American Institute of Physics – Conversational search
- OpenAI completions
- AI Strategy
- Solution design
- Application development
- Prompt tuning
Building a conversational search UI and RAG framework
Collaborating with our partner Mathison.ai, we implemented an AI-powered search interface for the American Institute of Physics (AIP). This enhancement allows researchers, students and physicists to explore the AIP’s published papers using natural language.
Understanding the challenge
The rapidly evolving field of Generative AI prompted the American Institute of Physics to delve into potential applications for their content catalogue. Their goal was to enhance the accessibility and consumption of relevant research through AI. To translate this into a real world experience for users, our approach involved developing a conversational search tool. The aim was to foster a more intuitive content discovery process, boosting both subscription and single article purchases.
Applying the right AI technologies
Teaming up with Matheson.ai, we developed a chat-based solution to semantically query the AIP content catalogue. The objective was to provide search results accompanied by generative summaries, underpinned by rigorous citation evidence. This innovative approach involved harnessing the capabilities of a Language Model (LLM) for generating embeddings, utilising a vector database for nearest neighbour matching and leveraging OpenAI's completions API to construct a Retrieve-Augmented Generation framework. The user interface, crafted with Next.js, boasts an elegant design that supports conversation histories, sharing features and feedback mechanisms. These components contribute to training the application for enhanced accuracy.
Spicerack swiftly responded to our RFP, with a comprehensive proposal that exceeded expectations. Their excellent and unusual partnership provides creative expertise and valuable guidance. They're advanced in their AI knowledge, open to new ideas and technologies, and a pleasure to work with - I can't recommend them highly enough.Founder, Mathison.ai