Gen AI Fundamentals & Concepts

Core Gen AI concepts including Transformer architecture, LLMs, attention mechanisms, tokens, embeddings, and foundational AI principles.

0
Easy Concepts
17
Medium Concepts
9
Hard Concepts

Medium Concepts (17)

What's the difference between a Large Language Model (LLM) and other ML models?

gen-aillm

Explain these LLM concepts: Tokens, Context window, Temperature & Top-p sampling, Beam search.

gen-aillmtokens

What's the difference between encoder-only, decoder-only, and encoder-decoder models?

gen-aitransformersllm

What's the difference between fine-tuning and prompt engineering?

gen-aifine-tuningprompt-engineering

Explain RAG. When would you use it over fine-tuning?

gen-airagfine-tuning

What metrics would you track during model training?

gen-aimlopstraining

How would you handle imbalanced training data for a classification task?

gen-aitrainingmlops

Explain chain-of-thought (CoT) prompting. Why does it work?

gen-aiprompt-engineering

What's few-shot vs. zero-shot prompting?

gen-aiprompt-engineering

Design a prompt for sentiment analysis. What could go wrong?

gen-aiprompt-engineering

What is Google ADK (Agent Development Kit)? Explain its key features, architecture, and how it differs from LangChain, CrewAI, and AutoGen.

google-adkagentsframeworkgeminiopen-source
View Details →CodeResources

What is MCP (Model Context Protocol) and how does Google ADK integrate with it?

google-adkmcptoolsprotocolintegration
View Details →CodeResources

LLM vs SLM: What is the difference between Large Language Models and Small Language Models? When to use which one in Python?

gen-aillmslmmodel-selectioncost-optimization
View Details →CodeResources

Are token counts directly proportional to context length? How do input and output tokens consume the context window?

gen-aillmtokenscontext-window

What is a context window and how to manage the context window in LLM?

gen-aillmcontext-windowtokensrag

What is stateless and stateful in API in LLM?

gen-aillmapistatelessstateful

How do LLMs set their maximum context window? Explain the role of architecture, training, and API configuration.

gen-aicontext-windowllmarchitecturetoken-limits
View Details →CodeResources

Hard Concepts (9)

Explain the Transformer architecture. What are attention mechanisms and why are they important?

gen-aitransformersattention

Explain quantization in LLMs. Why is it important?

gen-aiquantizationllm

Walk me through a RAG pipeline architecture.

gen-airagsystem-design

How would you evaluate RAG system performance?

gen-airagevaluation
View Details →CodeResources

What are common failure modes in RAG systems?

gen-airag

What's the difference between LoRA and full fine-tuning?

gen-aifine-tuninglora

Explain instruction tuning. Why is it important for chat models?

gen-aifine-tuningllm

What's prompt injection? How do you mitigate it?

gen-aiprompt-engineeringsecurity

What is the A2A (Agent-to-Agent) protocol in Google ADK? How does it enable inter-agent communication?

google-adka2aprotocolmulti-agentinteroperability
View Details →CodeResources