preliminary release notes

Author: Yury

README.md

@@ -1,34 +1,22 @@
 # Hnswlib - fast approximate nearest neighbor search
-Header-only C++ HNSW implementation with python bindings.
+Header-only C++ HNSW implementation with python bindings, insertions and updates.
 
 **NEWS:**
 
+**version 0.7.0** 
 
-**version 0.6.2** 
-
-* Fixed a bug in saving of large pickles. The pickles with > 4GB could have been corrupted. Thanks Kai Wohlfahrt for reporting.
-* Thanks to ([@GuyAv46](https://github.com/GuyAv46)) hnswlib inner product now is more consitent accross architectures (SSE, AVX, etc). 
-* 
-
-**version 0.6.1** 
-
-* Thanks to ([@tony-kuo](https://github.com/tony-kuo)) hnswlib AVX512 and AVX builds are not backwards-compatible with older SSE and non-AVX512 architectures. 
-* Thanks to ([@psobot](https://github.com/psobot)) there is now a sencible message instead of segfault when passing a scalar to get_items.
-* Thanks to ([@urigoren](https://github.com/urigoren)) hnswlib has a lazy index creation python wrapper.
-
-**version 0.6.0** 
-* Thanks to ([@dyashuni](https://github.com/dyashuni)) hnswlib now uses github actions for CI, there is a search speedup in some scenarios with deletions. `unmark_deleted(label)` is now also a part of the python interface (note now it throws an exception for double deletions). 
-* Thanks to ([@slice4e](https://github.com/slice4e)) we now support AVX512; thanks to ([@LTLA](https://github.com/LTLA)) the cmake interface for the lib is now updated. 
-* Thanks to ([@alonre24](https://github.com/alonre24)) we now have a python bindings for brute-force (and examples for recall tuning: [TESTING_RECALL.md](TESTING_RECALL.md). 
-* Thanks to ([@dorosy-yeong](https://github.com/dorosy-yeong)) there is a bug fixed in the handling large quantities of deleted elements and large K. 
-
-  
+* Added support to filtering (#402, #430) by [@kishorenc](https://github.com/kishorenc)
+* Added python interface for filtering (though note its performance is limited by GIL) (#417) by [@gtsoukas](https://github.com/gtsoukas)
+* Added support for replacing the elements that were market as delete with newly inserted elements (to control the size of the index, #418) by [@dyashuni](https://github.com/dyashuni)
+* Fixed data races/deadlocks in updates/insertion, added stress test for multithreaded operation (#418) by [@dyashuni](https://github.com/dyashuni)
+* Documentation, tests, exception handling, refactoring (#375, #379, #380, #395, #396, #401, #406, #404, #409, #410, #416, #415, #431, #432, #433) by [@jlmelville](https://github.com/jlmelville), [@dyashuni](https://github.com/dyashuni), [@kishorenc](https://github.com/kishorenc), [@korzhenevski](https://github.com/korzhenevski), [@yoshoku](https://github.com/yoshoku), [@jianshu93](https://github.com/jianshu93), [@PLNech](https://github.com/PLNech)
+* global linkages (#383) by [@MasterAler](https://github.com/MasterAler), USE_SSE usage in MSVC (#408) by [@alxvth](https://github.com/alxvth)
 
 
 ### Highlights:
 1) Lightweight, header-only, no dependencies other than C++ 11
-2) Interfaces for C++, Java, Python and R (https://github.com/jlmelville/rcpphnsw).
-3) Has full support for incremental index construction. Has support for element deletions 
+2) Interfaces for C++, Python, external support for Java and R (https://github.com/jlmelville/rcpphnsw).
+3) Has full support for incremental index construction and updating the elements. Has support for element deletions 
 (by marking them in index). Index is picklable.
 4) Can work with custom user defined distances (C++).
 5) Significantly less memory footprint and faster build time compared to current nmslib's implementation.
@@ -50,7 +38,7 @@ Note that inner product is not an actual metric. An element can be closer to som
 
 For other spaces use the nmslib library https://github.com/nmslib/nmslib. 
 
-#### Short API description
+#### API description
 * `hnswlib.Index(space, dim)` creates a non-initialized index an HNSW in space `space` with integer dimension `dim`.
 
 `hnswlib.Index` methods:
@@ -263,14 +251,17 @@ https://github.com/facebookresearch/faiss
 ["Revisiting the Inverted Indices for Billion-Scale Approximate Nearest Neighbors"](https://arxiv.org/abs/1802.02422) 
 (current state-of-the-art in compressed indexes, C++):
 https://github.com/dbaranchuk/ivf-hnsw
+* Amazon PECOS https://github.com/amzn/pecos 
 * TOROS N2 (python, C++): https://github.com/kakao/n2 
 * Online HNSW (C++): https://github.com/andrusha97/online-hnsw) 
 * Go implementation: https://github.com/Bithack/go-hnsw
 * Python implementation (as a part of the clustering code by by Matteo Dell'Amico): https://github.com/matteodellamico/flexible-clustering
+* Julia implmentation https://github.com/JuliaNeighbors/HNSW.jl
 * Java implementation: https://github.com/jelmerk/hnswlib
 * Java bindings using Java Native Access: https://github.com/stepstone-tech/hnswlib-jna
-* .Net implementation: https://github.com/microsoft/HNSW.Net
+* .Net implementation: https://github.com/curiosity-ai/hnsw-sharp
 * CUDA implementation: https://github.com/js1010/cuhnsw
+* Rust implementation https://github.com/rust-cv/hnsw
 * Rust implementation for memory and thread safety purposes and There is  A Trait to enable the user to implement its own distances. It takes as data slices of types T satisfying T:Serialize+Clone+Send+Sync.: https://github.com/jean-pierreBoth/hnswlib-rs
 
 ### 200M SIFT test reproduction 

setup.py

@@ -8,7 +8,7 @@
 from setuptools import Extension, setup
 from setuptools.command.build_ext import build_ext
 
-__version__ = '0.6.1'
+__version__ = '0.7.0'
 
 
 include_dirs = [