LlamaIndex toolkit for building data-driven applications

About the workshop

This workshop will provide a comprehensive understanding of LlamaIndex and how to utilize Large Language Models (LLMs) along with the LlamaIndex toolkit to build a variety of custom data-driven applications. We’ll focus on leveraging the Retrieval Augmented Generation (RAG) paradigm to create powerful systems such as Q&A systems, chatbots, and data agents. A core component of the workshop will be exploring how LlamaIndex serves as a crucial bridge between LLMs and your custom data.

Participant feedback

Visualization
{
"width": "container",
"$schema": "https://vega.github.io/schema/vega-lite/v5.json",
"description": "LlamaIndex workshop feedback",
"data": {
 "values": [
   {"Rating": "Dissatisfied", "Percentage": 1, "percentage": "3%"},
   {"Rating": "Satisfactory", "Percentage": 12, "percentage": "36%"},
   {"Rating": "Very satisfactory", "Percentage": 20, "percentage": "61%"}
 ]
},
"layer": [{
"mark": {"type": "arc", "tooltip": true}
},{
 "mark": {"type": "text", "radius": 115},
 "encoding": {
   "text": {"field": "percentage", "type": "quanlitative"}
 }
}],
"encoding": {
 "theta": {"field": "Percentage", "type": "quantitative", "stack": "normalize"},
 "color": {"field": "Rating", "type": "nominal"}
}
}

Who should participate?

This workshop is designed for data scientists, Machine Learning (ML) engineers, and researchers interested in developing applications powered by language models. Prior knowledge of language models and some programming experience, preferably in Python, will be beneficial.

Key takeaways - what participants will learn from the workshop

  1. Understanding Retrieval Augmented Generation (RAG) paradigm: Participants will learn about the RAG paradigm and how it enhances Large Language Models (LLMs) with custom data.
  2. Indexing stage mastery: The workshop will equip participants with skills to prepare a robust knowledge base using LlamaIndex’s data connectors and indexing capabilities.
  3. Effective querying techniques: Participants will learn to retrieve the most relevant context given a user query and synthesize responses using LLMs and LlamaIndex.
  4. Advanced building blocks: Participants will get practical experience in working with retrievers, node postprocessors, and response synthesizers.
  5. Text2SQL capabilities: Participants will learn how to use LlamaIndex to transform natural language queries to SQL queries over multiple tables.
  6. Router engines: Participants will learn about Router Engines, decision-making systems in LlamaIndex that choose the right query engine/index based on the user’s query.
  7. Data Agents: Participants will explore Data Agents, which leverage large language models to interact with data, understand context, and dynamically interact with external tools.
  8. Creating powerful end-to-end pipelines: Participants will learn to construct query engines, chat engines, and agents for a range of applications.

Duration of the workshop

The workshop will be approximately 4 hours long, including breaks.

Prior set-up and prep required by participants before coming to the workshop

Participants should have:

  1. Basic knowledge of Python programming and familiarity with language models.
  2. Our session will be conducted on Google Colab, so please ensure you have access to Google Colab.
  3. We’ll be utilizing GPT-based models (gpt2.5-turbo and gpt-4) for building applications with LlamaIndex, so having an OpenAI API key will be essential.

About the workshop instructor(s)

The workshop will be conducted by Ravi Theja - Data Scientist from Glance - InMobi, who holds a Master’s degree in Computer Science from IIIT-B and has published research in the field. The instructor is recognized for his open-source contributions to LlamaIndex, bringing practical insights from his contributions and industry experience to the workshop.

About The Fifth Elephant

The Fifth Elephant is a community funded organization. If you like the work that The Fifth Elephant does, and want to support meet-ups and activities in different cities in India, consider contributing by picking up a membership

Contact

Join The Fifth Elephant Telegram group at https://t.me/fifthel or follow @fifthel on Twitter.
For inquiries, contact The Fifth Elephant at +91-7676332020.

Venue

Juspay Technologies Private Limited

Stallion Business Center, 444, 18th Main Rd,

6th Block, Koramangala

Bengaluru - 560095

Karnataka, IN

Hosted by

Jump starting better data engineering and AI futures

Supported by

Workshop sponsor

Venue host

FP-Juspay is a forum to dive deep and contribute to the world of Functional Programming - Frameworks, Applications and People. more