Consulting Services

A React + AWS Serverless full stack implementation of the example applications found in the official OpenAI API documentation. See this system architectural diagram for details. This is an instructional tool for the YouTube channel "Full Stack With Lawrence" and for University of British Columbia course, "Artificial Intelligence Cloud Technology Implementation".

Powered by Cookiecutter <https://github.com/cookiecutter/cookiecutter>, Cookiecutter Open edX Devops Tools is a community maintained project template for jumpstarting production-ready, Kubernetes <https://kubernetes.io/>-based installations of the Open edX <https://openedx.org/>_ online learning management system running on AWS <https://aws.amazon.com/>_ cloud infrastructure that is built and managed with fully parameterized Terraform <https://www.terraform.io/>_ and Github Actions <https://docs.github.com/en/actions>_ automation scripts. The template offers a number of generation options, we invite you to check the dedicated docs <https://github.com/cookiecutter-openedx/cookiecutter-openedx-devops/tree/main/doc>_ pages to learn more about each of them.

Smarter is used as an instructional tool at University of British Columbia for teaching AI. The Smarter Project is an open source, cloud-native platform and developer framework for building sophisticated AI applications without writing a single line of Python. An application that searches the web, queries your databases, calls your APIs, uses the tools of any MCP server, and defends itself against prompt injection and data leaks is described in one short YAML file, and deployed with one command:

smarter apply -f my-ai-application.yaml

Demonstrate basic usage of Azure Machine Learning's Automated ML service. Implements the following:

• AzureAIMLWorkspace: Azure AI ML Studio workspace helper class. generates an authenticated instance of a workspace.
• AzureAIMLAssetsDataset: Azure AI ML Studio data set. Provides helpers for managing ML Studio data sets, and for porting to/from kaggle data sets and local csv and Excel files.
• AzureAIMLStudioComputeCluster: Azure AI ML Studio Compute - compute cluster object with helpers for instantitation.
• AzureAIMLStudioAssetsBatchEndpoint: Azure AI ML Studio Assets - batch end point. Providers helpers for managing end points.
• AzureAIMLStudioAuthoringAutomatedML: Azure AI ML Studio Authoring - Automated ML. Helper class for managing life cycle of 'automated ml' jobs. There is also an example production deployment of a model created using AutomatedML. See important deployment details, here. Note the following:

1. Model training is a computationally intensive task and it is not free. You'll need a paid Azure Subscription. Expect to spend in the neighborhood of $0.10/per hour ($USD) when training models.
2. This repo is currently based on Python3.9 even though this is several versions behind the latest stable version of Python. DO NOT ARBITRARILY UPGRADE TO LATER VERSIONS OF PYTHON. It will break. This repo is actively maintained. We monitor this. You have been warned.

A Python command-line application that demonstrates how to use OpenAI Api function calling to drive an automated agentic workflow. Additionally, this repo demonstrates

• how to use Docker Compose to containerize your project
• how to leverage Pydantic for constructing complex JSON objects Python code is located here

React Matrix Digital Rain Effect gives you your favorite Matrix movie screen effect in the form of a React component. The source originates from an October 2021 blog article written by Adam Nagy, "Matrix raining code effect using JavaScript".

• Lightweight: The active code in this repository is less than 100 lines. It uses a canvas for rendering, which should ensure that it is both performant and that it works in most browsers.
• Use Anywhere: The <MatrixRainingLetters /> component tag can be placed anywhere in your jsx return function. It accepts custom classes and responds normally to CSS styling.

An Open edX plugin showcasing a curated collection of code samples for extending and modifying the stock functionality of an Open edX installation using the built-in plugin architecture. This plugin can be installed in any Open edX installation version Juniper or later, independent of the installation method. This plugin currently runs in native builds, tutor installations, and Cookiecutter-openedx Kubernetes, amongst other proprietary installation methodologies. Open edX official documentation recommends that you leverage its plugin architecture rather than fork its code repositories. This project provides more than two dozen code examples to help you accomplish this. Usage:

pip install openedx-plugin-example

Technical features and coding techniques that are showcased in this repo include:

• Iterate and introspect structured course content
• Custom oauth backend that seamlessly integrates with Open edX third party authentication
• Custom url to auto-enroll students in a course
• Automatically detect and adapt to the browser OS locale setting
• Usage examples of Open edX's extensive library of Python decorators
• Open edX Django configuration settings
• Open edX Django urls
• Open edX Django logging
• Open edX Django signals
• Open edX Django RestFramework custom api
• Django app setup
• Django models
• Django and Mako templating
• Django static assets
• Django Admin
• Django middleware
• Django manage.py custom commands
• Django Waffle flags
• Python environment variables
• How to bundle multiple plugins in a single pip package
• How to redirect Open edX urls in lms and cms to endpoints created in this plugin
• How to automatically initialize Django model data during app startup
• Adding unit tests to plugin code
• Semantic version control
• Pre-commit with linting by flake8 and black, both of which are configured to match the opinionated styling that you'll find in Open edX repositories
• pip configuration, requirements, constraints, setup.py, pyproject.toml
• Publishing to PyPi

🤖 Retrieval Augmented Generation and Hybrid Search 🤖 A Hybrid Search and Augmented Generation prompting solution using Python OpenAI API Embeddings persisted to a Pinecone vector database index and managed by LangChain. Demonstrates the following:

• System Prompting. How do use the system prompt to modify LLM text completion behavior.
• Templates. How to create templates in order keep your prompts DRY.
• LangChain. How to setup a project using LangChain as an alternative to vendor specific LLM PyPi packages.
• PDF Loader. a command-line pdf loader program that extracts text, vectorizes, and loads into a Pinecone dot product vector database that is dimensioned to match OpenAI embeddings.
• Pinecone. How to create, load, and query a Pinecone vector database.
• Retrieval Augmented Generation (RAG). A chatGPT prompt based on a hybrid search retriever that locates relevant documents from the vector database and includes these in OpenAI prompts. Secondarily, I also use this repo for demonstrating how to setup Pydantic to manage your project settings and how to safely work with sensitive credentials data inside your project.

This repo contains source code and supplements for UBCx-VSP 1-Week AI Tools in Python and Stats, including code samples for the online modules in Canvas and the Netflix AI Greenlight Challenge: Can Data Science Predict the Next Hit Drama? Lets find out!!!

This is the source code for my Blog Article and FullStackWithLawrence Youtube Video. Terraform scaffolding to create a production-ready Kubernetes cluster running inside its own VPC. Sets up spot pricing for EC2 instances, and installs and configures commonly needed packages including:

• nginx-ingress-controller
• cert-manager
• metrics-server
• prometheus
• vertical pod autoscaler (vpa) Consists of the following source code: