Implementing Vector Search with LlamaIndex
Implementing Vector Search with LlamaIndex
.MP4, AVC, 1280x720, 30 fps | English, AAC, 2 Ch | 1h 19m | 233 MB
Instructor: Sandy Ludosky
.MP4, AVC, 1280x720, 30 fps | English, AAC, 2 Ch | 1h 19m | 233 MB
Instructor: Sandy Ludosky
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.
Implementing Vector Search with LlamaIndex
