AquiLLM

Research groups face persistent challenges in capturing, storing, and retrieving knowledge that is distributed across team members. Although structured data intended for analysis and publication is often well managed, much of a group's collective knowledge remains informal, fragmented, or undocumented—often passed down orally through meetings, mentoring, and day-to-day collaboration. This includes private resources such as emails, meeting notes, training materials, and ad hoc documentation. Together, these reflect the group's tacit knowledge—the informal, experience-based expertise that underlies much of their work. Accessing this knowledge can be difficult, requiring significant time and insider understanding. Retrieval-augmented generation (RAG) systems offer promising solutions by enabling users to query and generate responses grounded in relevant source material. However, most current RAG-LLM systems are oriented toward public documents and overlook the privacy concerns of internal research materials. We introduce AquiLLM, a lightweight, modular RAG system designed to meet the needs of research groups. AquiLLM supports varied document types and configurable privacy settings, enabling more effective access to both formal and informal knowledge within scholarly groups.

Data Types - Research groups generate a range of data, from publications and pulibc datasets that are formally published to informal data products like presentations, meeting notes, plots, etc. The informal data is just as important for the daily function of groups, but are difficult to capture and used. AquiLLM seeks to integrate both formal and informal data products while respecting the different levels of privacy that maybe necessary with non-public data.

Architecture - AquiLLM is composed of a Django backend with custom LLM, tool calling and RAG integration logic, a front end composed of Django templates, many of which contain React components, and external services: the database, object storage, and LLM inference API. AquiLLM’s focus on easy deployment and maintenance for small teams drove a number of technical choices.

For more details about the implementations and initial findings, see our research paper: "AquiLLM: a RAG Tool for Capturing Tacit Knowledge in Research Groups" by Chandler Campbell, Bernie Boscoe, and Tuan Do for presentation at USRSE 2025.