Update to 0.0.8 (#159)

Updates needed for 0.0.8 release

---------

Co-authored-by: Mihai Capotă <mihai@mihaic.ro>

Author: ethanglaser

CMakeLists.txt

@@ -23,7 +23,7 @@ project(svs
     # - /bindings/python/tests/test_common.py
     # Manually keep in-sync with:
     # - /bindings/python/setup.py
-    VERSION 0.0.7
+    VERSION 0.0.8
 )
 
 set(SVS_LIB svs_devel)

HISTORY.md

@@ -1,3 +1,17 @@
+# SVS 0.0.7 Release Notes
+
+## Additions and Changes
+
+* Implemented batch iterator support for hybrid search
+
+* Added support for custom threading and memory allocation
+
+* Introduced a timeout feature for search calls
+
+* Introduced `reuse_empty` flag in dynamic Vamana, enabling users to choose whether to reuse empty entries that may exist after deletion and consolidation
+
+* Enhanced heuristics in the Vamana construct to improve efficiency when adding a small number of points.
+
 # SVS 0.0.6 Release Notes
 
 **Please note** that this repository only contains the open-source portion of the SVS library, which supports all functionalities and features described in the [documentation](https://intel.github.io/ScalableVectorSearch/), except for our proprietary vector compression techniques, specifically LVQ [[ABHT23]](#1) and Leanvec [[TBAH24]](#2). These techniques are closed-source and supported exclusively on Intel hardware. We provide [shared library](https://github.com/intel/ScalableVectorSearch/releases) and [PyPI package](https://pypi.org/project/scalable-vs/) to enable these vector compression techniques in C++ and Python, respectively.

NEWS.md

@@ -1,13 +1,23 @@
-# SVS 0.0.7 Release Notes
+# SVS 0.0.8 Release Notes
 
 ## Additions and Changes
 
-* Implemented batch iterator support for hybrid search
+* Addition of 8-bit scalar quantization support to C++ interface
 
-* Added support for custom threading and memory allocation
+* Introduced multi-vector index and batch iterator support that allows multiple vectors to be mapped to the same external ID
 
-* Introduced a timeout feature for search calls
+* Automatic ISA dispatching with optimizations based on AVX support
 
-* Introduced `reuse_empty` flag in dynamic Vamana, enabling users to choose whether to reuse empty entries that may exist after deletion and consolidation
+* Enabled compatibility with ARM and MacOS
 
-* Enhanced heuristics in the Vamana construct to improve efficiency when adding a small number of points.
+* Enhanced logging capabilities
+
+* Updated vamana iterator API
+
+* Broader [shared library](https://github.com/intel/ScalableVectorSearch/releases) support:
+
+  * gcc-11+, clang-18+, glibc 2.26+ compatibility
+  
+  * Static library provided in addition to .so
+  
+  * Intel(R) MKL linked within the shared library - no need for Intel(R) MKL in user environment

bindings/python/setup.py

@@ -38,7 +38,7 @@
 
 setup(
     name="scalable-vs",
-    version="0.0.7",
+    version="0.0.8",
     description="Scalable Vector Search (SVS) is a performance library for vector similarity search.",
     long_description=long_description,
     long_description_content_type="text/markdown",

bindings/python/tests/test_common.py

@@ -42,7 +42,7 @@ def tearDown(self):
     #####
 
     def test_version(self):
-        self.assertEqual(svs.library_version(), "v0.0.7")
+        self.assertEqual(svs.library_version(), "v0.0.8")
 
     def test_conversion(self):
         # signed

tests/svs/lib/version.cpp

@@ -46,6 +46,6 @@ CATCH_TEST_CASE("Version Numbers", "[lib][versions]") {
 
 // Keep in-sync with CMakeLists.txt
 CATCH_TEST_CASE("Global Version", "[lib][versions]") {
-    static_assert(svs::lib::svs_version == svs::lib::Version(0, 0, 7), "Version mismatch!");
-    CATCH_REQUIRE(svs::lib::svs_version == svs::lib::Version(0, 0, 7));
+    static_assert(svs::lib::svs_version == svs::lib::Version(0, 0, 8), "Version mismatch!");
+    CATCH_REQUIRE(svs::lib::svs_version == svs::lib::Version(0, 0, 8));
 }