Building Contextual information Retrieval Systems with Large Language Models (LLMs)


In our data-dense world, efficient and effective information retrieval has become pivotal. Traditional information retrieval systems, while having served us well in the past, are increasingly falling short in an era characterized by massive, dynamic data and the demand for personalized, context-aware responses.

This tutorial will take participants on a journey to explore the transformative capabilities of Large Language Models (LLMs) like GPT-3 and GPT-4 in revolutionizing the field of information retrieval. A key highlight will be the introduction to LangChain, a growingly popular framework designed to enable data connectivity for LLMs, enhancing their ability to offer context-aware and personalized results. This tutorial is designed for tech professionals, AI researchers, data scientists, and developers, offering a fresh perspective on the intersection of AI and interactive information retrieval.

Session Outline:

Module 1: Introduction to Large Language Models and Information Retrieval
Understand the concept of Large Language Models (LLMs) and fundamental principles of information retrieval. Grasp how LLMs can enhance the information retrieval process and comprehend the context in which traditional methods can fall short.

Module 2: Delving into Data Connectivity and LangChain
Explore the role of data connectivity in augmenting the capabilities of LLMs for information retrieval. Discover LangChain, a growingly popular framework, that enables data connectivity for LLMs. Become familiar with the core components of LangChain and their functionalities in improving the efficiency of information retrieval.

Module 3: Building an Information Retrieval System using LLMs and LangChain
Learn how to connect an LLM to a data source using LangChain. Walkthrough the steps involved in building an information retrieval system that leverages the capabilities of an LLM and the LangChain framework. Note: This module is designed for conceptual understanding and does not require hands-on participation.

After attending this session, participants will gain an understanding of the essential principles of using Large Language Models (LLMs) for information retrieval. They will grasp the significance of data connectivity in enhancing LLMs' capabilities and will be introduced to LangChain, a tool designed for this purpose. They will acquire the foundational knowledge necessary to build an LLM-based information retrieval system. The open-source tools used during the presentation will include LangChain for data connectivity, Python for coding, GPT-3 or GPT-4 as representative LLMs, and Jupyter Notebook for live coding demonstrations.

Background Knowledge:

Python, Deep Learning, basic knowledge of LLMs


Chaine San Buenaventura is the co-founder of Voilabs, an early-stage AI startup based in Paris specializing in voice chatbots for customer service. They are exploring the transformative capabilities of AI in reshaping digital interactions and are committed to driving innovation in this space. Chaine continues to contribute her expertise to, where she has been serving as the Lead Machine Learning Engineer, assisting in the advancement of their AI initiatives. Passionate about the future of AI, Chaine consistently explores the intersection of deep learning and natural, context-rich digital interactions, continually pushing the boundaries of what's possible in Human-Machine Interaction. Her years of dedicated work in developing AI solutions and active participation in research, conferences, and community dialogues underscore her commitment to AI innovation and knowledge-sharing in the expanding field.

Open Data Science




Open Data Science
One Broadway
Cambridge, MA 02142

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
Consent to display content from - Youtube
Consent to display content from - Vimeo
Google Maps
Consent to display content from - Google