary focus on user-defined metrics and fewer dependencies.
-
-|                     | FAISS                         | USearch                            |
-| :------------------ | :---------------------------- | :--------------------------------- |
-| Implementation      | 84 K [SLOC][sloc] in `faiss/` | 3 K [SLOC][sloc] in `usearch/`     |
-| Supported metrics   | 9 fixed metrics               | Any User-Defined metrics           |
-| Supported languages | C++, Python                   | 10 languages                       |
-| Supported ID types  | `uint32_t`, `uint64_t`        | `uint32_t`, `uint40_t`, `uint64_t` |
-| Dependencies        | BLAS, OpenMP                  | None                               |
-| Bindings            | SWIG                          | Native                             |
-| Acceleration        | Learned Quantization          | Downcasting                        |
+USearch is compact and broadly compatible without sacrificing performance, primarily focusing on user-defined metrics and fewer dependencies.
+
+|                                              |                         FAISS |                        USearch |              Improvement |
+| :------------------------------------------- | ----------------------------: | -----------------------------: | -----------------------: |
+| Indexing time                                |                               |                                |                          |
+| 100 Million 96d `f32`, `f16`, `i8` vectors   |           2.6 h, 2.6 h, 2.6 h |            0.3 h, 0.2 h, 0.2 h | __9.6x, 10.4x, 10.7x__ ⁰ |
+| 100 Million 1536d `f32`, `f16`, `i8` vectors |           5.0 h, 4.1 h, 3.8 h |            2.1 h, 1.1 h, 0.8 h |    __2.3x 3.6x, 4.4x__ ⁰ |
+|                                              |                               |                                |                          |
+| Codebase length                              | 84 K [SLOC][sloc] in `faiss/` | 3 K [SLOC][sloc] in `usearch/` |           maintainable ¹ |
+| Supported metrics                            |               9 fixed metrics |       any user-defined metrics |             extendible ² |
+| Supported languages                          |                   C++, Python |                   10 languages |               portable ³ |
+| Supported ID types                           |                32-bit, 64-bit |         32-bit, 40-bit, 64-bit |              efficient ⁴ |
+| Required dependencies                        |                  BLAS, OpenMP |                              - |           light-weight ⁵ |
+| Bindings                                     |                          SWIG |                         Native |            low-latency ⁶ |
 
 [sloc]: https://en.wikipedia.org/wiki/Source_lines_of_code
 
+> ⁰ [Tested][intel-benchmarks] on Intel Sapphire Rapids, with the simplest inner-product distance, equivalent recall, and memory consumption, while also providing far superior search speed.
+> ¹ A shorter codebase makes the project easier to maintain and audit.
+> ² User-defined metrics allow you to customize your search for various applications, from GIS to creating custom metrics for composite embeddings from multiple AI models or hybrid full-text and semantic search.
+> ³ With USearch, you can reuse the same preconstructed index in various programming languages.
+> ⁴ The 40-bit integer allows you to store 4B+ vectors without allocating 8 bytes for every neighbor reference in the proximity graph.
+> ⁵ Lack of obligatory dependencies makes USearch much more portable.
+> ⁶ Native bindings introduce lower call latencies than more straightforward approaches.
+
+[intel-benchmarks]: https://www.unum.cloud/blog/2023-11-11-scaling-vector-search
+
 Base functionality is identical to FAISS, and the interface must be familiar if you have ever investigated Approximate Nearest Neighbors search:
 
 ```py
@@ -88,44 +106,30 @@ $ pip install usearch
 import numpy as np
 from usearch.index import Index
 
-index = Index(
-    ndim=3, # Define the number of dimensions in input vectors
-    metric='cos', # Choose 'l2sq', 'haversine' or other metric, default = 'ip'
-    dtype='f32', # Quantize to 'f16' or 'i8' if needed, default = 'f32'
-    connectivity=16, # Optional: How frequent should the connections in the graph be
-    expansion_add=128, # Optional: Control the recall of indexing
-    expansion_search=64, # Optional: Control the quality of search
-)
+index = Index(ndim=3)
 
 vector = np.array([0.2, 0.6, 0.4])
 index.add(42, vector)
+
 matches = index.search(vector, 10)
 
-assert len(index) == 1
-assert len(matches) == 1
 assert matches[0].key == 42
 assert matches[0].distance <= 0.001
 assert np.allclose(index[42], vector)
 ```
 
