Building Data-Driven Applications with LlamaIndex
A practical guide to retrieval-augmented generation (RAG) to enhance LLM applications
Created by Andrei Gheorghiu
Explore how to enhance large language model applications by connecting them to dynamic knowledge bases using LlamaIndex. Gain practical experience in ingesting, indexing, and querying data to build AI-driven apps that deliver accurate, fact-based responses. Tackle common LLM challenges and learn to deploy interactive solutions.
Packt | May 2024 | 368 min
What You Will Learn
You will work through hands-on examples that guide you from setting up LlamaIndex to building and deploying an interactive web application. Each step focuses on practical skills, from data ingestion to querying and troubleshooting, so you can confidently apply what you learn to real-world projects.
Key Features
- Ingest and parse data from multiple sources for robust knowledge bases
- Build and optimize indexes to improve retrieval and response quality
- Deploy interactive web apps that use LlamaIndex and best practices in prompt engineering
Target Audience
Ideal for Python developers who already understand NLP basics and want to build smarter, more interactive LLM applications. If you are looking to expand your skills in retrieval-augmented generation or want to overcome LLM limitations in your projects, you will find actionable techniques and advanced workflows here.
