feat(mlflow): Update Mlflow, API server, pyfunc server and batch predictor

.github/workflows/external.yml

@@ -22,9 +22,10 @@ jobs:
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
       - name: Build and push MLflow Docker image
-        uses: docker/build-push-action@v5
+        uses: docker/build-push-action@v6
         with:
           context: mlflow
+          push: true
           file: mlflow/Dockerfile
-          build-args: MLFLOW_VERSION=1.3.0
-          tags: ghcr.io/caraml-dev/mlflow:1.3.0
+          build-args: MLFLOW_VERSION=1.26.1
+          tags: ghcr.io/caraml-dev/mlflow:1.26.1

.github/workflows/merlin.yml

@@ -400,8 +400,9 @@ jobs:
       K3D_CLUSTER: merlin-cluster
       LOCAL_REGISTRY_PORT: 12345
       LOCAL_REGISTRY: "dev.localhost"
+      DOCKER_REGISTRY: "dev.localhost:12345"
       INGRESS_HOST: "127.0.0.1.nip.io"
-      MERLIN_CHART_VERSION: 0.13.4
+      MERLIN_CHART_VERSION: 0.13.18
       E2E_PYTHON_VERSION: "3.10.6"
       K3S_VERSION: v1.26.7-k3s1
     steps:

api/mlflow/mlflow.go

@@ -61,6 +61,7 @@ func (mlflow *client) doCall(req *request, resp interface{}) error {
 		return err
 	}
 
+	httpReq.Header.Set("Content-Type", "application/json")
 	httpResp, err := mlflow.httpClient.Do(httpReq)
 	if err != nil {
 		return err

api/mlflow/response.go

@@ -39,8 +39,8 @@ type Run struct {
 type Info struct {
 	RunID          string `json:"run_id"`
 	ExperimentID   string `json:"experiment_id"`
-	StartTime      string `json:"start_time"`
-	EndTime        string `json:"end_time"`
+	StartTime      int    `json:"start_time"`
+	EndTime        int    `json:"end_time"`
 	ArtifactURI    string `json:"artifact_uri"`
 	LifecycleStage string `json:"lifecycle_stage"`
 	Status         string `json:"status"`

mlflow/Dockerfile

@@ -9,11 +9,11 @@ RUN apt-get update && \
     apt-get clean
 
 RUN pip install google-cloud-storage
-RUN pip install psycopg2-binary==2.8.6
+RUN pip install psycopg2-binary==2.9.10
 
-ARG BOTO3_VERSION=1.7.12
-ARG MLFLOW_VERSION=1.3.0
-ARG SQLALCHEMY_VERSION=1.4.46
+ARG BOTO3_VERSION=1.35.39
+ARG MLFLOW_VERSION=1.26.1
+ARG SQLALCHEMY_VERSION=1.4.54
 
 RUN pip install boto3==${BOTO3_VERSION}
 RUN pip install SQLAlchemy==${SQLALCHEMY_VERSION}

python/batch-predictor/requirements.txt

@@ -1,6 +1,6 @@
 cloudpickle==2.0.0
 findspark==2.0.1
-merlin-sdk==0.44.0
+merlin-sdk==0.45.1
 mlflow==1.26.1
 pyarrow>=0.14.1,<=17.0.0
 pyspark==3.0.1

python/observation-publisher/requirements.txt

@@ -255,7 +255,7 @@ six==1.16.0
     #   querystring-parser
 smmap==5.0.1
     # via gitdb
-sqlalchemy==2.0.27
+sqlalchemy==1.4.54
     # via
     #   alembic
     #   mlflow

python/pyfunc-server/requirements.txt

@@ -4,7 +4,7 @@ cloudpickle==2.0.0
 confluent-kafka==2.3.0
 grpcio-health-checking
 grpcio-reflection
-merlin-sdk==0.44.0
+merlin-sdk==0.45.1
 numpy>=1.8.2
 orjson>=2.6.8
 prometheus-client