-Comparing the performance of FAISS against USearch on 1 Million 96-dimensional vectors from the famous Deep1B dataset, once can expect the following numbers on modern AWS `c7g.metal` instances.
-
-|              | FAISS, `f32` | USearch, `f32` | USearch, `f16` |     USearch, `i8` |
-| :----------- | -----------: | -------------: | -------------: | ----------------: |
-| Batch Insert |       16 K/s |         73 K/s |        100 K/s | 104 K/s __+550%__ |
-| Batch Search |       82 K/s |        103 K/s |        113 K/s |  134 K/s __+63%__ |
-| Bulk Insert  |       76 K/s |        105 K/s |        115 K/s | 202 K/s __+165%__ |
-| Bulk Search  |      118 K/s |        174 K/s |        173 K/s | 304 K/s __+157%__ |
-| Recall @ 10  |          99% |          99.2% |          99.1% |             99.2% |
+More settings are always available, and the API is designed to be as flexible as possible.
 
-> HNSW was configured with identical hyper-parameters:
-> connectivity `M=16`,
-> expansion @ construction `efConstruction=128`,
-> and expansion @ search `ef=64`.
-> Batch size is 256.
-> Jump to the [Performance Tuning][benchmarking] section to read about the effects of those hyper-parameters.
-
-[benchmarking]: https://github.com/unum-cloud/usearch/blob/main/docs/benchmarks.md
+```py
+index = Index(
+    ndim=3, # Define the number of dimensions in input vectors
+    metric='cos', # Choose 'l2sq', 'haversine' or other metric, default = 'ip'
+    dtype='f32', # Quantize to 'f16' or 'i8' if needed, default = 'f32'
+    connectivity=16, # Optional: How frequent should the connections in the graph be
+    expansion_add=128, # Optional: Control the recall of indexing
+    expansion_search=64, # Optional: Control the quality of search
+)
+```
 
 ## User-Defined Functions
 
@@ -220,7 +224,7 @@ multi_index.search(...)
 ## Clustering
 
 Once the index is constructed, it can be used to cluster entries much faster.
-In essense, the `Index` itself can be seen as a clustering, and it allows iterative deepening.
+In essence, the `Index` itself can be seen as a clustering, and it allows iterative deepening.
 
 ```py
 clustering = index.cluster(
@@ -241,7 +245,7 @@ g = clustering.network
 # Get members of a specific cluster
 first_members = clustering.members_of(centroid_keys[0])
 
-# Deepen into that cluster spliting it into more parts, all same arguments supported
+# Deepen into that cluster splitting it into more parts, all same arguments supported
 sub_clustering = clustering.subcluster(min_count=..., max_count=...)
 ```
 
