talk-data.com

As part of its missions, the Ministry of Culture aims to centralize the diverse data it manages. How can a platform be designed to host and distribute management, heritage, and decision-making data? What architecture choices were made considering the constraints? How does the search engine integrate into this platform, providing performance and smooth access? This is the story we will share, presented as a case study with practical insights.

As part of its missions, the Ministry of Culture aims to centralize the diverse data it manages. How can a platform be designed to host and distribute management, heritage, and decision-making data? What architecture choices were made considering the constraints? How does the search engine integrate into this platform, providing performance and smooth access? This is the story we will share, presented as a case study with practical insights.

Le moteur de recherche est au cœur de l’expérience utilisateur. Mais comment passer d’une recherche « classique » basée sur des mots-clés à une recherche sémantique capable de comprendre réellement les intentions ? Dans cette session, l’équipe The Fork partagera leur projet d’évolution vers une recherche augmentée par l’IA. En s’appuyant sur leur stack OpenSearch existante, ils ont ajouté une couche sémantique grâce aux LLM. L’objectif : analyser les requêtes utilisateurs, en extraire les éléments essentiels et les traduire en une recherche sémantique beaucoup plus pertinente. Vous découvrirez les défis rencontrés, les choix d’implémentation et les résultats obtenus dans un cas concret à fort impact utilisateur.

Search engines are at the heart of the user experience. But how do you move from a “classic” keyword-based search to a semantic search that truly understands user intent? In this session, The Fork team will share their journey toward evolving into an AI-augmented search. Building on their existing OpenSearch stack, they added a semantic layer powered by LLMs. The goal: analyze user queries, extract the key elements, and translate them into a much more relevant semantic search. You’ll discover the challenges they faced, the implementation choices, and the real-world results achieved in a high-impact user case.