Leveraging LLMs for Internal Knowledge Discovery

Abstract: 

Efficient knowledge discovery is crucial yet challenging in today's fast-paced, globally distributed work environments. This talk introduces a Retrieval Augmented Generation (RAG) based bot integrated with internal communication tools such as slack. It is designed to streamline access and discovery of documentation spread across multiple internal knowledge platforms and code-repositories and multiple languages. We will explore the chatbot's innovative architecture and practical applications.

The project originated from a simple need: navigating extensive documentation to find specific information, such as medical insurance coverage details. The project has evolved into a robust solution supporting number of teams and geographical regions. The chatbot's cross-platform capabilities allow it to combine data from sources like G-Drive, Github, and Confluence, providing comprehensive answers to user queries.

A significant challenge in knowledge discovery is the duplication of efforts across departments, different templated and languages (yes, we are a global organisation). Traditional solutions like organisation wide townhalls, newsletters, etc have limited reach due to language barriers and timezone differences. Our solution overcomes these hurdles by being asynchronous and language-agnostic, updating its knowledge base regularly, handling multiple languages seamlessly and transparently and universally available at the click of a button.

Attendees will gain insights into the technical intricacies of developing such a solution, the challenges encountered during its development, and its potential for future expansion. This session aims to demonstrate how RAG-based chatbots can revolutionize knowledge management and enhance collaboration in diverse, distributed work environments.

Join us to explore how this innovative chatbot can transform your approach to knowledge discovery and management.

Bio: 

Raghav is a seasoned Data Science professional with over a decade’s experience of research & development of large-scale solutions in Finance, Digital Experience, IT Infrastructure and Healthcare for giants such as Intel, American Express, United HealthGroup and DeliverHero. He is an innovator with 10+ patents, a published author of multiple well received books & peer-reviewed papers and a regular speaker in leading conferences on topics in the areas of Generative AI, Recommendation Systems, Computer Vision, NLP, Deep Learning, Machine Learning and Augmented Reality.

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