Merge pull request #141 from ORNL/dev

Main < Dev

.github/workflows/create-release-n-publish.yml

@@ -97,30 +97,22 @@ jobs:
         run: pip install flowcept[dask]
       - name: Test pip install multiple adapters
         run: pip install flowcept[mlflow,tensorboard]
-      - name: Test pip install full
-        run: pip install flowcept[full]
-      - name: Install dev dependencies
-        run: |
-          pip install -r extra_requirements/dev-requirements.txt
+      - name: Install our dependencies
+        run: pip install -e .[fulldev]  # This will install all dependencies, for all adapters and dev deps.
+      - name: Pip list
+        run: pip list      
       - name: Run Docker Compose
-        run: docker compose -f deployment/compose.yml up -d
-      - name: Copy settings
+        run: docker compose -f deployment/compose-full.yml up -d
+      - name: Test with pytest
         run: |
           mkdir -p ~/.flowcept
           cp resources/sample_settings.yaml ~/.flowcept/settings.yaml
           export FLOWCEPT_SETTINGS_PATH=~/.flowcept/settings.yaml
-      - name: Test with pytest
-        run: |
-          export FLOWCEPT_SETTINGS_PATH=~/.flowcept/settings.yaml
           cat $FLOWCEPT_SETTINGS_PATH
           pytest --ignore=tests/decorator_tests/ml_tests/llm_tests
       - name: Test notebooks
         run: |
-          pip install flowcept[full]
-          pip install -r extra_requirements/dev-requirements.txt
-          pip list | grep flowcept
           export FLOWCEPT_SETTINGS_PATH=~/.flowcept/settings.yaml
-          cat $FLOWCEPT_SETTINGS_PATH
           python flowcept/flowcept_webserver/app.py &
           sleep 3
           pytest --nbmake "notebooks/" --nbmake-timeout=600 --ignore=notebooks/dask_from_CLI.ipynb

.github/workflows/run-tests-kafka.yml

@@ -0,0 +1,54 @@
+name: All tests on Kafka MQ
+on:
+  pull_request:
+    branches: [ "dev", "main" ]
+    types: [opened, synchronize, reopened]
+# branches: [ "disabled" ]
+
+jobs:
+
+  build:
+    runs-on: ubuntu-latest
+    timeout-minutes: 60
+    if: "!contains(github.event.head_commit.message, 'CI Bot')"
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python 3.9
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.9"
+    - name: Check python version
+      run: python --version
+    - name: Install our dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip install -e .[fulldev]
+    - name: Pip list
+      run: pip list
+    - name: Run Docker Compose
+      run: docker compose -f deployment/compose-kafka.yml up -d
+    - name: Wait 1 min
+      run: sleep 60
+    - name: Check liveness
+      run: |
+        export MQ_TYPE=kafka
+        export MQ_PORT=9092
+        python -c 'from flowcept.configs import MQ_TYPE, MQ_PORT; print(f"MQ_TYPE={MQ_TYPE}"); print(f"MQ_TYPE={MQ_PORT}")'
+        python -c 'from flowcept import Flowcept; assert Flowcept.services_alive()'
+    - name: Run Tests with Kafka
+      run: |
+        export MQ_TYPE=kafka
+        export MQ_PORT=9092
+        pytest --ignore=tests/decorator_tests/ml_tests/llm_tests
+    - name: Test notebooks
+      run: |
+        pip install -e .[full]
+        export MQ_TYPE=kafka
+        export MQ_PORT=9092
+        python -c 'from flowcept.configs import MQ_TYPE, MQ_PORT; print(f"MQ_TYPE={MQ_TYPE}"); print(f"MQ_TYPE={MQ_PORT}")'
+        python -c 'from flowcept import Flowcept; assert Flowcept.services_alive()'
+        
+        python flowcept/flowcept_webserver/app.py &
+        sleep 3
+        export FLOWCEPT_SETTINGS_PATH=~/.flowcept/settings.yaml
+        pytest --ignore=notebooks/zambeze.ipynb --nbmake "notebooks/" --nbmake-timeout=600 --ignore=notebooks/dask_from_CLI.ipynb

