Rappi cuts search response times by 40% with Oracle AI solutions
Oracle AI Vector Search on Oracle Autonomous AI Database provides faster, highly personalized search results on company’s on-demand delivery app.
Colombia | High Technology
“By implementing Oracle AI Vector Search, we not only get lower latency, but we’ve also improved our conversion rate. Users are more engaged with the Rappi app to discover new products. At the end of the day, that means more orders that contribute to the growth of our business.”
Rappi, whose delivery app is the fastest-growing one in Latin America, wanted to upgrade its search engine to boost conversion rates, strengthen customer loyalty, and grow the business. The app’s previous keyword-based search couldn’t handle vague queries, misspelled words, or low-interaction keywords that lacked semantic meaning. Adopting Oracle Autonomous AI Database, Oracle AI Vector Search, and Oracle Cloud Infrastructure (OCI) Generative AI allowed Rappi to upgrade the app to more accurately decipher user intent and deliver faster and more relevant search results.
Why Rappi chose Oracle
Rappi chose Oracle AI solutions as its main data processing and storage platform based on its performance, reliability, and support for advanced AI capabilities. A key factor in the decision was that Oracle Autonomous AI Database and Oracle AI Vector Search would bring advanced AI capabilities to where the company’s data resides, eliminating the need to move data between platforms or specialty databases. Rappi also chose Oracle’s AI infrastructure because it could be used to easily vectorize the company’s extensive retail and restaurant catalogs, while also scaling to support millions of user queries per minute. Rappi views Oracle as a key partner in its AI evolution, choosing to support its move to Oracle’s AI infrastructure based on the organization’s technical expertise and ability to rapidly enable advanced AI use cases.
Results
Since Rappi migrated its platform to Oracle AI solutions, the app's latency has been reduced by 40% when delivering responses to user queries. Oracle AI Vector Search enables semantic search to power large language models in OCI Generative AI, a fully managed service that simplifies the administration of AI applications. This makes it possible for Rappi app users to interact with the company’s product catalog using natural language and image searches. AI Vector Search helps identify which products in Rappi’s catalog are best matched with a user’s search request based on underlying intent. Responses are delivered faster and are now more accurate and contextually relevant. Using Oracle AI solutions, Rappi has boosted its average order value and improved its conversion rate by 25%.
Partners
Rappi worked with its development partner, Marvik, as well as with the Oracle Customer Success Services and Cloud Lift Services teams, to migrate its on-demand delivery platform to Oracle AI.
About the company
Founded in 2015 as a grocery delivery service, Rappi now provides “anything, anywhere, anytime” delivery of a wide variety of products to its app users in more than 300 Latin American cities.