@@ -342,7 +346,7 @@ Comparing molecule graphs and searching for similar structures is expensive and
 It can be seen as a special case of the NP-Complete Subgraph Isomorphism problem.
 Luckily, domain-specific approximate methods exist.
 The one commonly used in Chemistry, is to generate structures from [SMILES][smiles], and later hash them into binary fingerprints.
-The latter are searchable with bitwise similarity metrics, like the Tanimoto coefficient.
+The latter are searchable with binary similarity metrics, like the Tanimoto coefficient.
 Below is an example using the RDKit package.
 
 ```python
@@ -380,9 +384,10 @@ The search is based on the Haversine distance metric, but can easily be extended
 ## Integrations
 
 - [x] GPTCache: [Python](https://github.com/zilliztech/GPTCache/releases/tag/0.1.29).
-- [x] LangChain: [Python](https://github.com/langchain-ai/langchain/releases/tag/v0.0.257) and [JavaScipt](https://github.com/hwchase17/langchainjs/releases/tag/0.0.125).
+- [x] LangChain: [Python](https://github.com/langchain-ai/langchain/releases/tag/v0.0.257) and [JavaScript](https://github.com/hwchase17/langchainjs/releases/tag/0.0.125).
 - [x] ClickHouse: [C++](https://github.com/ClickHouse/ClickHouse/pull/53447).
 - [x] Microsoft Semantic Kernel: [Python](https://github.com/microsoft/semantic-kernel/releases/tag/python-0.3.9.dev) and C#.
+- [x] LanternDB: [C++](https://github.com/lanterndata/lantern) and [Rust](https://github.com/lanterndata/lantern_extras).
 
 ## Citations
 
@@ -392,7 +397,7 @@ doi = {10.5281/zenodo.7949416},
 author = {Vardanian, Ash},
 title = {{USearch by Unum Cloud}},
 url = {https://github.com/unum-cloud/usearch},
-version = {2.8.3},
+version = {2.8.5},
 year = {2023},
 month = oct,
 }

package/build.gradle

@@ -109,11 +109,11 @@ jar {
     }
 }
 
-if (project.hasProperty('signArtifacts') && signArtifacts.toBoolean()) {
-    signing {
-        useGpgCmd()
-        sign publishing.publications
-    }
+signing {
+    def signingKey = findProperty("signingKey")
+    def signingPassword = findProperty("signingPassword")
+    useInMemoryPgpKeys(signingKey, signingPassword)
+    sign publishing.publications
 }
 
 publishing {
@@ -124,10 +124,8 @@ publishing {
             artifact sourcesJar
             artifact javadocJar
 
-            if (project.hasProperty('signArtifacts') && signArtifacts.toBoolean()) {
-                signing {
-                    sign publishing.publications.library
-                }
+            signing {
+                sign publishing.publications.library
             }
 
             pom {

package/conanfile.py

@@ -7,7 +7,7 @@ required_conan_version = ">=1.53.0"
 class USearchConan(ConanFile):
 
     name = "usearch"
-    version = '2.8.3'
+    version = '2.8.5'
     license = "Apache-2.0"
     description = "Smaller & Faster Single-File Vector Search Engine from Unum"
     homepage = "https://github.com/unum-cloud/usearch"

package/cpp/README.md

@@ -25,14 +25,20 @@ metric_punned_t metric(256, metric_kind_t::l2sq_k, scalar_kind_t::f32_k);
 index_dense_t index = index_dense_t::make(metric);
 float vec[3] = {0.1, 0.3, 0.2};
 
-index.reserve(10);
-index.add(/* key: */ 42, /* vector: */ {&vec[0], 3});
-auto results = index.search(/* query: */ {&vec[0], 3}, 5 /* neighbors */);
+index.reserve(10); // Pre-allocate memory for 10 vectors
+index.add(42, &vec[0]); // Pass a key and a vector
+auto results = index.search(&vec[0], 5); // Pass a query and limit number of results
 
 for (std::size_t i = 0; i != results.size(); ++i)
     results[i].element.key, results[i].element.vector, results[i].distance;
 ```
 
+Here we:
+
+- define a metric of kind [`metric_kind_t::l2sq_k`](https://unum-cloud.github.io/usearch/cpp/reference.html#_CPPv413metric_kind_t),
+- to be applied to [`scalar_kind_t::f32_k`](https://unum-cloud.github.io/usearch/cpp/reference.html#_CPPv413scalar_kind_t) floating-point vectors,
+- instantiate an [`index_dense_t`](https://unum-cloud.github.io/usearch/cpp/reference.html#_CPPv4I00EN4unum7usearch14index_dense_gtE) index.
+
 The `add` is thread-safe for concurrent index construction.
 It also has an overload for different vector types, casting them under the hood.
 The same applies to the `search`, `get`, `cluster`, and `distance_between` functions.
@@ -52,20 +58,78 @@ index.load("index.usearch"); // Copying from disk
 index.view("index.usearch"); // Memory-mapping from disk
 ```
 
-## User-Defined Metrics in C++
+## Multi-Threading
 
-For advanced users, more compile-time abstractions are available.
+Most AI, HPC, or Big Data packages use some form of a thread pool.
+Instead of spawning additional threads within USearch, we focus on the thread safety of `add()` function, simplifying resource management.
 
