Skip to content

hidevscommunity/full_stack_gen_ai_course

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

18 Commits
 
 
 
 

Repository files navigation

Full Stack Gen AI Program by Hidevs Community

Here's an overview of the program content:

Assignment doc link

Week 1 - Gen AI

Topics

1.1 Introduction of Gen AI

  • What is Gen AI?
  • Evolution of Gen AI
  • How does Gen AI work?
  • Types of Gen AI
  • Examples of Gen AI in use today
  • Benefits and challenges of Gen AI

1.2 The Fundamentals of Gen AI & Foundation Models

  • What is the Foundation Model?
  • Types of Foundation Models (table with 5+ parameters)
  • How do large language models work?
  • What is GPU and their role in AI & ML
  • Capabilities and limitations of large language models
  • How are large language models used in Gen AI?
  • Training a foundation model
  • Customizing a foundation model

Resources

Hidevs Community: Harnessing the Power of Gen AI for Business Transformation

The Fundamentals of Gen AI & Foundation Models

Week 2 - Prompt Engineering & LLM Models

LLM Models

  • Open source

  • Closed source

  • Popular models

  • Multimodels

  • Models based on use case

    Resources

    LLM Models

Prompt Engineering

  • Zero shot
  • Few shot
  • One shot
  • Chain of thoughts
  • Tree of thought

Resources

Prompt Engineering

Chatgpt prompt engineering for developers short courses by Andrew Ng

Pair Programming with LLM

Week 3 - Python

Topic: Learn Python using Address Book Project

Project Overview:

  • Basic Python
  • Object-Oriented Programming (OOP) concepts
  • Python data structures
  • File reading

Project Tasks:

  1. Add contact details
  2. Delete contact details
  3. Update contact details
  4. Search contact details by name

Resources

Python

Week 4 - Data Science

Project 1: Learn Data Science using Wine Reviews Analysis

Topics Covered:

  • Virtual environment setup
  • Exploring offline and online data science IDEs
  • Introduction to machine learning libraries like Pandas, NumPy, and Matplotlib

Project Tasks:

  1. Setup data science environment
  2. Data manipulation or preprocessing with Pandas
  3. Descriptive analysis and matrix calculation with NumPy
  4. Data visualization with Matplotlib

Project 2: Learn Data Science using Housing Price Prediction

Topics Covered:

  • Machine learning libraries like Pandas, NumPy, and Matplotlib
  • Feature engineering and model training with Scikit-learn library
  • Regression algorithms like linear regression and decision tree
  • Evaluation metrics for regression algorithms like R2 Score, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE)

Project Tasks:

  1. Data manipulation or preprocessing with Pandas
  2. Descriptive analysis and matrix calculation with NumPy
  3. Data visualization with Matplotlib and Seaborn
  4. Feature engineering with Scikit-learn
  5. Regression algorithms model training with Scikit-learn and Pickle
  6. Evaluation of machine learning model

Resources:

Week 5 - Natural Language Processing (NLP)

Project: Classifying the News Category

Topics Covered:

  • Introduction to NLP
  • Getting Started with NLTK (Natural Language Toolkit)
  • NLP basic terminologies and their extraction
  • Approaching NLP problems
  • Text Pre-processing
  • Feature Engineering (Featurization) of text data
  • Text Classification – Classifying the news category
  • Model Deployment

Resources:

Week 6 - Data Engineering

Fundamentals of Data Engineering

  • ETL (Extract, Transform, Load)
  • Querying
  • Pipelines

Week 7 - Langchain

Important Concepts of Langchain

  • Smart contracts
  • Decentralized applications (DApps)
  • Consensus mechanisms
  • Tokenization
  • Interoperability
  • Privacy and security protocols
  • Governance models
  • Cross-chain communication

Week 8 - Retrieval-Augmented Generation (RAG)

  • 5W1H on RAG
  • Basic Data Cleaning
  • Vector Database
  • Knowledge Graph Database
  • Chunking
  • Embedding
  • LLM Models
  • Trulens

Project Details

  • Q&A on PDF/CSV/DOC

Week 9 - Fine Tuning & PFET

Fine Tuning

  • 5W1H on FT (Who, What, When, Where, Why, How)
  • PFET
  • LoRA
  • QLoRA
  • Prefix tuning
  • Prompt tuning
  • Fine Tuning by multiple methods

Week 10 - Tech Stack to Build any Project in Gen AI

Programming Languages and Frameworks

  • Front end: Streamlit (React or Angular)
  • Back end: Langchain

Data Storage and Processing Tools

  • Database: Chroma or FAISS (for Vector DB)

Machine Learning or Gen AI or LLM Models Libraries

  • Open Source

Pricing

Cloud Computing Platforms

  • Deployment: Hugging Face Spaces

Determine the Efficiency/Accuracy of Gen AI Apps

  • Trulens

Considerations While Building any Gen AI Project

  • Hallucination
  • Latency
  • Costing

Week 11 - Challenges, Mitigation, Tools & Gen AI into Company

Potential Challenges and Mitigations

  • Ethical considerations
  • Data privacy and security concerns
  • Bias in Gen AI models
  • How to mitigate the challenges of Gen AI

Tools Available in the Market

  • Popular Gen AI development tools
  • How to choose the right tools for your project
  • Coding tools
  • Product tools
  • HR tools
  • Common Tools

How to Incorporate Gen AI into Any Company

  • Find use cases
  • Expense sheet
  • Revenue sheet
  • Profit margin
  • Top 4 Pricing API models
  • Top 4 Open Source API models
  • Benefits and drawbacks of pricing vs open source API models
  • The cost of developing and deploying Gen AI
  • Factors that affect the cost of Gen AI
  • How to reduce the cost of Gen AI
  • How companies are using Gen AI to improve their businesses
  • Examples of successful Gen AI integrations

Week 12 - Real World Projects

Week 13 - Profile Building

  • Resume Building
  • Linkedin Profile Building
  • Job Apply 50+ in single day at $0

Resources

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors