-
Course
- Core Tech
Implementing Vector Search with LlamaIndex
This course will teach you how to build a research assistant capable of reasoning and answering questions over document data.
What you'll learn
Using LLMs to perform complex tasks doesn't need to be difficult. In this course, Implementing Vector Search with LlamaIndex, you’ll learn to build a custom LLM-powered assistant with the ChromaDB vector store to load and search documents, and generate context-augmented outputs.
First, you’ll explore how to set up a vector store as an index to load and query data with a quickstart example.
Next, you’ll discover how to implement a ChromaDB vector store pipeline to generate content with augmented context.
Finally, you’ll learn how to create a LLM-powered and multi-step pipeline to perform multiple tasks.
When you’re finished with this course, you’ll have the skills and knowledge of Retrieval Augmented Generation (RAG) needed to design and implement an end-to-end LLM-powered query system that combines structured retrieval, advanced ranking techniques, and generative AI capabilities for real-world applications.
Table of contents
About the author
Sandy is a passionate and experienced interface designer, developer, and digital entrepreneur hailing from Toronto, in Ontario, Canada. She specializes in front-end development with HTML, CSS, CSS3 Animation, Javascript, JQuery, Sass, and Less.
More Courses by Sandy