This pilot tests how semantic search can improve access to the collection using locally hosted AI models.The work builds on an earlier prototype, where the National Museum was an early adopter of AI-based search. In this version, we test a fully local approach using our own models and infrastructure. The project is developed at the… Continue reading Semantic search in the collection using local AI
Category: AI
Finding the right resolution for image analysis
(By Tord Nilsen, Senior Advisor National Museum Norway) In our Semantic Search prototype, we have experienced some issues where the OpenAI GPT-4 Vision API sometimes will misinterpret images with low resolution. To avoid higher API costs than necessary, we have been sending images with a resolution of 256×256 pixels, but have observed that the API… Continue reading Finding the right resolution for image analysis
Semantic search in an online collection
THIS WAS FOR V1. READ ABOUT V2 HERE We are prototyping a new semantic search feature for Nasjonalmuseet’s online collection. This search method focuses on context and meaning within the image, and offers a different approach to exploring the objects in our collection from the conventional method of matching the user’s query against terms in… Continue reading Semantic search in an online collection