Update README.md

.env

@@ -1,5 +1,5 @@
-AWS_ACCESS_KEY_ID=AKIAIOSFODNN7EXAMPLE
+AWS_ACCESS_KEY_ID=admin
-AWS_SECRET_ACCESS_KEY=wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY
+AWS_SECRET_ACCESS_KEY=sample_key
 AWS_REGION=us-east-1
 AWS_BUCKET_NAME=mlflow
 MYSQL_DATABASE=mlflow

Caddyfile

@@ -1,22 +0,0 @@
-# Minio Console
-s3.localhost:9001 {
-    handle_path /* {
-        reverse_proxy s3:9001
-    }
-}
-
-# Minio API
-s3.localhost:9000 {
-    handle_path /* {
-        reverse_proxy s3:9000
-    }
-}
-
-mlflow.localhost {
-    basicauth /* {
-	    root JDJhJDEwJEVCNmdaNEg2Ti5iejRMYkF3MFZhZ3VtV3E1SzBWZEZ5Q3VWc0tzOEJwZE9TaFlZdEVkZDhX # root hiccup
-    }
-    handle_path /* {
-        reverse_proxy mlflow:5000
-    }
-}

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2020 Tomasz Dłuski
+Copyright (c) 2021 Tomasz Dłuski
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,86 +1,32 @@
 # MLFlow Docker Setup [![Actions Status](https://github.com/Toumash/mlflow-docker/workflows/VerifyDockerCompose/badge.svg)](https://github.com/Toumash/mlflow-docker/actions)
 
-If you want to boot up mlflow project with one-liner - this repo is for you. 
+> If you want to boot up mlflow project with one-liner - this repo is for you. 
+> The only requirement is docker installed on your system and we are going to use Bash on linux/windows.
 
-The only requirement is docker installed on your system and we are going to use Bash on linux/windows.
+# 🚀 1-2-3! Setup guide 
+1. Configure `.env` file for your choice. You can put there anything you like, it will be used to configure you services
+2. Run `docker compose up`
+3. Open up http://localhost:5000 for MlFlow, and http://localhost:9001/ to browse your files in S3 artifact store
 
-[![Youtube tutorial](https://img.youtube.com/vi/ma5lA19IJRA/0.jpg)](https://www.youtube.com/watch?v=ma5lA19IJRA)
+
+**👇Video tutorial how to set it up on Microsoft Azure 👇**
+
+[![Youtube tutorial](https://user-images.githubusercontent.com/9840635/144674240-f1ede224-410a-4b77-a7b8-450f45cc79ba.png)](https://www.youtube.com/watch?v=ma5lA19IJRA)
 
 # Features
- - Setup by one file (.env)
+ - One file setup (.env)
- - Production-ready docker volumes
+ - Minio S3 artifact store with GUI
- - Separate artifacts and data containers
+ - MySql mlflow storage
- - [Artifacts GUI](https://min.io/)
+ - Ready to use bash scripts for python development!
- - Ready bash scripts to copy and paste for colleagues to use your server!
+ - Automatically-created s3 buckets
 
 
-## Simple setup guide
+## How to use in ML development in python
-1. Configure `.env` file for your choice. You can put there anything you like, it will be used to configure you services
 
-2. Run the Infrastructure by this one line:
+<details>
-```shell
+<summary>Click to show</summary>
-$ docker-compose up -d
-Creating network "mlflow-basis_A" with driver "bridge"
-Creating mlflow_db      ... done
-Creating tracker_mlflow ... done
-Creating aws-s3         ... done
-```
 
-3. Create mlflow bucket. You can use my bundled script.
+1. Configure your client-side
-
-Just run 
-```shell 
-bash ./run_create_bucket.sh
-```
-
-You can also do it **either using AWS CLI or Python Api**.
-<details><summary>AWS CLI</summary>
-
-1. [Install AWS cli](https://aws.amazon.com/cli/) **Yes, i know that you dont have an Amazon Web Services Subscription - dont worry! It wont be needed!**
-2. Configure AWS CLI - enter the same credentials from the `.env` file
-
-```shell
-aws configure
-```
-> AWS Access Key ID [****************123]: AKIAIOSFODNN7EXAMPLE  
-> AWS Secret Access Key [****************123]: wJalrXUtnFEMI/K7MDENG/bPxRfiCYEXAMPLEKEY  
-> Default region name [us-west-2]: us-east-1  
-> Default output format [json]: <ENTER>  
-
-3. Run
-```shell
-aws --endpoint-url=http://localhost:9000 s3 mb s3://mlflow
-```
-
-</details>
-
-<details><summary>Python API</summary>
-
-1. Install Minio
-```shell
-pip install Minio
-```
-2. Run this to create a bucket
-```python
-from minio import Minio
-from minio.error import ResponseError
-
-s3Client = Minio(
-    'localhost:9000',
-    access_key='<YOUR_AWS_ACCESSS_ID>', # copy from .env file
-    secret_key='<YOUR_AWS_SECRET_ACCESS_KEY>', # copy from .env file
-    secure=False
-)
-s3Client.make_bucket('mlflow')
-```
-
-</details>
-
----
-
-4. Open up http://localhost:5000 for MlFlow, and http://localhost:9000/minio/mlflow/ for S3 bucket (you artifacts) with credentials from `.env` file
-
-5. Configure your client-side
 
 For running mlflow files you need various environment variables set on the client side. To generate them user the convienience script `./bashrc_install.sh`, which installs it on your system or `./bashrc_generate.sh`, which just displays the config to copy & paste.
 
@@ -89,7 +35,7 @@ For running mlflow files you need various environment variables set on the clien
 
 The script installs this variables: AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, MLFLOW_S3_ENDPOINT_URL, MLFLOW_TRACKING_URI. All of them are needed to use mlflow from the client-side.
 
