Bassem Yacoube: Using LangChain and LlamaIndex to customize LLMs on structured and unstructured data
Updated: Sep 4
Bassem Yacoube is a Lead AI/ML Solutions Architect with over 20 years of experience in the technology field (currently at OctoML.AI). He has worked on complex real-world customer solutions, using cutting-edge technologies, for the largest and most technical professional services organizations in the world, such as Microsoft Consulting Services, Ernst & Young Digital, and Amazon Web Services ProServe. His customers have included Fortune 100 companies in verticals such as Healthcare, IT, Telco, Finance, Retail, Oil & Gas, Manufacturing, and large government organizations.
Using LangChain and LlamaIndex to customize LLMs on structured and unstructured data.
Large language models (LLMs) have become increasingly powerful tools for a wide range of tasks, from generating text to answering questions. However, LLMs are often trained on massive datasets of text, which can make them difficult to customize for specific tasks or domains.
LangChain and LlamaIndex are two open-source frameworks that can be used to customize LLMs for structured and unstructured data. LangChain provides a high-level API for building LLM-based applications, while LlamaIndex provides a low-level library for indexing and querying structured and unstructured data.
In this talk, we will discuss how to use LangChain and LlamaIndex to customize LLMs for a variety of tasks, including:
Generating text: We will show how to use LangChain to generate text that is tailored to a specific domain or task.
Answering questions: We will show how to use LangChain to answer questions that are posed in natural language.
Classifying data: We will show how to use LangChain to classify data into different categories.
We will also discuss the challenges of customizing LLMs and how to overcome them.
This talk is for anyone who is interested in using LLMs for natural language processing tasks. No prior experience with LangChain or LlamaIndex is required.