Adding documentation in Examples folder

examples/README.md

@@ -0,0 +1,39 @@
+# EXAMPLES
+
+In this folder, you will find use cases referenced in the playlist to illustrate specific topics. These examples are based on public datasets and, while they may not always reflect real-world scenarios, they are designed to demonstrate particular aspects of the ML lifecycle.
+
+**Notebooks**
+
+Notebooks under `mlflow_for_ml_dev/notebooks/local_model_serving/` are used to demonstrate how to make the API requests in an interactive way.
+
+## Iris Classifier
+
+This example uses the classic Iris dataset, which is included in the scikit-learn package. The dataset provides a simple, well-known classification problem, making it ideal for demonstrating machine learning workflows.
+
+* package: `examples/iris_classifier`
+
+* dataset source: [sklearn load_iris method](https://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html)
+
+
+* Associated inference notebook:
+`mlflow_for_ml_dev/noteboks/local_model_serving/deploying_local_iris_model.ipynb`
+
+### Entrypoints available: 
+
+* `iris_clf_train ="examples.iris_classifier.train:main"`
+Trains the model and register it in the Model registry with name **Iris_Classifier_Model**, The model is set with alias **production** 
+
+* `iris_clf_inference = "examples.iris_classifier.inference:main"`
+Performs batch inference.
+
+* `iris_clf_online_inference="examples.iris_classifier.online_inference:main"`
+Performs online inference. Before running this script, ensure that the model has been trained and registered (for example, using the `iris_clf_train` script). Next, deploy the model locally by executing:
+
+```
+poetry run mlflow models serve -m models:/Iris_Classifier_Model@production --env-manager local
+```
+
+
+
+
+

examples/iris_classifier/online_inference.py

@@ -43,7 +43,7 @@ def main() -> None:
     Perform online inference using a REST API.
 
     To deploy the model in the local server, run the following command:
-    `poetry run mlflow models serve -m models:/Iris_Classifier_Model@production --no-conda`
+    `poetry run mlflow models serve -m models:/Iris_Classifier_Model@production --env-manager local`
 
     """
     payload, labels = get_payload(1)

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "mlflow_for_ml_dev"
-version = "1.4.0"
+version = "1.4.1"
 description = "Code examples for the youtube playlist 'MLflow for Machine Learning Development' by Manuel Gil"
 authors = ["Manuel Gil <[email protected]>"]
 readme = "README.md"