OPENAI_API_KEY

GROQ_API_KEY

PHOENIX_API_KEY

This course teaches how to use LlamaIndex to connect with large language models, build RAG systems, extract data, and create agentic and AI applications.

llamaindex.tar.gz

L2notebookjupyter

L3notebookjupyter

python

python-spa

python-spa-rag

python-spa-streamlit

python-spa-streamlit-ollama

This course explores LlamaIndex’s core architecture and how it connects unstructured data to language models. You’ll learn how to connect LLMs to content sources like documents, APIs, and knowledge bases.

You’ll build and refine RAG systems, extract structured data, and feed results into downstream analytics or automation workflows. Finally, you’ll orchestrate AI agents and workflows, from single-agent assistants to complex multi-agent architectures with shared memory and state. You’ll add logging, tracing, and dashboards to your pipelines, then apply everything in hands-on projects like building a document Q&A system and lesson-plan generator.


After completing this course, you’ll gain the skills to design and build end-to-end AI solutions with LlamaIndex, including RAG, structured data extraction, and multi-agent workflows in any domain.

Mastering LlamaIndex: From Fundamentals to Building AI Apps

Learn how to evaluate different components of an LLM application and iteratively improve system performance using LlamaIndex’s built-in evaluation tools.

Evaluating AI Applications Using LlamaIndex

Getting Started

Core Concepts and Using LLMs

Building a RAG Pipeline

Extracting Structured Outputs from LLMs

Agents and Workflows

Monitoring and Evaluating LLM Applications

Building Real-World Applications with LlamaIndex

Wrap Up

Evaluating AI Applications Using LlamaIndex