PDFs are packed with text, tables, and images, but extracting insights from them isn’t easy. Traditional methods involve multiple components like OCR and task-specific models—making them complex and hard to scale. Vision-Language Models like ColPali simplify this by representing all modalities in a unified format.In this session, you’ll see how ColPali can be combined with OpenSearch to enable conversational search over rich PDF content. We’ll also showcase a live demo to bring this concept to life.

Dans cette session, nous allons voir comment fonctionne OpenSearch pour le vector search et quelle stratégie utiliser pour optimiser et gagner en performance et réduire la latence.