Merge branch 'master' into feature/l3t3-format-benchmark

.dvc/.gitignore

@@ -0,0 +1,3 @@
+/config.local
+/tmp
+/cache

.dvc/config

@@ -0,0 +1,5 @@
+[core]
+    remote = minio
+['remote "minio"']
+    url = s3://ml-data
+    endpointurl = http://10.0.0.6:9000

.dvcignore

@@ -0,0 +1,3 @@
+# Add patterns of files dvc should ignore, which could improve
+# the performance. Learn more at
+# https://dvc.org/doc/user-guide/dvcignore

.github/workflows/ci.yml

@@ -2,6 +2,8 @@ name: Deploy Image to Docker Hub
 
 env:
   APP_NAME: 'prjctr'
+  STREAMLIT_NAME: 'app-streamlit'
+  FASTAPI_NAME: 'app-fastapi'
 
 on:
   push:
@@ -11,7 +13,31 @@ on:
   workflow_dispatch:
 
 jobs:
+  tests:
+    runs-on: ubuntu-latest
+    steps:
+      - name: 'Checkout GitHub Action'
+        uses: actions/checkout@main
+
+      - name: 'Set up Python'
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.8'
+
+      - name: 'Install dependencies'
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r app/requirements-dev.txt
+
+      - name: 'Run pytest'
+        run: |
+          cd app/
+          pytest tests/
+        env:
+          PYTHONPATH: '.'
+
   push-image:
+    needs: tests
     runs-on: ubuntu-latest
     steps:
       - name: 'Checkout GitHub Action'
@@ -28,3 +54,12 @@ jobs:
         run: |
           docker build . --tag docker.io/${{ secrets.DH_USERNAME }}/$APP_NAME:latest
           docker push docker.io/${{ secrets.DH_USERNAME }}/$APP_NAME:latest
+      - name: 'Build & Push Image streamlit'
+        run: |
+          docker build . --tag docker.io/${{ secrets.DH_USERNAME }}/$STREAMLIT_NAME:latest
+          docker push docker.io/${{ secrets.DH_USERNAME }}/$STREAMLIT_NAME:latest
+      - name: 'Build & Push Image fastapi'
+        run: |
+          docker build . --tag docker.io/${{ secrets.DH_USERNAME }}/$FASTAPI_NAME:latest
+          docker push docker.io/${{ secrets.DH_USERNAME }}/$FASTAPI_NAME:latest
+

Dockerfile

@@ -1,12 +1,38 @@
-FROM python:3.12-slim as builder
+FROM python:3.11-slim as builder
 
 WORKDIR /app
 
 COPY app/requirements.txt .
 RUN pip install -r requirements.txt
 
-FROM builder
+FROM builder AS app-flask
 
 COPY app .
 CMD ["gunicorn", "--bind", "0.0.0.0:8000", "app:app"]
 EXPOSE 8000
+
+FROM builder AS app-streamlit
+CMD streamlit run --server.address 0.0.0.0 --server.port 8080 src/serving/streamlit.py
+
+
+FROM builder AS app-fastapi
+CMD uvicorn --host 0.0.0.0 --port 8090 --workers 4 src.serving.fastapi:app 
+
+FROM builder AS app-seldon
+EXPOSE 5000
+EXPOSE 9000
+ENV MODEL_NAME SeldonAPI
+ENV SERVICE_TYPE MODEL
+COPY app/src/serving/seldon.py /app/SeldonAPI.py
+
+RUN chown -R 8888 /app
+RUN mkdir /.cache
+RUN chmod 777 /.cache
+RUN mkdir /.config
+RUN chmod 777 /.config
+
+CMD exec seldon-core-microservice $MODEL_NAME --service-type $SERVICE_TYPE
+
+
+FROM builder AS app-kserve
+ENTRYPOINT ["python", "app/src/serving/kserve.py"]

README.md

@@ -23,6 +23,131 @@ Works on push to master/feature*
 ![Alt text](assets/actions.png)
 