.github/workflows/run-tests.yml

@@ -19,17 +19,36 @@ jobs:
     - name: Install our dependencies
       run: |
         python -m pip install --upgrade pip
-        pip install -e .[full]
-        pip install -r extra_requirements/dev-requirements.txt
-    - name: Run Docker Compose
-      run: docker compose -f deployment/compose.yml up -d
-    - name: Test with pytest
+        pip install -e .[fulldev]  # This will install all dependencies, for all adapters and dev deps.
+    - name: Pip list
+      run: pip list
+    - name: Start Docker Compose  with Redis
+      run: docker compose -f deployment/compose-full.yml up -d
+    - name: Test with pytest with Redis
       run: |
         pytest --ignore=tests/decorator_tests/ml_tests/llm_tests
-    - name: Test notebooks
+    - name: Test notebooks with Redis
       run: |
         pip install -e .
         python flowcept/flowcept_webserver/app.py &
         sleep 3
         export FLOWCEPT_SETTINGS_PATH=~/.flowcept/settings.yaml
         pytest --nbmake "notebooks/" --nbmake-timeout=600 --ignore=notebooks/dask_from_CLI.ipynb
+    - name: Shut down compose
+      run: docker compose -f deployment/compose-full.yml down
+    - name: Start Docker Compose with Kafka
+      run: docker compose -f deployment/compose-kafka.yml up -d
+    - name: Wait 1 min
+      run: sleep 60
+    - name: Check liveness
+      run: |
+        export MQ_TYPE=kafka
+        export MQ_PORT=9092
+        python -c 'from flowcept.configs import MQ_TYPE, MQ_PORT; print(f"MQ_TYPE={MQ_TYPE}"); print(f"MQ_TYPE={MQ_PORT}")'
+        python -c 'from flowcept import Flowcept; assert Flowcept.services_alive()'
+    - name: Run Tests with Kafka
+      run: |
+        export MQ_TYPE=kafka
+        export MQ_PORT=9092
+        # Ignoring heavy tests. They are executed with Kafka in another GH Action. 
+        pytest --ignore=tests/decorator_tests/ml_tests --ignore=tests/adapters/test_tensorboard.py

.github/workflows/test-python-310-macos.yml

@@ -35,7 +35,7 @@ jobs:
     - name: Run Docker Compose
       run: |
         docker compose version
-        docker compose -f deployment/compose.yml up -d
+        docker compose -f deployment/compose-full.yml up -d
     - name: Test with pytest
       run: |
         pytest --ignore=tests/decorator_tests/ml_tests/llm_tests/

.github/workflows/test-python-310.yml

@@ -25,7 +25,7 @@ jobs:
         pip install -e .[full]
         pip install -r extra_requirements/dev-requirements.txt
     - name: Run Docker Compose
-      run: docker compose -f deployment/compose.yml up -d
+      run: docker compose -f deployment/compose-full.yml up -d
     - name: Test with pytest
       run: |
         pytest --ignore=tests/decorator_tests/ml_tests/llm_tests

.github/workflows/test-python-311.yml

@@ -28,7 +28,7 @@ jobs:
         pip install -e .[full]
         pip install -r extra_requirements/dev-requirements.txt
     - name: Run Docker Compose
-      run: docker compose -f deployment/compose.yml up -d
+      run: docker compose -f deployment/compose-full.yml up -d
     - name: Test with pytest
       run: |
         pytest --ignore=tests/decorator_tests/ml_tests/llm_tests/

README.md

@@ -52,6 +52,34 @@ You may need to set the environment variable `FLOWCEPT_SETTINGS_PATH` with the a
 
 5. To use FlowCept's Query API, see utilization examples in the notebooks.
 
+### Simple Example with Decorators Instrumentation
+
+In addition to existing adapters to Dask, MLFlow, and others (it's extensible for any system that generates data), FlowCept also offers instrumentation via @decorators. 
+
+```python 
+from flowcept import Flowcept, flowcept_task
+
+@flowcept_task
+def sum_one(n):
+    return n + 1
+
+
+@flowcept_task
+def mult_two(n):
+    return n * 2
+
+
+with Flowcept(workflow_name='test_workflow'):
+    n = 3
+    o1 = sum_one(n)
+    o2 = mult_two(o1)
+    print(o2)
+
+print(Flowcept.db.query(filter={"workflow_id": Flowcept.current_workflow_id}))
+```
+
+
+
 ## Performance Tuning for Performance Evaluation
 
 In the settings.yaml file, the following variables might impact interception performance:

deployment/compose-full.yml

@@ -0,0 +1,32 @@
+version: '3.8'
+name: flowcept
+services:
+  flowcept_redis:
+    container_name: flowcept_redis
+    image: redis
+    ports:
+      - 6379:6379
+
+  flowcept_mongo:
+    container_name: flowcept_mongo
+    image: mongo:latest
+    # volumes:
+    #   - /Users/rsr/Downloads/mongo_data/db:/data/db
+    ports:
+      - 27017:27017
+
+
+#   # This is just for the cases where one does not want to use the same Redis instance for caching and messaging, but
+#   # it's not required to have separate instances.
+# #  local_interceptor_cache:
+# #    container_name: local_interceptor_cache
+# #    image: redis
+# #    ports:
+# #      - 60379:6379
+
+  zambeze_rabbitmq:
+     container_name: zambeze_rabbitmq
+     image: rabbitmq:3.11-management
+     ports:
+       - 5672:5672
+       - 15672:15672

