Myntra integrates ChatGPT with search for better product discovery

Myntra said MyFashionGPT will scout through catalogues available on the app to give users a better option for their queries.

“Many times people are figuring out in their own mind as to what they need for a certain look or an occasion and then search for individual products. For example, I want a saree, blouse, jhumkas, red lipstick, sandals for a wedding. But now, with MyFashionGPT everything is coming under just one search: What to wear for a wedding?” Myntra said in a statement.

Also read | AI at warp speed: disruption, innovation, and what’s at stake

For example, customers can search for numerous scenarios, including looks based on local or global destinations, such as a trip to Manali in December, social events such as weddings or haldi, celebrity styling ideas such as Tom Cruise’s look in Mission Impossible, pairing ideas such as “What to wear with pink Lehenga” etc.

Based on the nature of the query, customers will be shown up to six ensemble options, including products across multiple categories from topwear, bottomwear, footwear, and accessories to makeup, Myntra said.

Discover the stories of your interest

The AI-based assistant can keep refining its results as follow-up queries are posted by the user.While Myntra claims to be the first fashion and beauty ecommerce company to do this, others have already integrated ChatGPT’s technology for advanced search results. US-based grocery delivery app Instacart uses the technology to curate food-related queries.

The new product discovery feature is powered by OpenAI’s large language model, ChatGPT 3.5. The user search is sent to the ChatGPT model to fetch the looks for the user, creating appropriate prompts. The chatbot’s response is then processed by Myntra’s search ecosystem to show curated lists of products across multiple categories for the user’s selected look, the company said.

Going forward, Myntra plans to add voice search, conversational interaction (like talking to a sales assistant), and personalisation of outfit recommendations. For example, if a user is searching for party attire, the outfit’s recommendations will use the customers’ previous shopping history, styles and brand preferences as well as price points to show results. In addition, it will allow users to refine the results based on further inputs, in a conversational style.

Users can access the MyFashionGPT feature on the Myntra app via ‘M-Xplore’, the floating action button on the home page. Additionally, customers clicking the ‘search bar’ on the app to discover products will also see an option to try the MyFashionGPT feature.

“We are thrilled to introduce MyFashionGPT, our revolutionary ensemble suggestions feature powered by ChatGPT,” said Raghu Krishnananda, chief product and technology officer, Myntra. “It is a special launch as we are arguably the first fashion, beauty and lifestyle platform globally to roll out this feature to the entire customer base at this scale.