 
+### Streamlit 
+
+Run:
+```
+streamlit run src/serving/streamlit.py
+```
+
+![Alt text](assets/streamlit.png)
+
+Deploy k8s:
+```
+kubectl create -f deployment/app-ui.yml
+kubectl port-forward --address 0.0.0.0 svc/app-ui.yml 8080:8080
+```
+
+Deploy k8s:
+```
+kubectl create -f deployment/app-ui.yml
+kubectl port-forward --address 0.0.0.0 svc/app-ui.yml 8080:8080
+```
+
+
+### Fast API 
+
+Postman
+
+![Alt text](assets/fastapi.png)
+
+
+
+Deploy k8s:
+```
+kubectl create -f deployment/app-fasttext.yml
+kubectl port-forward --address 0.0.0.0 svc/app-fasttext 8090:8090
+```
+
+### Seldon
+
+Instalation
+
+```
+kubectl apply -f https://github.com/datawire/ambassador-operator/releases/latest/download/ambassador-operator-crds.yaml
+kubectl apply -n ambassador -f https://github.com/datawire/ambassador-operator/releases/latest/download/ambassador-operator-kind.yaml
+kubectl wait --timeout=180s -n ambassador --for=condition=deployed ambassadorinstallations/ambassador
+
+kubectl create namespace seldon-system
+
+helm install seldon-core seldon-core-operator --version 1.15.1 --repo https://storage.googleapis.com/seldon-charts --set usageMetrics.enabled=true --set ambassador.enabled=true  --namespace seldon-system
+```
+
+Deploy k8s:
+```
+kubectl create -f deployment/seldon-custom.yaml
+```
+
+### Kserve
+
+Deploy k8s:
+
+```
+kubectl create -f deployment/kserve.yaml
+kubectl get inferenceservice custom-model
+```
+
+
+### Load testing
+
+![Alt text](assets/locust.png)
+
+```
+locust -f benchmarks/load_test.py --host=http://localhost:9933 --users 50 --spawn-rate 10 --autostart --run-time 600s
+
+### DVC
+
+Install DVC
+
+```
+brew install dvc
+```
+
+Init in repo
+
+```
+dvc init --subdir
+git status
+git commit -m "init DVC"
+```
+
+Move file with data and add to DVC, commit DBV data config
+
+```
+dvc add ./data/data.csv
+git add data/.gitignore data/data.csv.dvc
+git commit -m "create data"
+```
+
+Add remote data storage and push DVC remote config
+(ensure that bucket already created)
+
+```
+dvc remote add -d minio s3://ml-data
+dvc remote modify minio endpointurl [$AWS_ENDPOINT](http://10.0.0.6:9000)
+
+git add .dvc/config
+git commit -m "configure remote"
+git push 
+```
+
+Upload data
+```
+export AWS_ACCESS_KEY_ID='...'
+export AWS_SECRET_ACCESS_KEY='...'
+dvc push
+
+
+### Label studio
+
+```
+docker pull heartexlabs/label-studio:latest
+docker run -it -p 8080:8080 -v `pwd`/mydata:/label-studio/data heartexlabs/label-studio:latest
+```
+
+![Alt text](assets/labeling.png)
+
+
 ### Minio setup
 Mac/Local
 ```
@@ -78,3 +203,79 @@ JSON format demonstrates faster write times but slower read times compared to ot
 PARQUET format showcases the fastest write times and relatively fast read times, with a smaller file size after write compared to CSV and JSON.
 
 ORC format exhibits moderate write times and the smallest file size after write among the tested formats, with efficient read times.
+=======
+### POD autoscaling
+
+Install metric service
+
+```
+kubectl apply -f https://github.com/kubernetes-sigs/metrics-server/releases/latest/download/components.yaml
+kubectl patch -n kube-system deployment metrics-server --type=json -p '[{"op":"add","path":"/spec/template/spec/containers/0/args/-","value":"--kubelet-insecure-tls"}]'
