Browse Library
Sign In Start Free Trial
Close icon Search icon
Account
Browse Library Advanced Search Sign In Start Free Trial

Add to playlist

Create a Playlist

Modal Close icon
You need to login to use this feature.
  • Book Overview & Buying Building Data-Driven Applications with LlamaIndex
  • Table Of Contents Toc
  • Feedback & Rating feedback
Building Data-Driven Applications with LlamaIndex

Building Data-Driven Applications with LlamaIndex

By : Andrei Gheorghiu
5 (10)
Buy this Book
close
close
Building Data-Driven Applications with LlamaIndex

Building Data-Driven Applications with LlamaIndex

5 (10)
By: Andrei Gheorghiu
Buy this Book

Overview of this book

Discover the immense potential of Generative AI and Large Language Models (LLMs) with this comprehensive guide. Learn to overcome LLM limitations, such as contextual memory constraints, prompt size issues, real-time data gaps, and occasional ‘hallucinations’. Follow practical examples to personalize and launch your LlamaIndex projects, mastering skills in ingesting, indexing, querying, and connecting dynamic knowledge bases. From fundamental LLM concepts to LlamaIndex deployment and customization, this book provides a holistic grasp of LlamaIndex's capabilities and applications. By the end, you'll be able to resolve LLM challenges and build interactive AI-driven applications using best practices in prompt engineering and troubleshooting Generative AI projects.
Table of Contents (18 chapters)
close
close
close
Preface
Icon
Preface
Icon
Who this book is for
Icon
What this book covers
Icon
To get the most out of this book
Icon
Download the example code files
Icon
Conventions used
Icon
Get in touch
Icon
Share Your Thoughts
Icon
Download a free PDF copy of this book
Free Chapter
1
Part 1:Introduction to Generative AI and LlamaIndex
Icon
Part 1:Introduction to Generative AI and LlamaIndex
2
Chapter 1: Understanding Large Language Models
Icon
Chapter 1: Understanding Large Language Models
Icon
Introducing GenAI and LLMs
Icon
Understanding the role of LLMs in modern technology
Icon
Exploring challenges with LLMs
Icon
Augmenting LLMs with RAG
Icon
Summary
3
Chapter 2: LlamaIndex: The Hidden Jewel - An Introduction to the LlamaIndex Ecosystem
Icon
Chapter 2: LlamaIndex: The Hidden Jewel - An Introduction to the LlamaIndex Ecosystem
Icon
Technical requirements
Icon
Optimizing language models – the symbiosis of fine-tuning, RAG, and LlamaIndex
Icon
Discovering the advantages of progressively disclosing complexity
Icon
Introducing PITS – our LlamaIndex hands-on project
Icon
Preparing our coding environment
Icon
Familiarizing ourselves with the structure of the LlamaIndex code repository
Icon
Summary
4
Part 2: Starting Your First LlamaIndex Project
Icon
Part 2: Starting Your First LlamaIndex Project
5
Chapter 3: Kickstarting Your Journey with LlamaIndex
Icon
Chapter 3: Kickstarting Your Journey with LlamaIndex
Icon
Technical requirements
Icon
Uncovering the essential building blocks of LlamaIndex – documents, nodes, and indexes
Icon
Building our first interactive, augmented LLM application
Icon
Starting our PITS project – hands-on exercise
Icon
Summary
6
Chapter 4: Ingesting Data into Our RAG Workflow
Icon
Chapter 4: Ingesting Data into Our RAG Workflow
Icon
Technical requirements
Icon
Ingesting data via LlamaHub
Icon
An overview of LlamaHub
Icon
Using the LlamaHub data loaders to ingest content
Icon
Parsing the documents into nodes
Icon
Working with metadata to improve the context
Icon
Estimating the potential cost of using metadata extractors
Icon
Preserving privacy with metadata extractors, and not only
Icon
Using the ingestion pipeline to increase efficiency
Icon
Handling documents that contain a mix of text and tabular data
Icon
Hands-on – ingesting study materials into our PITS
Icon
Summary
7
Chapter 5: Indexing with LlamaIndex
chevron up
Icon
Chapter 5: Indexing with LlamaIndex
Icon
Technical requirements
Icon
Indexing data – a bird’s-eye view
Icon
Understanding the VectorStoreIndex
Icon
Persisting and reusing Indexes
Icon
Exploring other index types in LlamaIndex
Icon
Building Indexes on top of other Indexes with ComposableGraph
Icon
Estimating the potential cost of building and querying Indexes
Icon
Indexing our PITS study materials – hands-on
Icon
Summary
8
Part 3: Retrieving and Working with Indexed Data
Icon
Part 3: Retrieving and Working with Indexed Data
9
Chapter 6: Querying Our Data, Part 1 – Context Retrieval
Icon
Chapter 6: Querying Our Data, Part 1 – Context Retrieval
Icon
Technical requirements
Icon
Learning about query mechanics – an overview
Icon
Understanding the basic retrievers
Icon
Building more advanced retrieval mechanisms
Icon
Understanding the concepts of dense and sparse retrieval
Icon
Summary
10
Chapter 7: Querying Our Data, Part 2 – Postprocessing and Response Synthesis
Icon
Chapter 7: Querying Our Data, Part 2 – Postprocessing and Response Synthesis
Icon
Technical requirements
Icon
Re-ranking, transforming, and filtering nodes using postprocessors
Icon
Understanding response synthesizers
Icon
Implementing output parsing techniques
Icon
Building and using query engines
Icon
Hands-on – building quizzes in PITS
Icon
Summary
11
Chapter 8: Building Chatbots and Agents with LlamaIndex
Icon
Chapter 8: Building Chatbots and Agents with LlamaIndex
Icon
Technical requirements
Icon
Understanding chatbots and agents
Icon
Implementing agentic strategies in our apps
Icon
Hands-on – implementing conversation tracking for PITS
Icon
Summary
12
Part 4: Customization, Prompt Engineering, and Final Words
Icon
Part 4: Customization, Prompt Engineering, and Final Words
13
Chapter 9: Customizing and Deploying Our LlamaIndex Project
Icon
Chapter 9: Customizing and Deploying Our LlamaIndex Project
Icon
Technical requirements
Icon
Customizing our RAG components
Icon
Using advanced tracing and evaluation techniques
Icon
Introduction to deployment with Streamlit
Icon
HANDS-ON – a step-by-step deployment guide
Icon
Summary
14
Chapter 10: Prompt Engineering Guidelines and Best Practices
Icon
Chapter 10: Prompt Engineering Guidelines and Best Practices
Icon
Technical requirements
Icon
Why prompts are your secret weapon
Icon
Understanding how LlamaIndex uses prompts
Icon
Customizing default prompts
Icon
The golden rules of prompt engineering
Icon
Summary
15
Chapter 11: Conclusion and Additional Resources
Icon
Chapter 11: Conclusion and Additional Resources
Icon
Other projects and further learning
Icon
Key takeaways, final words, and encouragement
Icon
Summary
16
Index
Icon
Index
Icon
Why subscribe?
17
Other Books You May Enjoy
Icon
Other Books You May Enjoy
Icon
Packt is searching for authors like you
Icon
Share Your Thoughts
Icon
Download a free PDF copy of this book

