4
Ingesting Data into Our RAG Workflow
We’ve taken a good look at the overall structure of LlamaIndex from afar. It’s now time to get much closer and understand the small details of this framework. It’s bound to get more technical but also more intriguing as we go further.
Ready to go deeper down the rabbit hole? Follow me!
In this chapter, we will learn about the following:
- Using the LlamaHub connectors to ingest our data
- Taking advantage of the many text-chunking tools in LlamaIndex
- Infusing our nodes with metadata and relationships
- Keeping our data private and our budget safe
- Creating ingestion pipelines for better efficiency and lower costs
Technical requirements
You will need to install the following Python libraries in your environment ...
Get Building Data-Driven Applications with LlamaIndex now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
