Installation & Setup

# Basic installation
pip install mlflow

# With specific extras
pip install mlflow[extras]          # Includes scikit-learn, boto3, etc.
pip install mlflow[gateway]         # For MLflow AI Gateway (LLM support)

# Verify installation
mlflow --version
python -c "import mlflow; print(mlflow.__version__)"

# Start with default settings (SQLite backend, local artifacts)
mlflow server --host 127.0.0.1 --port 5000

# Or simply use the UI command
mlflow ui --port 5000

# Access the UI at http://127.0.0.1:5000

# Install PostgreSQL driver
pip install psycopg2-binary

# Start server with PostgreSQL backend
mlflow server \
  --backend-store-uri postgresql://user:password@localhost:5432/mlflow \
  --default-artifact-root s3://my-mlflow-bucket/artifacts \
  --host 0.0.0.0 \
  --port 5000

# Local filesystem (default)
--default-artifact-root ./mlruns

# Amazon S3
--default-artifact-root s3://my-bucket/mlflow-artifacts

# Google Cloud Storage
--default-artifact-root gs://my-bucket/mlflow-artifacts

# Azure Blob Storage
--default-artifact-root wasbs://container@account.blob.core.windows.net/mlflow

# HDFS
--default-artifact-root hdfs://namenode:8020/mlflow

FROM python:3.11-slim

RUN pip install mlflow psycopg2-binary boto3

EXPOSE 5000

CMD ["mlflow", "server", \
     "--backend-store-uri", "postgresql://user:pass@db:5432/mlflow", \
     "--default-artifact-root", "s3://mlflow-artifacts", \
     "--host", "0.0.0.0", \
     "--port", "5000"]

version: '3.8'
services:
  db:
    image: postgres:15
    environment:
      POSTGRES_USER: mlflow
      POSTGRES_PASSWORD: mlflow
      POSTGRES_DB: mlflow
    volumes:
      - postgres_data:/var/lib/postgresql/data

  mlflow:
    build: .
    ports:
      - "5000:5000"
    depends_on:
      - db
    environment:
      - AWS_ACCESS_KEY_ID=${AWS_ACCESS_KEY_ID}
      - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}

volumes:
  postgres_data:

import mlflow
from sklearn.datasets import load_iris
from sklearn.ensemble import RandomForestClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score

# Point to tracking server (optional if running locally)
mlflow.set_tracking_uri("http://127.0.0.1:5000")

# Create or set experiment
mlflow.set_experiment("my-first-experiment")

# Load data
iris = load_iris()
X_train, X_test, y_train, y_test = train_test_split(
    iris.data, iris.target, test_size=0.2, random_state=42
)

# Start a run
with mlflow.start_run(run_name="first-run"):
    # Log parameters
    n_estimators = 100
    mlflow.log_param("n_estimators", n_estimators)
    mlflow.log_param("random_state", 42)

    # Train model
    model = RandomForestClassifier(n_estimators=n_estimators, random_state=42)
    model.fit(X_train, y_train)

    # Log metrics
    accuracy = accuracy_score(y_test, model.predict(X_test))
    mlflow.log_metric("accuracy", accuracy)

    # Log model
    mlflow.sklearn.log_model(model, "model")

    print(f"Accuracy: {accuracy:.4f}")
    print(f"Run ID: {mlflow.active_run().info.run_id}")