Complete course on Generative AI: Prompting Engineering, Running LLMs locally (Ollama), Building AI apps using LangChain
If you are a developer, data scientist, analyst, researcher, or simply someone passionate about mastering the next wave of artificial intelligence, this course is your complete roadmap. Have you ever wondered how ChatGPT, Claude, or Gemini actually work behind the scenes? Or perhaps you’ve asked yourself, “How can I build my own AI apps or run large language models locally?” This course will take you from curiosity to complete mastery—step by step.
What you’ll learn
- Design and engineer effective prompts using proven frameworks like Chain-of-Thought, Step-Back, and Role prompting..
- Tune and control LLM behavior by adjusting hyperparameters such as temperature, top-p, max tokens, and penalties..
- Run and customize Large Language Models locally using Ollama and integrate them with Python applications..
- Build complete Generative AI workflows using LangChain, including prompt templates, chains, memory, and dynamic routing..
- Develop Retrieval-Augmented Generation (RAG) systems that combine LLMs with vector databases for grounded, factual answers..
- Design user-friendly AI interfaces using Streamlit and explore On-Device AI deployment with Qualcomm AI Hub..
Course Content
- Introduction –> 1 lecture • 8min.
- Prompt Engineering –> 12 lectures • 1hr 36min.
- Prompt hyperparameters and their tuning –> 5 lectures • 36min.
- Prompt evaluation –> 3 lectures • 33min.
- Running LLMs Locally on your PC –> 4 lectures • 23min.
- Using Ollama with Python –> 3 lectures • 16min.
- Building LLM Applications using LangChain in Python –> 3 lectures • 15min.
- Chains and Runnables (LangChain Expressions Language) –> 6 lectures • 47min.
- Memory in LangChain –> 7 lectures • 36min.
- Retrieval Augmented Generation – Building your own RAG applications –> 6 lectures • 49min.
- Tools and Agents: Building your own AI Agents –> 5 lectures • 38min.
- LangSmith for monitoring our Application –> 2 lectures • 11min.
- Creating Graphical UI using Streamlit for our application –> 2 lectures • 13min.
- What’s under the hood: Understanding the foundations of LLMs –> 9 lectures • 1hr 31min.
- Getting Started with On-Device AI –> 3 lectures • 17min.
- Model Training & Deployment Steps –> 3 lectures • 20min.
- Model Compilation & Profiling –> 4 lectures • 23min.
- Model Optimization & Deployment –> 6 lectures • 48min.
- Conclusion –> 2 lectures • 2min.
Requirements
If you are a developer, data scientist, analyst, researcher, or simply someone passionate about mastering the next wave of artificial intelligence, this course is your complete roadmap. Have you ever wondered how ChatGPT, Claude, or Gemini actually work behind the scenes? Or perhaps you’ve asked yourself, “How can I build my own AI apps or run large language models locally?” This course will take you from curiosity to complete mastery—step by step.
“Generative AI Skillpath: Zero to Hero in Generative AI” is not just another theory-heavy course. It’s a hands-on, end-to-end journey into the world of large language models (LLMs), prompt engineering, LangChain, RAG, AI agents, Streamlit interfaces, and even On-Device AI using Qualcomm AI Hub. You’ll learn how to design, evaluate, and build AI applications from scratch—powered by real-world tools and frameworks that professionals use every day.
In this course, you will:
- Master the art of prompting — from basic prompt crafting to advanced frameworks like Chain-of-Thought, Step-Back, and Role prompting.
- Understand and fine-tune hyperparameters such as temperature, top-p, and penalties to control the tone, creativity, and consistency of AI outputs.
- Run powerful LLMs locally using Ollama and seamlessly integrate them with Python for custom applications.
- Build AI-powered workflows using LangChain — from creating prompt templates and chains to integrating memory and dynamic routing.
- Develop complete Retrieval-Augmented Generation (RAG) systems, connecting your AI models to private or local data sources for grounded, factual responses.
- Design intelligent agents that can search the web, use tools, and maintain memory using LangChain’s Agent framework.
- Monitor and optimize your applications with LangSmith to ensure reliability and traceability.
- Create sleek user interfaces for your AI apps using Streamlit, and explore the future of On-Device AI deployment on Qualcomm’s platform.
Why take this course now?
Generative AI is reshaping industries—from content creation and analytics to software development and research. But to truly harness its potential, you must go beyond using tools—you must understand, build, and innovate with them. This course equips you with not just knowledge, but the technical fluency and practical experience to design your own intelligent systems.
Throughout the course, you will:
- Design and test prompt frameworks with measurable improvements in AI output quality.
- Run and customize open-source LLMs on your PC without relying on cloud APIs.
- Build your own AI chatbots, assistants, and RAG applications using LangChain and Python.
- Optimize and deploy models on-device for privacy, speed, and offline use.
- Gain real-world project experience that bridges the gap between AI theory and implementation.
This course stands apart with its complete lifecycle coverage—from prompt design to application development and on-device deployment. Whether your goal is to become an AI engineer, product innovator, or simply stay ahead in the AI revolution, this course will take you from zero to full mastery.
Don’t just use AI—build it, understand it, and lead with it. Enroll today and become a creator in the age of Generative AI.