Automated Code generation for Information Technology Tasks in YAML through Large Language Models
It addresses a gap in code generation for domain-specific languages in IT automation, which is incremental as it adapts existing methods to a new domain.
This paper tackles the problem of generating Ansible-YAML code for IT automation from natural language prompts, presenting Ansible Wisdom, a transformer-based model that achieves a BLEU score of 66.67, outperforming larger models like Codex-Davinci-002 with a BLEU score of 50.4.
The recent improvement in code generation capabilities due to the use of large language models has mainly benefited general purpose programming languages. Domain specific languages, such as the ones used for IT Automation, have received far less attention, despite involving many active developers and being an essential component of modern cloud platforms. This work focuses on the generation of Ansible-YAML, a widely used markup language for IT Automation. We present Ansible Wisdom, a natural-language to Ansible-YAML code generation tool, aimed at improving IT automation productivity. Ansible Wisdom is a transformer-based model, extended by training with a new dataset containing Ansible-YAML. We also develop two novel performance metrics for YAML and Ansible to capture the specific characteristics of this domain. Results show that Ansible Wisdom can accurately generate Ansible script from natural language prompts with performance comparable or better than existing state of the art code generation models. In few-shot settings we asses the impact of training with Ansible, YAML data and compare with different baselines including Codex-Davinci-002. We also show that after finetuning, our Ansible specific model (BLEU: 66.67) can outperform a much larger Codex-Davinci-002 (BLEU: 50.4) model, which was evaluated in few shot settings.