DocsGPT: Migrating One of the Industry’s Most Popular Open Source AI Assistants to Atlas Vector Search

Arc53, a company focused on building predictive AI/ML solutions since 2019, launched DocsGPT in response to the growing popularity of generative AI and the need for developers to incorporate their proprietary data into genAI models. DocsGPT is an open-source documentation assistant that enables developers to build conversational user experiences with NLP on top of their data. With over 14,000 GitHub stars and a vibrant community, it has been adopted by organizations such as the UK government's Department of Work and Pensions and nearly 20,000 other users. As part of its managed service, DocsGPT utilizes MongoDB Atlas due to its ability to handle high read and write throughput with transactional guarantees while providing seamless integration with vector search capabilities for real-time gen AI applications. The migration from Elasticsearch to MongoDB Atlas Vector Search enables users to store metadata, chat history, and user account information in a single platform accessed by a single API, streamlining the development of genAI apps with reduced cost and complexity. DocsGPT engineering team benefits from being part of the AI Innovators program, which provides free Atlas credits and access to technical expertise for their migration efforts.