 ```cpp
-template <typename distance_at = default_distance_t,              // `float`
-          typename key_at = default_key_t,                        // `int64_t`, `uuid_t`
-          typename compressed_slot_at = default_slot_t,           // `uint32_t`, `uint40_t`
-          typename dynamic_allocator_at = std::allocator<byte_t>, //
-          typename tape_allocator_at = dynamic_allocator_at>      //
-class index_gt;
+#pragma omp parallel for
+    for (std::size_t i = 0; i < n; ++i)
+        native.add(key, span_t{vector, dims});
+```
+
+During initialization, we allocate enough temporary memory for all the cores on the machine.
+On the call, the user can supply the identifier of the current thread, making this library easy to integrate with OpenMP and similar tools.
+
+Moreover, you can take advantage of one of the provided "executors" to parallelize the search:
+
+- `executor_openmp_t`, that would use OpenMP under the hood.
+- `executor_stl_t`, that will spawn `std::thread` instances.
+- `dummy_executor_t`, that will run everything sequentially.
+
+## Clustering
+
+Aside from basic Create-Read-Update-Delete (CRUD) operations and search, USearch also supports clustering.
+Once the index is constructed, you can either:
+
+- Identify a cluster to which any external vector belongs, once mapped onto the index.
+- Split the entire index into a set of clusters, each with its own centroid.
+
+For the first, the interface accepts a vector and a "clustering level", which is essentially the index of the HNSW graph layer, in which to search.
+If you pass zero, the traversal will happen in every level except the bottom one.
+Otherwise, the search will be limited to the specified level.
+
+```cpp
+some_scalar_t vector[3] = {0.1, 0.3, 0.2};
+cluster_result_t result = index.cluster(&vector, index.max_level() / 2);
+match_t cluster = result.cluster;
+member_cref_t member = cluster.member;
+distance_t distance = cluster.distance;
 ```
 
-The following distances are pre-packaged:
+If you wish to split the whole structure into clusters, you must provide an iterator over a range of vectors, that will be processed in parallel using the previously described function.
+Unlike the previous function, you don't have to manually specify the level, as the algorithm will pick the best one for you, depending on the number of clusters you want to highlight.
+Aside from that auto-tuning, this function will regroup some of the clusters, if they are too small, and return the final number of clusters.
+
+```cpp
+std::size_t queries_count = queries_end - queries_begin;
+index_dense_clustering_config_t config;
+config.min_clusters = 1000;
+config.max_clusters = 2000;
+config.mode = index_dense_clustering_config_t::merge_smallest_k;
+
+// Outputs:
+vector_key_t cluster_centroids_keys[queries_count];
+distance_t distances_to_cluster_centroids[queries_count];
+executor_default_t thread_pool;
+dummy_progress_t progress_bar;
+
+clustering_result_t result = cluster(
+        queries_begin, queries_end,
+        config,
+        &cluster_centroids_keys, &distances_to_cluster_centroids,
+        thread_pool, progress_bar);
+```
+
+This approach requires basic understanding of templates meta-programming to implement the `queries_begin` and `queries_end` smart-iterators.
+On the bright side, it allows iteratively deepening into a specific cluster.
+
+As in many other bulk-processing APIs, the `executor` and `progress` are optional.
+
+## User-Defined Metrics
+
+In its high-level interface, USearch supports a variety of metrics, including the most popular ones:
 
 - `metric_cos_gt<scalar_t>` for "Cosine" or "Angular" distance.
 - `metric_ip_gt<scalar_t>` for "Inner Product" or "Dot Product" distance.
@@ -78,16 +142,20 @@ The following distances are pre-packaged:
 - `metric_haversine_gt<scalar_t>` for "Haversine" or "Great Circle" distance between coordinates used in GIS applications.
 - `metric_divergence_gt<scalar_t>` for the "Jensen Shannon" similarity between probability distributions.
 
-## Multi-Threading
+In reality, for most common types, one of the [SimSIMD](https://github.com/ashvardanian/SimSIMD) backends will be triggered, providing hardware-acceleration for most common CPUs.
 
-Most AI, HPC, or Big Data packages use some form of a thread pool.
-Instead of spawning additional threads within USearch, we focus on the thread safety of `add()` function, simplifying resource management.
+If you need a different metric, you can implement it yourself and wrap it into a `metric_punned_t`, which is our alternative to the `std::function`.
+Unlike the `std::function`, it is a trivial type, which is important for performance.
+
+## Advanced Interface
+
+If you are proficient in C++ and ready to get your hands dirty, you can use the low-level interface.
 
