Qt introduces AI Assistant for cross-platform UI development

Qt Group is introducing the Qt AI Assistant to streamline cross-platform UI development by minimising tasks that do not require active coding.

The AI Assistant is designed to provide guidance on developing application UIs using the Qt framework and automates routine tasks such as writing unit test cases, documenting code, and generating repetitive code segments. While the tool predominantly focuses on QML and Qt Quick use cases from the Qt framework, it is compatible with other programming languages such as C++ and Python.

Developers using the Qt AI Assistant will be able to integrate their chosen language models into the workflow, including options to self-host these models, thereby reducing dependency on third-party AI services. The AI Assistant is pre-configured for a range of language models, including Claude 3.5 Sonnet, OpenAI GPT-4o, Llama 3.3 70B QML, Code Llama 13B QML, and Code Llama 7B.

"We've been hearing from developers that they're increasingly spending time on tedious tasks that don't involve coding. Qt AI Assistant is part of our efforts to correct that. We want to eliminate the chores in developers' day-to-day, because software development should be about writing great code," says Peter Schneider, Senior Product Lead at Qt Group. "The industry has been buzzing with AI announcements – everyone's got their favourite language model, and we don't want to take that away from anyone. It was important that we support an open approach and allow enterprises to freely choose their preferred LLM deployment method."

The AI Assistant allows developers to direct various content generation activities to different models, ensuring that code suggestions are produced by the most suitable model for the programming language in use. This separation allows developers full control over which LLMs they use, without being constrained by third-party provider limitations.

Addressing security concerns, particularly for embedded devices and high-end desktop applications, the AI Assistant enables private cloud deployments of language models. This prevents code from being exposed to external threats and protects intellectual property. Developers also have the option to operate the AI Assistant manually to minimise disruptions.

"Our mission is to help customers increase productivity throughout the product development lifecycle," says Juhapekka Niemi, Senior Vice President, Product Management, at Qt Group. "Qt AI Assistant is an important step towards our vision of enabling rapid UI development and reducing project timelines from months to weeks, and eventually days."

Qt Group plans to release fine-tuned language models later this year, including the Llama 3.3 70B and Code Llama 13B, which have been trained on over 4,000 human-validated QML code examples. These models will be made available for free on the Hugging Face portal, providing additional resources for open-source Qt developers wishing to leverage third-party assistants.