Generative AI & LLM Engineering: RAG, LangChain, Fine-Tuning

About this course

Topics covered in this course.1. Introduction to Generative AI, difference between GenAI and Traditional AI, different AI models including Linear Regression, Classification and Clustering & local LLMs set up using Ollama2. Foundation Models including OpenAI, Llama, Gemini, Claude & Qwen, why parameters matter, different between regular LLms and reasoning LLMs and Transformer Architecture3. Prompt Engineering including zero shot, few shot & chain of thought, different prompts use for different tasks4. Why Vector Databases, differences between Vector Databases including Pinecone, Chroma & FAISS and traditional DBs. How we ingest company knowledge base to vector DBs using chunking and embeddings and how we do semantic search. 5. Frameworks including LangChain, LlamaIndex & vLLM. Building different applications using LangChain and LlamaIndex frameworks and how we use vLLM for deploying models to local or on prem environment and use for inferencing. 6. Model Compression & Finetuning including Lora, QLora & PEFT. Finetuning using GCP and LORA. Different quantization techniques. 7. Generative AI usage and Architectures (IR, RAG, RAG with reRanker, Hybrid Search, Contextual RAG & LightRAG) & Observability8. Applications & APIs using Streamlit & Gradio. Exposing LLMs using REST end points for UI to consume. Natural language to SQL generation. Agents & Multi Agent Systems. Difference between Gen AI and Agentic AI. Different Agentic AI architectures.

Prices, discounts and availability are set by Udemy. We may earn a commission when you purchase through links on this site.