Open Deep Search (ODS) is an open-source framework designed to bridge the gap between proprietary AI search solutions and their open-source counterparts.
Companies like Google, Perplexity AI, Microsoft, and OpenAI are developing sophisticated 'Search AI' or 'Answer Engines' powered by Large Language Models (LLMs).
Perplexity AI's Sonar Reasoning Pro and OpenAI's GPT-4o Search Preview are closed-source systems, restricting innovation and transparency.
ODS, developed by researchers from Sentient, University of Washington, Princeton University, and UC Berkeley, challenges proprietary systems and achieves state-of-the-art performance on benchmarks.