2 Data Structures & Algorithms

• Core Data Structures
• Lists
• Creating, accessing, modifying, and iterating over lists
• List comprehensions
• Tuples:
• Creating and using tuples
• Unpacking tuples
• Sets
• Creating and using sets
• Set operations (union, intersection, difference)
• Dictionaries
• Creating and using dictionaries
• Dictionary methods and comprehensions

3. File Handling and Data Processing

• File Operations
• Reading and Writing Files:
• Opening, reading, writing, and closing files
• Working with different file modes (r, w, a, rb, wb)
• Working with CSV and JSON:
• Reading from and writing to CSV and JSON files using csv and json modules

4. Object-Oriented Programming

• OOPs Basics
• Classes and Objects:
• Defining classes and creating objects
• Instance variables and methods
• Class Variables and Methods:
• Using class variables and class methods
• Inheritance
• Single and multiple inheritance
• Polymorphism and Encapsulation:
• Method overriding
• Private variables and name mangling

5. Exception Handling and Debugging

• Exception Types:
• Common exceptions (ValueError, TypeError, etc.,)
• Try, Except Blocks:
• Using try, except, else, and finally

6. Working with Libraries

• Scientific Computing
• NumPy:
• Arrays and matrix operations
• Pandas:
• DataFrames for data manipulation
• Reading and writing data (CSV, Excel)
• Data Visualization
• Matplotlib
• Plotting graphs and charts
• Seaborn:
• Statistical data visualization

Generative AI

1. Introduction

• GenAI and It’s Industry Applications
• Introduction to Generative AI
• AI vs ML vs DL vs NLP vs Generative AI
• Generative AI principles
• What is the role of ML in Gen-AI
• Different ML techniques (Supervised, Unsupervised, Semisupervised & Reinforcement Learning)
• Applications in various domains
• Ethical considerations

2. NLP & Deep Learning

• NLP essentials
• Basic NLP tasks
• Different text classification approaches
• Frequency based – Bag of words,TF-IDF, N-gram.
• Distribution Models – CBOW, Skipgram (Traditional approaches) and
word2vec, Glove.
• Deep learning techniques – CNNs, RNNs, LSTMs, GRU and Transformers
3. Generative AI Models
• Auto encodes
• VAE’s and applications
• GAN’s and it’s applications
• Different types of GAN’s and applications

4. Language Models & Transformer Models

• Different types of Language models
• Applications of Language models
• Transformers and its architecture
• BERT, RoBERTa, GPT variations
• Applications of transformer models

5. Prompt Engineering

• What is Prompt Engineering
• What are the different principles of Prompt Engineering
• Types of Different Prompt Engineering Techniques
• How to Craft effective prompts to the LLMs
• Priming Prompt
• Prompt Decomposition

6. Large Language Models

• Generative AI lifecycle
• What is RLHF
• LLM pre-training and scaling
• Different Fine-Tuning techniques

7. Different Chunk Metrics

• What is Chunking
• What is the use of chunking the document
• What are the traditional effective chunking techniques
• What are the problems and limitations with traditional chunking
techniques?
• How to overcome the limitations of Traditional chunking
• Advanced Chunking Techniques:
– Character Splitting
– Recursive Character Splitting
– Document based Chunking
– Semantic Chunking
– Agentic Chunking

8. RAG and Advanced RA with Langchain

• What is RAG
• What are the main components of RAG
• High level architecture of RAG
• How to Build RAG using external data sources
• Advanced RAG

9. Langchain for LLMs

• What is Langchain
• What are the core concepts of Langchain
• Components of Langchain
• How to use Langchain agents

10. Vector Databases

• LlamaIndex
• What are Vector Databases
• Why do we prefer Vector Databases over Traditional Databases
• Different Types of Vector Databases: OpenSource and Close Source
• OpenSource: Chroma DB, Weaviate,Faiss,Qdrant
• Close-Source Vector Databases:Pinecone,ArangoDB,Cloud-Based Solutions

11. Finetuning LLMs

• Supervised Finetuning
• Repurposing-Feature Extraction
• Advanced techniques in Supervised Finetuning -PEFT -LoRA, QLoRA

12. LLMs Evaluation

• Text based LLMs
• Automatic Evaluation: BULE Score, ROUGE Score, METEOR, BERT Score.
• Human Evaluation: Coherence, Factuality, Originality, Engagement

13. Image based LLMs

• Automatic Evaluation: Pixel-level metrics, FID (Frechet Inception
Distance), IS (Inception Score), Perceptual Quality Metrics, Diversity
Metrics.
• Human Evaluation: Photorealism, Style, Creativity, Cohesiveness

14. Audio generation LLMs:

• Automatic Evaluation: FAD (Frechet Audio Distance), IS (Inception Score), Perceptual Quality Metrics – PAQM, PAQM – SNR (Signal-toNoise Ratio), PAQM – PESQ (Perceptual Evaluation of Speech Quality)
• Human Evaluation: Perceptual Quality – PQ, PQ- Naturalness, PQFidelity, PQ- Musicality, Task Specific Evaluation.

15. Video Generation LLMs:

• Automatic Evaluation: FVD (Frechet Video Distance), Inception Score(IS), Perceptual Quality Metrics, Motion Based Metrics – Optical Flow Error, Content-Specific Metrics.
• Human Evaluation: Visual Quality, Temporal Coherence, Content Fidelity

16. LLMops

• Model Deployment and Management
• Scalability and Performance Optimization
• Security and Privacy
• Monitoring and Logging
• Cost Optimization
• Model Interpretability and Explainability.

17. LLM’s on Cloud

• Amazon Bedrock, Azure OpenAI

18. Langsmith

• What is langsmiths?
• Applications and use-cases

19. Agentic ai & MCP

• What is agentic ai
• Building single agent
• Multi agents by using MCP

20. Different AI Tools

• Open AI
• Hugging face
• PyTorch
• tensorflow
• lang chai & lang graph
• ChatGPT
• Gemini
• Copilot