AI-powered assistant accelerates engineering queries for NUMA Innovation

NUMA Innovation provides advanced simulation and analysis services across fluid dynamics, heat transfer, stress analysis, and numerical code development, supporting clients in tackling complex engineering challenges using open-source tools like OpenFOAM.

The Challenge

To support its technical simulations and code customisations, NUMA Innovation regularly refers to dense OpenFOAM documentation. Searching for relevant information manually was time-consuming and inefficient. While aware of commercial AI tools, the team needed a domain-specific solution that maintained full control over sensitive data and could deliver accurate, engineering-grade responses without relying on external APIs.

The Solution

Working with the Hartree Centre’s Northern Ireland team, NUMA co-developed a secure, local Retrieval-Augmented Generation (RAG) assistant using open-source technologies. The system integrates:

  • Ollama for running fine-tuned language models locally.
  • Docker for hosting internal documentation and creating a semantic search vector database.
  • OpenWebUI for easy document uploads and interaction with the assistant.

After testing multiple models, one of the LLMs was selected for its strong performance in understanding C++-based OpenFOAM queries and low hardware requirements. The AI assistant is fully offline, ensuring total data security and control.

logo-1

Dr Ronan Flanagan, NUMA Innovation

“Working with Hartree has been very rewarding from the initial information day through to delivery of the final results. They have been very knowledgeable and supportive throughout the full project and we have learnt a lot about the broad field of machine learning and AI. We would recommend partnering with Hartree for AI research activities and we will look forward to collaborating again in the future when the opportunity arises.”


Project Impact

NUMA’s new local AI assistant delivers instant, trusted answers to technical queries, improving efficiency and reducing dependency on external AI services. Key outcomes include:

  • Faster access to configuration and code guidance
  • Improved accuracy from using trusted internal sources
  • Full data privacy through offline deployment
  • Cost savings by avoiding third-party subscriptions
  • A scalable foundation for future AI-driven CAE tools

The collaboration demonstrates how Generative AI can be responsibly applied to support specialist engineering workflows and enhance internal productivity.

Further Information

This work was completed as one of our data projects. Our projects are up to 12 weeks in duration. We will work alongside your business to scope your project, demonstrate proof of concept, and explore options to deploy it within your business. If you would like to learn more about the Hartree Centre Northern Ireland Hub and our Programme, please get in touch with us at: info@hartreeni.uk

Our Impact on UK Industry and Society

The Hartree National Centre for Digital Innovation enables businesses to acquire the skills, knowledge and technical capability required to adopt digital technologies like super computing, data analytics, artificial intelligence (AI) and quantum computing. The SME Engagement Hubs play a key role in offering targeted support for business challenges in their region, creating value and generating economical and societal impact for the UK.