Abstract

In India’s offline markets, shopping is always about having an interactive dialogue. Yet, as e-commerce platforms evolved, dense UI interfaces clouded and removed conversational experience. With GenAI, we at Flipakrt have revitalized this dialogue. We called it Conversational Commerce

This talk will dive into the technical nuances of the GenAI implementation, from semantic understanding, to its seamless integration with Flipkart’s vast product ecosystem.

Broad outline

1. Touch upon the various use-cases where GenAI is used in Flipkart.
2. Dive deep into how LLMs are used to Understand User messages better in Conversational Commerce.
   1. Decoding Queries: Use ChatGPT-like LLM models to interpret and act on user queries.
   2. Clarifying Ambiguities: Generate questions to gain clarity on ambiguous or vague inputs.
   3. Contextual Conversations: Maintain continuity throughout dialogues, identifying when users switch topics.
3. Deep dive into the importance of Conversation Design and how its used in-conjuction with LLMs to provide a rich chat experience to the user.
4. The challenges faced, how they were overcome and the road forward.
5. Finally, our insights on LLMs, how and when to use them, and how local in-house models can augument large deployed models such as ChatGPT.

Target Audience

Data scientists and Software Architects building Chat Assistants for large organisations with diverse use-cases.

Unique Value Proposition

The talk focusses on building large scale production GenAI applications, solving a broad set of problems in Flipkart. We will give a view of how and why a GenAI POC and a Production grade application are different.

Speakers

• Anantharam Vanchiprakash LinkedIn
• Priyanka Nahata LinkedIn