Show HN: Using Multimodal RAG and OpenAI GPT-4 Vision for Insurance Industry

3 points by kirkmarple 2 years ago · 0 comments · 1 min read

With OpenAI's release of their GPT-4 Vision model, it has opened up the ability to analyze visual content (images and videos) and gather insights, which was previously not possible with existing Large Language Models (LLMs).

We walkthrough how to build an image analysis pipeline and AI copilot for insurance companies with Graphlit, with just a few API calls, and no AI experience required.

No comments yet.