Trip.com Group
Hotel search
Queries for "night view" missed "scenic evenings." AI now matches intent across 1.2M properties in <100ms, regardless of phrasing.
- <100ms P99.9 search latency for travelers
- Thousands of landing pages automated via AI
Legacy keyword search failed on typos and vague queries. Now, semantic AI interprets natural language and images to find exact items.
Latin America's fastest-growing on-demand delivery app operates across more than 300 cities, connecting users with extensive retail and restaurant catalogs.
The legacy keyword-based search engine struggled to process vague queries, misspelled words, or low-interaction keywords that lacked semantic...
“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.”
Multi-vertical super-app for on-demand delivery, fintech, and travel services.
Worked with Rappi to migrate its on-demand delivery platform to Oracle AI solutions.
Enterprise database software and cloud infrastructure services.
Rappi's Product search is part of this use case:
Related implementations across industries and use cases
Queries for "night view" missed "scenic evenings." AI now matches intent across 1.2M properties in <100ms, regardless of phrasing.
Guests spent 40 hours planning trips using rigid search menus. Now, AI matches natural language queries to live flights and loyalty data.
Messy ingredient data broke text search, capping matches at 20%. AI semantic search now maps free-form inputs to unlock recipe imports.
Queries for "night view" missed "scenic evenings." AI now matches intent across 1.2M properties in <100ms, regardless of phrasing.
Messy ingredient data broke text search, capping matches at 20%. AI semantic search now maps free-form inputs to unlock recipe imports.
Rate limits capped geocoding at 2,000 requests/min. A fine-tuned LLM now clears 8,000/min—cutting costs by 80%.
Time zones bottlenecked competitive intel for global sales. Now, an AI Slack agent delivers vetted talking points and charts on demand.
Protecting users from harmful on-device AI required internet. A powerful safety AI now runs directly on the PC, guarding users even when offline.
A 200% yearly data expansion bottlenecked global operations. Now, AI accelerates coding, drafts recipe cards, and resolves inquiries.
Legacy keyword search failed on typos and vague queries. Now, semantic AI interprets natural language and images to find exact items.
Latin America's fastest-growing on-demand delivery app operates across more than 300 cities, connecting users with extensive retail and restaurant catalogs.
The legacy keyword-based search engine struggled to process vague queries, misspelled words, or low-interaction keywords that lacked semantic...
“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.”
Multi-vertical super-app for on-demand delivery, fintech, and travel services.
Worked with Rappi to migrate its on-demand delivery platform to Oracle AI solutions.
Enterprise database software and cloud infrastructure services.
Rappi's Product search is part of this use case:
Related implementations across industries and use cases
Queries for "night view" missed "scenic evenings." AI now matches intent across 1.2M properties in <100ms, regardless of phrasing.
Guests spent 40 hours planning trips using rigid search menus. Now, AI matches natural language queries to live flights and loyalty data.
Messy ingredient data broke text search, capping matches at 20%. AI semantic search now maps free-form inputs to unlock recipe imports.
Queries for "night view" missed "scenic evenings." AI now matches intent across 1.2M properties in <100ms, regardless of phrasing.
Messy ingredient data broke text search, capping matches at 20%. AI semantic search now maps free-form inputs to unlock recipe imports.
Rate limits capped geocoding at 2,000 requests/min. A fine-tuned LLM now clears 8,000/min—cutting costs by 80%.
Time zones bottlenecked competitive intel for global sales. Now, an AI Slack agent delivers vetted talking points and charts on demand.
Protecting users from harmful on-device AI required internet. A powerful safety AI now runs directly on the PC, guarding users even when offline.
A 200% yearly data expansion bottlenecked global operations. Now, AI accelerates coding, drafts recipe cards, and resolves inquiries.