Indexing our PITS study materials – hands-on

With a solid understanding of how indexing works in LlamaIndex, we’re now ready to implement the indexing logic in our tutoring application.

Let’s create the index_builder.py module. This module takes care of Index creation. In the current implementation, it creates two Indexes: a VectorStoreIndex and a TreeIndex. As you can see, this is a very basic implementation and there is definitely room for improvement. Let’s handle the imports first:

from llama_index.core import (
    VectorStoreIndex, TreeIndex, load_index_from_storage)
from llama_index.core import StorageContext
from global_settings import INDEX_STORAGE
from document_uploader import ingest_documents

Next, we’ll implement our Index building function:

def build_indexes(nodes):
    try:
        storage_context = StorageContext.from_defaults(
   ...

Unlock full access

Continue reading for free

A Packt free trial gives you instant online access to our library of over 7000 practical eBooks and videos, constantly updated with the latest in tech
Start a 7-day FREE trial
End of Section 9
Next Section

Create a Note

Modal Close icon
You need to login to use this feature.
notes
bookmark search playlist download
font-size

Change the font size

margin-width

Change margin width

day-mode

Change background colour

Close icon Search
Country selected
Close icon Your notes and bookmarks

Delete Bookmark

Modal Close icon
Are you sure you want to delete it?
Cancel
Yes, Delete

Delete Note

Modal Close icon
Are you sure you want to delete it?
Cancel
Yes, Delete

Edit Note

Modal Close icon
Write a note (max 255 characters)
Cancel
Update Note

Confirmation

Modal Close icon
claim successful
Order Page Read Now

Buy this book with your credits?

Modal Close icon
Are you sure you want to buy this book with one of your credits?
Close
YES, BUY