scripts/e2e/deploy-merlin.sh

@@ -28,7 +28,7 @@ install_merlin() {
     --set deployment.image.registry=${DOCKER_REGISTRY} \
     --set deployment.image.repository=merlin \
     --set deployment.image.tag=${VERSION} \
-    --set transformer.image=${DOCKER_REGISTRY}/merlin-transformer:${VERSION} \
+    --set rendered.overrides.StandardTransformerConfig.ImageName=${DOCKER_REGISTRY}/merlin-transformer:${VERSION} \
     --set imageBuilder.dockerRegistry=${DOCKER_REGISTRY} \
     --set imageBuilder.predictionJobBaseImages."3\.7\.*".imageName=${DOCKER_REGISTRY}/merlin/merlin-pyspark-base-py37:${VERSION} \
     --set imageBuilder.predictionJobBaseImages."3\.7\.*".buildContextURI=git://github.com/caraml-dev/merlin.git#${GIT_REF} \
@@ -48,6 +48,8 @@ install_merlin() {
     --set imageBuilder.predictionJobBaseImages."3\.10\.*".mainAppPath=/home/spark/merlin-spark-app/main.py \
     --set ingress.host=merlin.caraml.${INGRESS_HOST} \
     --set mlflow.ingress.host=merlin-mlflow.caraml.${INGRESS_HOST} \
+    --set mlflow.image.repository=caraml-dev/mlflow \
+    --set mlflow.image.tag=1.26.1 \
     --set mlp.deployment.apiHost=http://mlp.caraml.${INGRESS_HOST}/v1 \
     --set mlp.deployment.mlflowTrackingUrl=http://merlin-mlflow.caraml.${INGRESS_HOST} \
     --set mlp.ingress.host=mlp.caraml.${INGRESS_HOST} \

scripts/e2e/setup-and-run-e2e.sh

@@ -8,7 +8,7 @@ export LOCAL_REGISTRY=dev.localhost
 export DOCKER_REGISTRY=${LOCAL_REGISTRY}:${LOCAL_REGISTRY_PORT}
 export VERSION=test-local
 export MLP_CHART_VERSION=0.4.18
-export MERLIN_CHART_VERSION=0.11.1
+export MERLIN_CHART_VERSION=0.13.18
 
 
 # Create k3d cluster and managed registry

scripts/e2e/setup-cluster.sh

@@ -103,6 +103,12 @@ install_knative() {
     kubectl rollout status deployment/domainmapping-webhook -n knative-serving -w --timeout=${TIMEOUT}
     kubectl rollout status deployment/webhook -n knative-serving -w --timeout=${TIMEOUT}
 
+    # Update knative config-deployment config map to allow resolving of the local e2e image repository
+    kubectl get configmap -n knative-serving config-deployment -o yaml > temp.yaml
+    yq -i '.data.registries-skipping-tag-resolving |= ("\(.),${DOCKER_REGISTRY}" | envsubst)' temp.yaml
+    kubectl apply -f temp.yaml
+    kubectl rollout restart deployment -n knative-serving controller
+
     # Install knative-istio
     kubectl apply -f https://github.com/knative-sandbox/net-istio/releases/download/knative-v${KNATIVE_NET_ISTIO_VERSION}/net-istio.yaml
 

scripts/quick_install.sh

@@ -12,7 +12,7 @@ export INGRESS_HOST=$(kubectl -n istio-system get service istio-ingressgateway -
 export DOCKER_REGISTRY=ghcr.io/caraml-dev
 export VERSION=0.33.0
 export GIT_REF=v0.33.0
-export MERLIN_CHART_VERSION=0.11.7
+export MERLIN_CHART_VERSION=0.13.18
 export OAUTH_CLIENT_ID=""
 
 cd e2e; ./deploy-merlin.sh $INGRESS_HOST $DOCKER_REGISTRY $VERSION $GIT_REF $MERLIN_CHART_VERSION $OAUTH_CLIENT_ID