Results of the QAChat AMOS Project with QAware (Video and Report, Summer 2023 Project)
This project is one of five Scrum projects with industry partners that were part of the Summer 2023 AMOS Projects. Below please find the video (you may also like the other videos) and the project summary which details the final result of the project. We run these projects every semester, so please be in touch if you would like to motivate one of your own!
|Project mission||QAchat evaluates newly developed LLMs to create a chatbot that provides users with accurate, reliable and context-specific answers to their questions – with a focus on accessibility and ease of use. The best suited network is trained on provided data that is collected from existing communication and documentation sources. The model is made available to users through a Slackbot integration, where questions can be asked and answers are provided.|
|Project summary||We created a chatbot on Slack that can respond with company-specific information. This chatbot is able to respond in a variety of languages, including German and English. The chatbot can retrieve data from different platforms such as Confluence, Slack and Google Drive. It is also possible to exclude certain data sources, which are specified in a configurable blacklist. All parts can be fully automated and run on a configurable schedule. Our service complies with corporate security policies, as our chatbot can run locally or on any cloud provider.|
|Additional information||Our project is modular, so we can integrate also more data sources such as:|
– Project management poster
– Software developer poster