Search papers, labs, and topics across Lattice.
The paper introduces AI-VERDE, a platform designed to provide academic institutions with unified access to various LLMs (commercial, cloud-hosted, and on-premise) while addressing access control, privacy, RAG, and budget management. AI-VERDE simplifies LLM integration for instruction and research, offering both a web interface and API access. A pilot deployment at a large public university showed high engagement, suggesting the platform effectively lowers barriers to LLM utilization in educational settings.
Democratizing LLM access in academia just got easier: AI-VERDE offers a unified platform for managing commercial, cloud, and on-premise models with built-in access control, RAG, and budget management.
We present AI-VERDE, a unified LLM-as-a-platform service designed to facilitate seamless integration of commercial, cloud-hosted, and on-premise open LLMs in academic settings. AI-VERDE streamlines access management for instructional and research groups by providing features such as robust access control, privacy-preserving mechanisms, native Retrieval-Augmented Generation (RAG) support, budget management for third-party LLM services, and both a conversational web interface and API access. In a pilot deployment at a large public university, AI-VERDE demonstrated significant engagement across diverse educational and research groups, enabling activities that would typically require substantial budgets for commercial LLM services with limited user and team management capabilities. To the best of our knowledge, AI-Verde is the first platform to address both academic and research needs for LLMs within an higher education institutional framework.
