What can I wear for a wedding? Ask MyFashionGPT

Fashion etailer Myntra says its new generative AI large language model (LLM) search feature, built using Microsoft’s Azure OpenAI Service, is helping customers discover a complete look from multiple categories of products, thereby enhancing their shopping experience.

The feature, called MyFashionGPT, is integrated in the Myntra app and answers user’s search queries with better actionable results.

“Leveraging Azure OpenAI Service, we were able to plug in different large language models in the same prompt and figure out which model worked best for our use case. So, we had a lot of freedom to compare and choose the right model,” Santanu Kanchada, back-end engineer in the search engineering team of Myntra, said in a blogpost on Thursday.


With access to Azure OpenAI Service, Myntra fine-tuned the back-end and user interface, launching MyFashionGPT in May, just before its biggest marquee event, the End of Reason Sale. It included sample prompts that gave users an idea of how they could use conversational language rather than keywords.

“This is big,” said Arit Mondal, director of product management at Myntra, “Why? Because, this is the first time we have a solution, which is solving the unsolved ‘search’ problem in the fashion, beauty and lifestyle industry. And it’s live for customers at scale.”

Since then, Myntra has already seen search queries broaden, offering new opportunities for product discovery. For instance, a search query for beachwear also results in accessories like hats, sunglasses and footwear pop-up.

“Users who shop using the AI shopping assistant are three times more likely to end up making a purchase,” said Mondal. “Because it also helps users discover a complete look from multiple categories of products, we are seeing that on average they add products from 16% more categories than usual.”

The company further plans to enhance MyFashionGPT by introducing voice search and provide personalised results as well as aid customer support teams, it said.