diff --git a/.github/conan_dockerfile/Dockerfile b/.github/conan_dockerfile/Dockerfile
index d8d38c7e..d670fbc6 100644
--- a/.github/conan_dockerfile/Dockerfile
+++ b/.github/conan_dockerfile/Dockerfile
@@ -14,7 +14,8 @@ RUN sudo -E apt-get update \
 ARG PY_VERSION=3.8
 RUN pyenv install -s $PY_VERSION \
   && pyenv global $PY_VERSION
-RUN pip install "conan==1.59.0" catkin_pkg numpy wheel auditwheel cmake
+RUN pip install "conan==1.59.0" catkin_pkg oldest-supported-numpy wheel auditwheel cmake
+# oldest-supported-numpy for ABI compatibility
 
 # install patchelf
 RUN wget https://github.com/NixOS/patchelf/releases/download/0.17.2/patchelf-0.17.2-x86_64.tar.gz \
diff --git a/README.md b/README.md
index 65159f74..62b43ba0 100644
--- a/README.md
+++ b/README.md
@@ -17,7 +17,7 @@ https://pypi.org/project/lanelet2/)
 
 Convert Lanelet2 maps directly to instance labels for map perception and other map-based learning tasks! `lanelet2_ml_converter` provides local instance labels of various abstraction layers and representations accessible as numpy arrays from python. Check out the `lanelet2_ml_converter` module for more information and usage examples.
 
-**Note:** As the module is not released officially yet, to try it out you need to either build Lanelet2 with the python bindings yourself or manually install the pip wheel files from the CI artefacts (download [here](https://github.com/immel-f/Lanelet2/actions/runs/7820288630/artifacts/1228128122)).
+**Note:** As the module is not released officially yet, to try it out you need to either build Lanelet2 with the python bindings yourself or manually install the pip wheel files from the CI artefacts (download [here](https://github.com/immel-f/Lanelet2/actions/runs/7876754592/artifacts/1239381043) with a logged in GitHub account).
 
 ## Overview