+```
+
+Run from config
+
+```
+kubectl create -f deployment/app-fastapi-scaling.yml
+```
+
+
+### Model optimization
+
+Run pruning:
+
+```
+python -m src.model.pruning
+```
+
+Run distilation:
+
+```
+python -m src.model.distilation
+```
+
+### Kafka
+
+Install kafka
+```
+helm repo add bitnami https://charts.bitnami.com/bitnami
+helm install zookeeper bitnami/zookeeper --set replicaCount=1 --set auth.enabled=false --set allowAnonymousLogin=true --set persistance.enabled=false --version 11.0.0
+helm install kafka bitnami/kafka --set zookeeper.enabled=false --set replicaCount=1 --set persistance.enabled=false
+
+
+# eventing
+kubectl apply -f https://github.com/knative/eventing/releases/download/knative-v1.9.7/eventing-crds.yaml
+kubectl apply -f https://github.com/knative/eventing/releases/download/knative-v1.9.7/eventing-core.yaml
+kubectl apply -f https://github.com/knative-sandbox/eventing-kafka/releases/download/knative-v1.9.1/source.yaml
+```
+
+Run deployment
+
+```
+kubectl apply -f deployment/kafka-infra.yml
+
+kubectl port-forward $(kubectl get pod --selector="app=minio" --output jsonpath='{.items[0].metadata.name}') 9000:9000
+
+mc config host add myminio http://127.0.0.1:9000 miniominio miniominio
+
+mc mb myminio/input
+mc mb myminio/output
+
+mc admin config set myminio notify_kafka:1 tls_skip_verify="off"  queue_dir="" queue_limit="0" sasl="off" sasl_password="" sasl_username="" tls_client_auth="0" tls="off" client_tls_cert="" client_tls_key="" brokers="kafka-headless.default.svc.cluster.local:9092" topic="test" version=""
+
+
+mc admin service restart myminio
+mc event add myminio/input arn:minio:sqs::1:kafka -p --event put --suffix .json
+
+kubectl create -f deployment/kafka-infra.yml
+
+
+```
+
+### Data drift detetion
+
+```
+python -m src.monitoring.drift
+```
+
+![Alt text](assets/drift.png)

app/requirements-dev.txt

@@ -3,3 +3,16 @@ pytest==7.4.4
 pytest-mock==3.12.0
 datasets==2.16.1
 pandas==2.1.4
+evaluate==0.4.1
+great-expectations==0.18.7
+pytest==7.4.4
+scikit-learn==1.3.2
+accelerate==0.25.0
+datasets==2.16.1
+wandb==0.16.1
+httpx==0.23.0
+locust==2.20.1
+textpruner==1.1.post2
+evidently==0.4.13
+sentence_transformers==2.2.2
+ipykernel==6.28.0

app/requirements.txt

@@ -2,4 +2,9 @@ flask==3.0.0
 gunicorn==21.2.0
 boto3==1.34.12
 botocore==1.34.12
-
+transformers==4.36.2
+streamlit==1.29.0
+fastapi>=0.95.0
+uvicorn>=0.22.0
+# kserve==0.11.2
+protobuf==3.20.1

app/src/helpers/wandb_registry.py

@@ -0,0 +1,15 @@
+from pathlib import Path
+import wandb
+
+def publish_model(model_path: str, project: str, name: str, model_type: str = "model"):
+    with wandb.init(project=project, job_type="model-publishing") as run:
+        artifact = wandb.Artifact(name, type=model_type)
+        artifact.add_dir(model_path)
+        run.log_artifact(artifact)
+    print(f"Published {name} to W&B")
+
+def download_model(model_name: str, project: str, download_path: Path, model_type: str = "model"):
+    with wandb.init(project=project) as run:
+        artifact = run.use_artifact(model_name, type=model_type)
+        artifact_dir = artifact.download(root=download_path)
+        print(f"Downloaded {model_name} to {artifact_dir}")