Over the past two years Qt has been working to embrace generative AI for enhanced coding capabilities within Qt Creator for Qt/QML/C++ applications. It started with GitHub Copilot integration and has been continuing well beyond that and today marks the debut of the Qt AI Assistant v0.9.
The Qt AI Assistant v0.9 release is designed to provide the latest AI-driven coding help for constructing Qt/C++ software. There is now local LLM support with this Qt AI Assistant via the CodeLlama-7B-QML and DeepSeekCoder v2 Lite language model support.
Qt also has published CodeLlama-7B-QML and CodeLlama-13B-QML as their fine-tuned models on HuggingFace and Ollama that is trained on additional QML code snippets.
Qt AI Assistant v0.9 also adds text streaming support for better handling of responses from large language models progressively as a text stream. Initial support has also been introduced for constructing Google Test tests with the help of AI. Furthermore, the Qt AI Assistant is also now able to generate inline code comments for QML and C++ code.
Those curious about Qt’s AI ambitions can learn more about this latest work via the Qt blog.