Skip to content

Commit

Permalink
Merge pull request #1466 from cliveseldon/884_rolling_updates
Browse files Browse the repository at this point in the history
Change naming of deployments
  • Loading branch information
seldondev authored Mar 3, 2020
2 parents 2df3c9e + fb4af8f commit 14c1b09
Show file tree
Hide file tree
Showing 161 changed files with 2,328 additions and 18,132 deletions.
16 changes: 12 additions & 4 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -84,8 +84,6 @@ examples/models/pyspark_pmml/.gitignore
examples/models/h2o_mojo/src/main/resources/model.zip

#created model folders
examples/models/deep_mnist/MNIST_data/
examples/models/deep_mnist/model/
examples/models/sklearn_iris/IrisClassifier.sav
examples/istio/canary_update/MNIST_data/
examples/istio/canary_update/tmp/
Expand All @@ -99,8 +97,6 @@ examples/models/r_mnist/t10k-images-idx3-ubyte
examples/models/r_mnist/t10k-labels-idx1-ubyte
examples/models/r_mnist/train-images-idx3-ubyte
examples/models/r_mnist/train-labels-idx1-ubyte
examples/models/sk_mnist/MNIST_data/
examples/models/sk_mnist/sk.pkl
examples/models/sklearn_iris_fbs/IrisClassifier.sav

# Pickle files
Expand Down Expand Up @@ -201,3 +197,15 @@ testing/scripts/go

operator/operator.tar
operator/helm/tmp/

# vim
*.swp

notebooks/helm_examples.py
notebooks/*.py
examples/ambassador/canary/ambassador_canary.py
examples/ambassador/custom/ambassador_custom.py
examples/ambassador/headers/ambassador_headers.py
examples/ambassador/shadow/ambassador_shadow.py
examples/models/metrics/metrics.py
examples/models/tracing/tracing.py
22 changes: 19 additions & 3 deletions core-builder/Dockerfile
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
FROM openjdk:13.0.1-jdk-buster

ENV PYTHON_VERSION "3.6.0"
ENV PYTHON_VERSION "3.6.10"

# install docker
RUN \
Expand Down Expand Up @@ -57,12 +57,14 @@ RUN mkdir -p /usr/share/maven /usr/share/maven/ref \
ENV MAVEN_HOME=/usr/share/maven
ENV MAVEN_CONFIG="$USER_HOME_DIR/.m2"

# ZLIB1G required for installation python
# compression and ssl libs required for installation python and dependencies (pandas)
RUN apt-get upgrade && \
apt-get update && \
apt-get install zlib1g -y && \
apt-get install zlib1g-dev -y && \
apt-get install libssl-dev -y
apt-get install libssl-dev -y && \
apt-get install libbz2-dev -y && \
apt-get install liblzma-dev -y

RUN curl -SLO https://www.python.org/ftp/python/${PYTHON_VERSION}/Python-${PYTHON_VERSION}.tgz \
&& tar xvf Python-${PYTHON_VERSION}.tgz \
Expand Down Expand Up @@ -110,6 +112,20 @@ RUN \
update-alternatives --set ip6tables /usr/sbin/ip6tables-legacy && \
update-alternatives --set iptables /usr/sbin/iptables-legacy

# install jupyter
RUN pip install jupyter

# Install grpcurl
RUN go get github.com/fullstorydev/grpcurl && \
go install github.com/fullstorydev/grpcurl/cmd/grpcurl

ENV PATH="${PATH}:/root/go/bin"

# Notebooks python requirements
RUN pip install alibi && \
pip install matplotlib && \
pip install keras

WORKDIR /work

# Define default command.
Expand Down
2 changes: 1 addition & 1 deletion core-builder/Makefile
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
DOCKER_IMAGE_NAME=seldonio/core-builder
DOCKER_IMAGE_VERSION=0.11
DOCKER_IMAGE_VERSION=0.12

build_docker_image:
docker build --force-rm=true -t $(DOCKER_IMAGE_NAME):$(DOCKER_IMAGE_VERSION) .
Expand Down
3 changes: 0 additions & 3 deletions doc/source/examples/deep_mnist.nblink

This file was deleted.

3 changes: 0 additions & 3 deletions doc/source/examples/onnx_resnet.nblink

This file was deleted.

3 changes: 0 additions & 3 deletions doc/source/examples/sklearn_mnist.nblink

This file was deleted.

3 changes: 0 additions & 3 deletions doc/source/examples/tmpl_model_with_metrics.nblink

This file was deleted.

6 changes: 1 addition & 5 deletions doc/source/ingress/ambassador.md
Original file line number Diff line number Diff line change
Expand Up @@ -77,11 +77,7 @@ A worked example for [canary deployments](../examples/ambassador_canary.html) is

Shadow deployments allow you to send duplicate requests to a parallel deployment but throw away the response. This allows you to test machine learning models under load and compare the results to the live deployment.

You simply need to add some annotations to your Seldon Deployment resource for your shadow deployment.

* `seldon.io/ambassador-shadow:true` : Flag to mark this deployment as a Shadow deployment in Ambassador.
* `seldon.io/ambassador-service-name:<existing_deployment_name>` : The name of the existing Seldon Deployment you want to attach to as a shadow.
* Example: `"seldon.io/ambassador-service-name":"example"`
Simply set the `shadow` boolean in your shadow predictor.

A worked example for [shadow deployments](../examples/ambassador_shadow.html) is provided.

Expand Down
Loading

0 comments on commit 14c1b09

Please sign in to comment.