deployment/compose-kafka.yml

@@ -0,0 +1,57 @@
+version: '3.8'
+name: flowcept
+services:
+  flowcept_redis:
+    container_name: flowcept_redis
+    image: redis
+    ports:
+      - 6379:6379
+
+  flowcept_mongo:
+    container_name: flowcept_mongo
+    image: mongo:latest
+    # volumes:
+    #   - /Users/rsr/Downloads/mongo_data/db:/data/db
+    ports:
+      - 27017:27017
+
+  zookeeper:
+    image: confluentinc/cp-zookeeper:6.1.1
+    ports:
+      - "2181:2181"
+    environment:
+      ZOOKEEPER_CLIENT_PORT: 2181
+
+  # reachable on 9092 from the host and on 29092 from inside docker compose
+  kafka:
+    image: confluentinc/cp-kafka:6.1.1
+    depends_on:
+      - zookeeper
+    ports:
+      - '9092:9092'
+    expose:
+      - '29092'
+    environment:
+      KAFKA_ZOOKEEPER_CONNECT: 'zookeeper:2181'
+      KAFKA_LISTENER_SECURITY_PROTOCOL_MAP: PLAINTEXT:PLAINTEXT,PLAINTEXT_HOST:PLAINTEXT
+      KAFKA_INTER_BROKER_LISTENER_NAME: PLAINTEXT
+      KAFKA_ADVERTISED_LISTENERS: PLAINTEXT://kafka:29092,PLAINTEXT_HOST://localhost:9092
+      KAFKA_OFFSETS_TOPIC_REPLICATION_FACTOR: '1'
+      KAFKA_MIN_INSYNC_REPLICAS: '1'
+
+  init-kafka:
+    image: confluentinc/cp-kafka:6.1.1
+    depends_on:
+      - kafka
+    entrypoint: [ '/bin/sh', '-c' ]
+    command: |
+      "
+      # blocks until kafka is reachable
+      kafka-topics --bootstrap-server kafka:29092 --list
+
+      echo -e 'Creating kafka topics'
+      kafka-topics --bootstrap-server kafka:29092 --create --if-not-exists --topic interception --replication-factor 1 --partitions 1 
+      
+      echo -e 'Successfully created the following topics:'
+      kafka-topics --bootstrap-server kafka:29092 --list
+      "

deployment/compose.yml

@@ -16,6 +16,7 @@ services:
       - 27017:27017
 
 
+
 #   # This is just for the cases where one does not want to use the same Redis instance for caching and messaging, but
 #   # it's not required to have separate instances.
 # #  local_interceptor_cache:
@@ -24,9 +25,3 @@ services:
 # #    ports:
 # #      - 60379:6379
 
-  zambeze_rabbitmq:
-     container_name: zambeze_rabbitmq
-     image: rabbitmq:3.11-management
-     ports:
-       - 5672:5672
-       - 15672:15672

extra_requirements/dev-requirements.txt

@@ -1,11 +1,10 @@
 pytest==6.2.4
 flake8==5.0.4
 black==23.1.0
-numpy==1.23.4
+numpy<2.0.0
 bokeh==2.4.2
-jupyterlab==3.6.1
-nbmake==1.4
-cluster_experiment_utils
+jupyterlab
+nbmake
 # Pytorch models stuff:
 torch
 torchvision

extra_requirements/kafka-requirements.txt

@@ -0,0 +1 @@
+confluent-kafka==2.5.3

extra_requirements/mlflow-requirements.txt

@@ -1,4 +1,4 @@
-mlflow-skinny==2.1.1
+mlflow-skinny>2.1.1,<=2.16.2
 SQLAlchemy==1.4.42
 alembic==1.8.1
 watchdog==2.2.1

extra_requirements/tensorboard-requirements.txt

@@ -1,3 +1,3 @@
-tensorboard==2.13.0
-tensorflow==2.13.0
+tensorboard
+tensorflow
 tbparse==0.0.7

flowcept/__init__.py

@@ -1,12 +1,15 @@
 import flowcept
+
 from flowcept.configs import SETTINGS_PATH
+
 from flowcept.version import __version__
 
 from flowcept.commons.vocabulary import Vocabulary
 
-from flowcept.flowcept_api.consumer_api import FlowceptConsumerAPI
+
+from flowcept.flowcept_api.flowcept_controller import Flowcept
 from flowcept.flowcept_api.task_query_api import TaskQueryAPI
-from flowcept.flowcept_api.db_api import DBAPI
+from flowcept.instrumentation.decorators.flowcept_task import flowcept_task
 
 from flowcept.commons.flowcept_dataclasses.workflow_object import (
     WorkflowObject,

flowcept/analytics/data_augmentation.py

@@ -4,10 +4,12 @@
 import pandas as pd
 
 from h2o.automl import H2OAutoML
+from typing_extensions import deprecated
 
 h2o.init()
 
 
+@deprecated
 def train_model(
     df,
     x_cols: List[str],
@@ -26,6 +28,7 @@ def train_model(
     return aml
 
 
+@deprecated
 def augment_df_linearly(df, N, cols_to_augment, seed=1234):
     np.random.seed(seed)
     new_df = df.copy()
@@ -48,6 +51,7 @@ def augment_df_linearly(df, N, cols_to_augment, seed=1234):
     return appended_df
 
 
+@deprecated
 def augment_data(df, N, augmentation_model: H2OAutoML, x_cols, y_col):
     new_df = augment_df_linearly(df, N, x_cols)
     h2odf = h2o.H2OFrame(new_df.loc[new_df["original"] == 0][x_cols])