Prep v0.13.0-rc.2

CHANGELOG.md

@@ -1,5 +1,27 @@
 # Change Log
 
+## [v0.13.0](https://github.com/SeldonIO/alibi-detect/tree/v0.13.0) (2024-04-17)
+[Full Changelog](https://github.com/SeldonIO/alibi-detect/compare/v0.13.0...v0.12.0)
+
+This is a minor release. The main feature is adding support for Python 3.12 and increasing the TensorFlow version bound.
+
+Note: If saving detectors with `legacy=True` or loading detectors that were saved with `legacy=True` users must set the environment variable `TF_USE_LEGACY_KERAS=1` in order to configure tensorflow to use the legacy Keras 2 implementation instead of the now-default Keras 3. See **TensorFlow + Keras 2 backwards compatibility** section of the [Getting Started docs for Keras](https://keras.io/getting_started/) for more details.
+
+### Added
+
+- Added support for python3.12 ([#917](https://github.com/SeldonIO/alibi-detect/pull/917))
+
+### Fixed
+
+- Numerical stability fix for spectral residual outlier detector ([#907](http://github.com/SeldonIO/alibi-detect/pull/907))
+- Fixes Mahalanobis detector incompatibility with `scipy>1.13` ([#913](https://github.com/SeldonIO/alibi-detect/pull/913))
+- Fixed image rendering in Jupyter notebooks ([#918](https://github.com/SeldonIO/alibi-detect/pull/918))
+
+### Changed
+
+- Migrated docs to gitbook ([#904](https://github.com/SeldonIO/alibi-detect/pull/904), [#937](https://github.com/SeldonIO/alibi-detect/pull/937), [#923](https://github.com/SeldonIO/alibi-detect/pull/923))
+- Increased tensorflow version bound to `<2.19` ([#908](https://github.com/SeldonIO/alibi-detect/pull/908))
+
 ## [v0.12.0](https://github.com/SeldonIO/alibi-detect/tree/v0.12.0) (2024-04-17)
 [Full Changelog](https://github.com/SeldonIO/alibi-detect/compare/v0.11.5...v0.12.0)
 

CITATION.cff

@@ -19,6 +19,6 @@ authors:
 - family-names: "Athorne"
   given-names: "Alex"
 title: "Alibi Detect: Algorithms for outlier, adversarial and drift detection"
-version: 0.12.0
-date-released: 2024-04-17
+version: 0.13.0
+date-released: 2025-12-03
 url: "https://github.com/SeldonIO/alibi-detect"

README.md

@@ -407,8 +407,8 @@ BibTeX entry:
   title = {Alibi Detect: Algorithms for outlier, adversarial and drift detection},
   author = {Van Looveren, Arnaud and Klaise, Janis and Vacanti, Giovanni and Cobb, Oliver and Scillitoe, Ashley and Samoilescu, Robert and Athorne, Alex},
   url = {https://github.com/SeldonIO/alibi-detect},
-  version = {0.12.1.dev0},
-  date = {2024-04-17},
+  version = {0.13.0},
+  date = {2025-12-03},
   year = {2019}
 }
 ```

alibi_detect/version.py

@@ -3,4 +3,4 @@
 # 2) we can import it in setup.py for the same reason
 # 3) we can import it into your module module
 
-__version__ = "0.12.1.dev0"
+__version__ = "0.13.0"

docs-gb/saving.md

@@ -30,7 +30,11 @@ od = load_detector(filepath)
 Detectors can be saved using two formats:
 
 * **Config format**: For drift detectors, by default `save_detector` serializes the detector via a config file named `config.toml`, stored in `filepath`. The [TOML](https://toml.io/en/) format is human-readable, which makes the config files useful for record keeping, and allows a detector to be edited before it is reloaded. For more details, see [Detector Configuration Files](config_files.md).
-* **Legacy format**: Outlier and adversarial detectors are saved to [dill](https://dill.readthedocs.io/en/latest/dill.html) files stored within `filepath`. Drift detectors can also be saved in this legacy format by running `save_detector` with `legacy=True`. Loading is performed in the same way, by simply running `load_detector(filepath)`.
+* **Legacy format**: Outlier and adversarial detectors are saved to [dill](https://dill.readthedocs.io/en/latest/dill.html) files stored within `filepath`. Drift detectors can also be saved in this legacy format by running `save_detector` with `legacy=True`. Loading is performed in the same way, by simply running `load_detector(filepath)`. 
+
+{% hint style="info" %}
+**Note:** If you save a detector with `legacy=True`, or load one that was saved with `legacy=True`, and you are using TensorFlow>2.15, then you must set the environment variable `TF_USE_LEGACY_KERAS=1`. This is in order to tell TensorFlow to use the legacy Keras 2 implementation to save and load TensorFlow models. See **TensorFlow + Keras 2 backwards compatibility** section of the [Getting Started docs for Keras](https://keras.io/getting_started/) for more details.
+{% endhint %}
 
 ## Supported detectors