Build & Test AI Agents, Chatbots, and RAG with Ollama & Local LLMs

This course is designed for complete beginners—even if you have zero knowledge of LangChain, you’ll learn step by step how to build LLM-based applications using local Large Language Models (LLMs).

The course is fully updated with LangChain v1.0.3

We’ll go beyond development and dive into evaluating and testing AI agents, RAG applications, and chatbots using RAGAs to ensure they deliver accurate and reliable results, following key industry metrics for AI performance.

What You’ll Learn:

• Fundamentals of LangChain & LangSmith

• Chat Message History in LangChain for storing conversation data

• Running Parallel & Multiple Chains (RunnableParallels, etc.)

• Building Chatbots with LangChain & Streamlit (with message history)

• Understanding Tools and Tool chains in LLM

• Building Tools and Custom Tools for LLM 

• Creating AI Agents using LangChain

• Implementing RAG with vector stores & local LLM embeddings

• Using AI Agents and RAG with Tooling while building LLM Apps

• Optimizing & Debugging AI applications with LangSmith

• Evaluating & Testing LLM applications with RAGAs

• Real-world projects & hands-on testing strategies

• Assessing RAG & AI Agents with RAGAs

This entire course is taught inside Jupyter Notebook with Visual Studio, providing an interactive, guided experience where you can run the code seamlessly and follow along effortlessly.

By the end of this course, you’ll be able to build, test, and optimize AI-powered applications with confidence!