Comprehensive Generative AI Learning Path

Curated by Anish Roychowdhury

April 4, 2025

Contents

1 Foundations of Generative AI 3
1.1 Introduction to Generative AI . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
1.2 Large Language Models (LLMs) Basics . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

2 Prompt Engineering 3
2.1 Basics of Prompt Engineering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
2.2 Advanced Prompt Engineering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3

3 Generative Models 3
3.1 Diffusion Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3
3.2 GANs (Generative Adversarial Networks) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

4 Building AI Agents 4
4.1 AI Agent Frameworks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
4.2 Multi-Agent Systems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

5 Retrieval-Augmented Generation (RAG) 4

5.1 Basics of RAG . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
5.2 Vector Databases . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4

6 Fine-Tuning LLMs 5
6.1 Parameter-Efficient Fine-Tuning (PEFT) . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
6.2 Instruction Fine-Tuning . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5

7 Reinforcement Learning from Human Feedback (RLHF) 5

7.1 Introduction to RLHF . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5

8 Model Context Protocol (MCP) 5

8.1 Fundamentals of MCP . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
8.2 Implementing MCP in Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5
8.3 Advanced MCP Patterns . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6

9 Deployment of Generative AI Models 6

9.1 Local Deployment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
9.2 Serverless Deployment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
9.3 Edge Deployment . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6

10 Evaluation Metrics for Generative AI Models 6

10.1 Error Metrics and Loss Computation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
10.2 Advanced Evaluation Frameworks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6

1
11 Practical Projects and Applications 7
11.1 End-to-End Gen AI Projects . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
11.2 Industry-Specific Applications . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7

12 Ethical Considerations and Responsible AI 7

12.1 Ethical Frameworks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
12.2 Bias Mitigation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7

13 Future Directions in Generative AI 7

13.1 Multimodal Models . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
13.2 AI Research Frontiers . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

14 Community Resources and Continuous Learning 8

14.1 Open Source Communities . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8
14.2 Conferences and Workshops . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8

2
1 Foundations of Generative AI
1.1 Introduction to Generative AI
• Overview of generative models and applications.

– DeepLearning.AI Generative AI for Beginners

https://github.com/microsoft/generative-ai-for-beginners
– Big Book of Generative AI by Databricks
https://www.databricks.com/resources/ebook/big-book-generative-ai

1.2 Large Language Models (LLMs) Basics

• Learn about LLMs, tokenization, embeddings, and transformers.
– Building LLMs from Scratch (15 Lectures)
https://lnkd.in/gifp9PkM
– Transformer Architecture Explained
https://jalammar.github.io/illustrated-transformer/
– Transformers from Scratch in Python
https://towardsdatascience.com/build-your-own-transformer-from-scratch-using-pytorch-84c850470dcb

2 Prompt Engineering
2.1 Basics of Prompt Engineering
• Techniques like zero-shot, one-shot, few-shot learning, and chain-of-thought prompting.
– Prompt Engineering Guide
https://aman.ai/primers/ai/prompt-engineering/
– LangChain Prompt Templates
https://lnkd.in/dVkuiizQ

2.2 Advanced Prompt Engineering

• Generated knowledge, prompt chaining, and ReAct.

– Prompt Tuning with Hugging Face

https://huggingface.co/docs/peft/task guides/clm-prompt-tuning
– NVIDIA Blog on Prompt Engineering
https://developer.nvidia.com/blog/an-introduction-to-large-language-models-prompt-engineering-and-

3 Generative Models
3.1 Diffusion Models
• Learn how diffusion models generate images and other content.
– Diffusion Models Explained
https://towardsdatascience.com/diffusion-models-made-easy-8414298ce4da
– Illustrated Stable Diffusion
https://jalammar.github.io/illustrated-stable-diffusion/

3
3.2 GANs (Generative Adversarial Networks)
• Explore GAN architectures and applications.
– Understanding GANs
https://towardsdatascience.com/understanding-generative-adversarial-networks-gans-cd6e4651a29
– GAN Lecture Series
https://lnkd.in/eSf66zT

4 Building AI Agents
4.1 AI Agent Frameworks
• Learn frameworks like LangChain, CrewAI, and AutoGen.

– LangChain Crash Course

https://medium.com/databutton/getting-started-with-langchain-a-powerful-tool-for-working-with-larg
– CrewAI GitHub Repository
https://github.com/joaomdmoura/crewAI

4.2 Multi-Agent Systems

• Practical workflows for multi-agent environments.
– Multi AI Agent Systems with CrewAI
https://lnkd.in/dTudrD55
– OpenAI Agents SDK in Python
https://github.com/openai/openai-agents-python

5 Retrieval-Augmented Generation (RAG)

5.1 Basics of RAG
• Combine LLMs with external knowledge bases using vector databases.

– Guide to RAG Frameworks

https://deepchecks.com/practical-guide-to-crafting-your-first-llm-powered-app-using-rag-framework/
– LangChain for RAG Applications
https://medium.com/mlearning-ai/create-a-chatbot-in-python-with-langchain-and-rag-85bfba8c62d2

5.2 Vector Databases

• Learn about vector search and embedding storage solutions.
– Introduction to Vector Databases
https://weaviate.io/blog/what-is-a-vector-database
– FAISS Tutorial
https://medium.com/mlearning-ai/mastering-similarity-searches-building-a-faiss-index-with-cosine-s

4
6 Fine-Tuning LLMs
6.1 Parameter-Efficient Fine-Tuning (PEFT)
• Techniques like LoRA and QLoRA for efficient tuning.

