Building LLM-powered Knowledge Workers over your Data with LlamaIndex

Abstract: 

Large Language Models (LLM’s) are starting to revolutionize how users can search for, interact with, and generate new content. Some recent stacks around Retrieval Augmented Generation (RAG) have emerged where users are building LLM search/retrieval applications (e.g. chatbots) on their own private data. Moreover, there is an opportunity to have even richer set of interactions with data; by empowering LLM agents with both read and write capabilities over a set of diverse data tools, they hold the promise of automating knowledge workflows.

LlamaIndex provides the core tools to build LLM-powered search and retrieval systems as well as more automated knowledge workers capable of interfacing with your data sources in more sophisticated manners. In this workshop, we help you build both a simple QA bot as well as an automated workflow agent, all powered by LLMs.

Session Outline:

Lesson 1: Build a simple QA system over your Data

In this first section, you’ll familiarize yourself with some core modules of LlamaIndex: data connectors, data indexes, query engines, as well as our primitives such as LLMs and prompts. This will help you build a simple Question-Answering system over some example data.

Lesson 2: Elevate this QA system with more advanced techniques

In this second section, you’ll add more sophisticated reasoning to your QA system. You’ll use our router module to help make automated decisions about whether to perform embedding-based retrieval or bulk retrieval depending on the question.

Lesson 3: Build Data Agents

In this final section, you’ll explore our more sophisticated, unconstrained module - Data Agents. You’ll be able to create a knowledge worker that’s capable not only of looking up information, also of sending/updating email drafts.

Bio: 

Jerry is the co-founder/CEO of LlamaIndex, an open-source tool that provides a central data management/query interface for your LLM application. Before this, he has spent his career at the intersection of ML, research, and startups. He led the ML monitoring team at Robust Intelligence, did self-driving AI research at Uber ATG, and worked on recommendation systems at Quora. He graduated from Princeton in 2017 with a degree in CS.

Open Data Science

 

 

 

Open Data Science
One Broadway
Cambridge, MA 02142
info@odsc.com

Privacy Settings
We use cookies to enhance your experience while using our website. If you are using our Services via a browser you can restrict, block or remove cookies through your web browser settings. We also use content and scripts from third parties that may use tracking technologies. You can selectively provide your consent below to allow such third party embeds. For complete information about the cookies we use, data we collect and how we process them, please check our Privacy Policy
Youtube
Consent to display content from - Youtube
Vimeo
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google