 ```cpp
-#pragma omp parallel for
-    for (std::size_t i = 0; i < n; ++i)
-        native.add(key, span_t{vector, dims});
+template <typename distance_at = default_distance_t,              // `float`
+          typename key_at = default_key_t,                        // `int64_t`, `uuid_t`
+          typename compressed_slot_at = default_slot_t,           // `uint32_t`, `uint40_t`
+          typename dynamic_allocator_at = std::allocator<byte_t>, //
+          typename tape_allocator_at = dynamic_allocator_at>      //
+class index_gt;
 ```
-
-During initialization, we allocate enough temporary memory for all the cores on the machine.
-On the call, the user can supply the identifier of the current thread, making this library easy to integrate with OpenMP and similar tools.

package/csharp/DEV_SETUP.md

@@ -11,7 +11,7 @@ To obtain all libraries, download the artifacts generated by the GitHub workflow
 
 To get a library for your current platform (Linux or Macos), execute: `./eng/build_lib.sh`.
 
-For more details, refer to the [compilation guide](https://github.com/unum-cloud/usearch/blob/main/docs/compilation.md).
+For more details, refer to the [compilation guide](https://github.com/unum-cloud/usearch/blob/main/CONTRIBUTING.md).
 
 # Build and Test
 

package/csharp/nuget/nuget-package.props

@@ -1,7 +1,7 @@
 <?xml version="1.0" encoding="utf-8"?>
 <Project>
   <PropertyGroup>
-    <Version Condition="'$(Version)' == ''">2.8.3</Version>
+    <Version Condition="'$(Version)' == ''">2.8.5</Version>
 
     <Authors>Unum</Authors>
     <Company>Unum</Company>

package/docs/{compilation.rst → contributing.rst}

@@ -1,5 +1,5 @@
 ========================
-Compilation
+Contributing
 ========================
 
-.. mdinclude:: compilation.md
+.. mdinclude:: ../CONTRIBUTING.md

package/docs/index.rst

@@ -22,7 +22,7 @@ Overview
    :hidden:
    :caption: �
 
-   compilation
+   contributing
    benchmarks
    format
 

package/include/usearch/index.hpp

@@ -11,7 +11,7 @@
 
 #define USEARCH_VERSION_MAJOR 2
 #define USEARCH_VERSION_MINOR 8
-#define USEARCH_VERSION_PATCH 3
+#define USEARCH_VERSION_PATCH 5
 
 // Inferring C++ version
 // https://stackoverflow.com/a/61552074

package/include/usearch/index_dense.hpp

@@ -323,7 +323,7 @@ class index_dense_gt {
     /// @brief Schema: input buffer, bytes in input buffer, output buffer.
     using cast_t = std::function<bool(byte_t const*, std::size_t, byte_t*)>;
     /// @brief Punned index.
-    using index_t = index_gt<                 //
+    using index_t = index_gt<                        //
         distance_t, vector_key_t, compressed_slot_t, //
         dynamic_allocator_t, tape_allocator_t>;
     using index_allocator_t = aligned_allocator_gt<index_t, 64>;
@@ -1512,10 +1512,14 @@ class index_dense_gt {
      *  @brief  Implements clustering, classifying the given objects (vectors of member keys)
      *          into a given number of clusters.
      *
-     *  @param[in] queries_begin Iterator targeting the fiest query.
-     *  @param[in] queries_end
+     *  @param[in] queries_begin Iterator pointing to the first query.
+     *  @param[in] queries_end Iterator pointing to the last query.
      *  @param[in] executor Thread-pool to execute the job in parallel.
      *  @param[in] progress Callback to report the execution progress.
+     *  @param[in] config Configuration parameters for clustering.
+     *
+     *  @param[out] cluster_keys Pointer to the array where the cluster keys will be exported.
+     *  @param[out] cluster_distances Pointer to the array where the distances to those centroids will be exported.
      */
     template <                                   //
         typename queries_iterator_at,            //
@@ -1526,7 +1530,7 @@ class index_dense_gt {
         queries_iterator_at queries_begin,      //
         queries_iterator_at queries_end,        //
         index_dense_clustering_config_t config, //
-        vector_key_t* cluster_keys,                    //
+        vector_key_t* cluster_keys,             //
         distance_t* cluster_distances,          //
         executor_at&& executor = executor_at{}, //
         progress_at&& progress = progress_at{}) {
@@ -1715,7 +1719,7 @@ class index_dense_gt {
     }
 
     template <typename scalar_at>
-    add_result_t add_(                      //
+    add_result_t add_(                             //
         vector_key_t key, scalar_at const* vector, //
         std::size_t thread, bool force_vector_copy, cast_t const& cast) {
 
@@ -1811,8 +1815,8 @@ class index_dense_gt {
     }
 
     template <typename scalar_at>
-    aggregated_distances_t distance_between_( //
-        vector_key_t key, scalar_at const* vector,   //
+    aggregated_distances_t distance_between_(      //
+        vector_key_t key, scalar_at const* vector, //
         std::size_t thread, cast_t const& cast) const {
 
         // Cast the vector, if needed for compatibility with `metric_`