– Fine-Tuning with LoRA

https://abvijaykumar.medium.com/fine-tuning-llm-parameter-efficient-fine-tuning-peft-lora-qlora-pa
– Hugging Face Blog on PEFT
https://huggingface.co/blog/trl-peft

6.2 Instruction Fine-Tuning

• Customize LLMs for specific tasks using instruction tuning.
– Instruction Fine-Tuning Guide
https://medium.com/@ud.chandra/instruction-fine-tuning-llama-2-with-pefts-qlora-method-d6a801ebb19
– Fine-Tune Your Own Llama Model in Colab
https://towardsdatascience.com/fine-tune-your-own-llama-2-model-in-a-colab-notebook-df9823a04a32

7 Reinforcement Learning from Human Feedback (RLHF)

7.1 Introduction to RLHF
• Understand how RLHF improves model alignment with human preferences.

– Hugging Face RLHF Blog

https://huggingface.co/blog/rlhf
– Short Course on RLHF by DeepLearning.AI
https://www.deeplearning.ai/short-courses/reinforcement-learning-from-human-feedback/

8 Model Context Protocol (MCP)

8.1 Fundamentals of MCP
• Understanding the Model Context Protocol for LLM interactions.
– Anthropic’s MCP Guide
https://github.com/anthropics/anthropic-cookbook/blob/main/model context protocol/model context pro
– Claude MCP Documentation
https://docs.anthropic.com/claude/docs/model-context-protocol

8.2 Implementing MCP in Applications

• Practical implementations and best practices.

– Structured Outputs with Claude 3 MCP

https://medium.com/@saitejasagi/structured-outputs-with-anthropics-claude-3-model-context-protocol
– OpenAI’s Approach to Structured Outputs
https://github.com/openai/openai-cookbook/blob/main/examples/How to format inputs to ChatGPT models

5
8.3 Advanced MCP Patterns
• Complex data extraction and validation patterns.
– Anthropic Research on MCP
https://www.anthropic.com/research/claude-3-model-context-protocol
– MCP Implementation Examples
https://github.com/ArnaudBuchholz/reserve-mcp

9 Deployment of Generative AI Models

9.1 Local Deployment
• Run models locally on your machine.

– 5 Free Tools for Local Deployment of LLMs

https://lnkd.in/dJsRrn2c

9.2 Serverless Deployment

• Deploy serverless applications using platforms like AWS Bedrock.
– Serverless Workflows with Amazon Bedrock
https://lnkd.in/dENcD795

9.3 Edge Deployment

• Bring generative AI capabilities to edge devices.
– Deploying LLMs at the Edge with NVIDIA IGX Orin Developer Kit
https://lnkd.in/d94BxVjw

10 Evaluation Metrics for Generative AI Models

10.1 Error Metrics and Loss Computation
• Evaluate model performance using metrics like BLEU score and perplexity.
– Foundations of NLP Metrics: BLEU Score and WER Metrics
https://towardsdatascience.com/foundations-of-nlp-explained-bleu-score-and-wer-metrics-1a5ba06d812
– Perplexity in Language Models Explained
https://medium.com/@priyankads/perplexity-of-language-models-41160427ed72

10.2 Advanced Evaluation Frameworks

• Comprehensive evaluation strategies for generative models.

– OpenAI Evals Framework

https://github.com/openai/evals
– Hugging Face Evaluation Leaderboard
https://huggingface.co/spaces/evaluate-measurement/leaderboard

6
11 Practical Projects and Applications
11.1 End-to-End Gen AI Projects
• Build complete applications leveraging generative AI.

– LangChain Practical Projects

https://github.com/gkamradt/langchain-tutorials
– Microsoft TaskWeaver Framework
https://github.com/microsoft/TaskWeaver

11.2 Industry-Specific Applications

• Learn how generative AI is transforming specific industries.
– McKinsey: Generative AI in Healthcare
https://www.mckinsey.com/capabilities/quantumblack/our-insights/generative-ai-in-healthcare
– AWS Gen AI Case Studies
https://aws.amazon.com/solutions/case-studies/generative-ai/

12 Ethical Considerations and Responsible AI

12.1 Ethical Frameworks
• Understanding ethical considerations in generative AI development.

– Stanford HAI Ethics Framework

https://hai.stanford.edu/sites/default/files/2020-09/AI-Ethics-Framework HDSI.pdf
– UNESCO AI Ethics Guidelines
https://www.unesco.org/en/artificial-intelligence/recommendation-ethics

12.2 Bias Mitigation

• Techniques to identify and reduce bias in generative models.
– Ethical Considerations in NLP Research
https://huggingface.co/blog/ethics-soc-2
– Anthropic’s Red Teaming Approach
https://www.anthropic.com/research/red-teaming-language-models-to-reduce-harms

13 Future Directions in Generative AI

13.1 Multimodal Models
• Explore models that handle multiple modalities (text, image, audio).

– GPT-4V System Card

https://openai.com/research/gpt-4v-system-card
– Multimodal Reasoning in LLMs
https://huggingface.co/blog/multimodal-reasoning

7
13.2 AI Research Frontiers
• Cutting-edge research directions in generative AI.
– Mamba: State-Space Models
https://arxiv.org/abs/2312.11805
– Practical Guide to LLMs in Production
https://github.com/Mooler0410/LLMsPracticalGuide

14 Community Resources and Continuous Learning

14.1 Open Source Communities
• Join communities to collaborate and learn from peers.

– Hugging Face Community

https://huggingface.co/
– LAION AI Organization
https://github.com/LAION-AI

14.2 Conferences and Workshops

• Stay updated with the latest research through conferences.
– NeurIPS Conference
https://neurips.cc/
– ACL Conference Proceedings
https://aclanthology.org/venues/acl/