-6. Test the pipeline with below command with conda. If you dont have conda installed run with `--no-conda`
+2. Test the pipeline with below command with conda. If you dont have conda installed run with `--no-conda`
 
 ```shell
 mlflow run git@github.com:databricks/mlflow-example.git -P alpha=0.5
@@ -97,8 +43,16 @@ mlflow run git@github.com:databricks/mlflow-example.git -P alpha=0.5
 python ./quickstart/mlflow_tracking.py
 ```
 
-7. *(Optional)* If you are constantly switching your environment you can use this environment variable syntax
+3. *(Optional)* If you are constantly switching your environment you can use this environment variable syntax
 
 ```shell
 MLFLOW_S3_ENDPOINT_URL=http://localhost:9000 MLFLOW_TRACKING_URI=http://localhost:5000 mlflow run git@github.com:databricks/mlflow-example.git -P alpha=0.5
 ```
+
+</details>
+ 
+
+## Licensing
+Copyright (c) 2021 Tomasz Dłuski
+
+Licensed under the MIT License (the "License"); you may not use this file except in compliance with the License. You may obtain a copy of the License by reviewing the file [LICENSE](./LICENSE) in the repository.

docker-compose.yml

@@ -1,38 +1,23 @@
-version: '3.2'
+version: "3.9"
 services:
-  caddy:
-    image: caddy:2-alpine
-    container_name: caddy
-    volumes:
-      - ./Caddyfile:/etc/caddy/Caddyfile
-      - /caddy/data:/data
-      - /caddy/config:/config
-    ports:
-      - 80:80
-      - 443:443
-      - 9000:9000
-      - 9001:9001
-    restart: unless-stopped
   s3:
-    restart: always
+    image:  minio/minio:RELEASE.2021-11-24T23-19-33Z
-    image: minio/minio:latest
+    restart: unless-stopped
-    container_name: aws-s3
     ports:
-      - 9000
+      - "9000:9000"
-      - 9001
+      - "9001:9001"
     environment:
       - MINIO_ROOT_USER=${AWS_ACCESS_KEY_ID}
       - MINIO_ROOT_PASSWORD=${AWS_SECRET_ACCESS_KEY}
-    command:
+    command: server /data --console-address ":9001"
-      server /date --console-address ":9001"
-    volumes:
-      - ./s3:/date
     networks:
-      - default
+      - internal
-      - proxy-net
+      - public
+    volumes:
+      - minio_volume:/data
   db:
-      restart: always
     image: mysql/mysql-server:5.7.28
+    restart: unless-stopped
     container_name: mlflow_db
     expose:
       - "3306"
@@ -42,13 +27,13 @@ services:
       - MYSQL_PASSWORD=${MYSQL_PASSWORD}
       - MYSQL_ROOT_PASSWORD=${MYSQL_ROOT_PASSWORD}
     volumes:
-          - ./dbdata:/var/lib/mysql
+      - db_volume:/var/lib/mysql
     networks:
-          - default
+      - internal
   mlflow:
-      restart: always
     container_name: tracker_mlflow
     image: tracker_ml
+    restart: unless-stopped
     build:
       context: ./mlflow
       dockerfile: Dockerfile
@@ -59,11 +44,26 @@ services:
       - AWS_SECRET_ACCESS_KEY=${AWS_SECRET_ACCESS_KEY}
       - AWS_DEFAULT_REGION=${AWS_REGION}
       - MLFLOW_S3_ENDPOINT_URL=http://s3:9000
-      entrypoint: mlflow server --backend-store-uri mysql+pymysql://${MYSQL_USER}:${MYSQL_PASSWORD}@db:3306/${MYSQL_DATABASE} --default-artifact-root s3://${AWS_BUCKET_NAME}/ -h 0.0.0.0
     networks:
-          - proxy-net
+      - public
-          - default
+      - internal
-
+    entrypoint: bash ./wait-for-it.sh db:3306 -t 90 -- mlflow server --backend-store-uri mysql+pymysql://${MYSQL_USER}:${MYSQL_PASSWORD}@db:3306/${MYSQL_DATABASE} --default-artifact-root s3://${AWS_BUCKET_NAME}/ -h 0.0.0.0
+  create_s3_buckets:
+    image: minio/mc
+    depends_on:
+      - "s3"
+    entrypoint: >
+      /bin/sh -c "
+      until (/usr/bin/mc alias set minio http://s3:9000 '${AWS_ACCESS_KEY_ID}' '${AWS_SECRET_ACCESS_KEY}') do echo '...waiting...' && sleep 1; done;
+      /usr/bin/mc mb minio/mlflow;
+      exit 0;
+      "
+    networks:
+      - internal
 networks:
-  default:
+  internal:
-  proxy-net:
+  public:
+    driver: bridge
+volumes:
+  db_volume:
+  minio_volume:

mlflow/Dockerfile

@@ -1,10 +1,10 @@
 FROM continuumio/miniconda3:latest
 
+RUN pip install mlflow boto3 pymysql
+
 ADD . /app
 WORKDIR /app
 
 COPY wait-for-it.sh wait-for-it.sh 
 RUN chmod +x wait-for-it.sh
 
-RUN pip install mlflow boto3 pymysql
-

quickstart/mlflow_tracking.py

@@ -5,7 +5,7 @@ from mlflow import mlflow,log_metric, log_param, log_artifacts
 
 if __name__ == "__main__":
     with mlflow.start_run() as run:
-        mlflow.set_tracking_uri('https://mlflow.localhost')
+        mlflow.set_tracking_uri('http://localhost:5000')
         print("Running mlflow_tracking.py")
 
         log_param("param1", randint(0, 100))