Large Language Models (LLMs): concepts and vocabulary | Complete Generative AI: From Foundations to Production
A self-paced 26-week learning path with 15 modules: AI foundations, Python, machine learning, transformers, LLMs, prompts, APIs, embeddings, RAG, frameworks, agents, customization, multimodal AI, Spring Boot with React, and production LLMOps. Includes 15 practical assignments and three portfolio projects.
Prerequisites: Begin with basic computer skills. Programming is introduced in Weeks 2–3. Use a local Python environment for coding labs; Java and React experience helps in Weeks 21–22. Model downloads, provider accounts and deployment resources are optional learner-managed dependencies. The 26-week schedule is suggested; reading estimates exclude independent project work.
Learning goals
What an LLM learns
Tokens, context windows and inference
Open-weight and proprietary models
Temperature, top-p and sampling
Hallucinations and limitations
Evaluation and model selection
Quantization and local inference
Understand the foundations
A language model estimates a distribution over the next token given preceding context. Repeating that operation generates a sequence. The context window bounds what a single request can include, but a large limit does not guarantee reliable use of every supplied detail. Reserve space for output, tool schemas and conversation history. A model can produce a plausible unsupported statement because fluency is optimized differently from evidence-backed correctness. Grounding and evaluation remain necessary even with deterministic-looking responses.
Connect the ideas
Temperature rescales logits before sampling; top-p restricts selection to a probability mass threshold. Implementations differ, and lower randomness is not a factuality guarantee. Open-weight means model weights are available under particular terms; it does not automatically mean unrestricted use, open training data or low operational cost. Quantization represents weights with fewer bits and can reduce memory, with quality and hardware tradeoffs. Weight memory alone omits caches, activations, runtime overhead and concurrent requests.
Checkpoint: explain these concepts in your own words, then describe one failure that the design must detect. Use synthetic or permissioned data throughout the course.
01. Introduction to Artificial Intelligence · Week 1
02. Python Programming for Gen AI · Weeks 2–3
03. Mathematics and Machine Learning Foundations · Week 4
04. Deep Learning and Transformers · Weeks 5–6
05. Large Language Models (LLMs) · Weeks 7–8
06. Prompt Engineering · Weeks 9–10
07. Generative AI APIs and Application Development · Week 11
08. Embeddings and Vector Databases · Weeks 12–13
09. Retrieval-Augmented Generation (RAG) · Weeks 14–15
10. LangChain, LlamaIndex and AI Frameworks · Week 16
11. AI Agents and Agentic AI · Weeks 17–18
12. Fine-Tuning and Model Customization · Week 19
13. Multimodal Generative AI · Week 20
14. Gen AI with Java Spring Boot and React · Weeks 21–22
15. Production Gen AI, LLMOps and Capstone · Weeks 23–26