AI Learning resouces

 Collection of resources

• aka.ms/genai-beginners - github- generative-ai-for-beginners
• rasbt/LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
• microsoft/ML-For-Beginners: 12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all
• openai/openai-cookbook: Examples and guides for using the OpenAI API
• CompVis/stable-diffusion: A latent text-to-image diffusion model
• 
  
• microsoft/ai-agents-for-beginners: 18 Lessons to Get Started Building AI Agents
• microsoft/AI-For-Beginners: 12 Weeks, 24 Lessons, AI for All!
• pathwaycom/llm-app: Ready-to-run cloud templates for RAG, AI pipelines, and enterprise search with live data. 🐳Docker-friendly.⚡Always in sync with Sharepoint, Google Drive, S3, Kafka, PostgreSQL, real-time data APIs, and more.
• facebookresearch/segment-anything: The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Software Engineering learning

 Each company share the engineering articles, explaining the architecture of their solutions.

• Learning Center | Cloudflare
• Google Engineering Practices Documentation | eng-practices
• Engineering | Uber Blog
• AWS Reference Architecture Examples and Best Practices
• Stripe | Dev Blog
• Netflix TechBlog
• The latest from GitHub's engineering team - The GitHub Blog
• Engineering at Meta - Engineering at Meta Blog

Engineering Excellence

Engineering Excellence

Having solid engineering process and tools in place help to improve the agility of the system. Here is the high-level flow recommended by our VP.

While building the solution we need to see how we can bring value, MVP instead of build parts which is not adding value initially.

AI Tools

• https://app.mindpal.space
• https://riverside.fm
• Gammas - Gamma
• https://fathom.video 

Microsoft copilot Agent

 In Copilot Chat https://m365.cloud.microsoft/chat

Click on All Agents on side bar

Copilot Studio

Provide the details and you are agent is ready

Teams PowerShell

 The PowerShell helps to get quick meta data around Teams.

Install-Module -Name MicrosoftTeams
Connect-MicrosoftTeams
Get-TeamAllChannel -GroupId   | select DisplayName | clip

Azure Machine Learning

Azure Machine Learning is the home for Data Scientists to run experiments.  But the language and constructs used in Microsoft Azure ML will be confusing in the first go.  This article helps to clear some fundamentals.

The below words are confusing, and the UI is not that great.

• Pipeline
• You can create a pipeline object and execute in an experiment.
• Pipeline Job
• Experiment: Pipeline jobs are grouped into experiments to organize job history. You can set the experiment for every pipeline job.
• Pipeline Endpoint
• Can have multiple Pipeline but only one could be the default.
• Published Pipeline

Running a script - Experiment Job Type: Command 

from azureml.core import Workspace, Experiment, Environment, ScriptRunConfig

ws = Workspace.from_config()

experiment = Experiment(workspace=ws, name='day1-experiment-try1')

config = ScriptRunConfig(source_directory='./', script='Hello.py', compute_target='gurupc')

run = experiment.submit(config)

run.log('mymetric', 1)

run.wait_for_completion(show_output=True, wait_post_processing=True)

aml_url = run.get_portal_url()

print(aml_url)

Running a Pipeline - Experiment Job Type: Pipeline

https://github.com/guvijaya/TipsAndTricks/blob/master/Azure%20Machine%20Learning/AML%20Pipelines%20Intro.py