
RegRag: Enhancing Software Release Management through Retrieval-Augmented LLMs
- Project
- 20023 SmartDelta
- Type
- New product
- Description
This tool provides retrieval-augmented domain-specific chatbots to enable better release management. The tool provides a question-answering chatbot, ReqRAG, leveraging Retrieval Augmented Generation (RAG) with Large Language Models (LLMs) to deliver accurate and up-to-date information from internal technical documents in response to given queries.
- Contact
- Muhammad Abbas (RISE)
- abbas.khan@ri.se
- Research area(s)
- Large Language Models, Information retrieval, Release Management
- Technical features
A question-answering chatbot, ReqRAG, leveraging Retrieval Augmented Generation (RAG) with Large Language Models (LLMs) to deliver accurate and up-to-date information from technical documents in response to given queries. We employ various context retrieval techniques paired with state-of-the-art LLMs and have evaluated the application of ReqRAG chatbot in industrial settings. Our results indicate that, on average, 70% of the generated responses are adequate, useful, and relevant to the practitioners.
- Integration constraints
N/A
- Targeted customer(s)
Engineers often need to refer back to release notes, manuals, and system architecture documents to understand, modify, or upgrade functionalities in alignment with new software releases. This is crucial to ensure that new stakeholder requirements align with the existing system, maintaining compatibility and preventing integration issues
- Conditions for reuse
Contact for licensing information
- Confidentiality
- Public
- Publication date
- 11-03-2025
- Involved partners
- RISE - Research institutes of Sweden (SWE)
- ALSTOM Rail Sweden AB (SWE)