AI-driven assistance can enhance developer experience and productivity and optimize overall software delivery performance.
Generative AI is being used to expand the use of large language models to streamline time-consuming tasks.
AI tools are not a replacement for traditional tools and processes but instead provide more nuanced commentary on code quality.
Gemini models in Vertex AI can be used to build a custom extension of a CI/CD pipeline that uses Gemini’s language and text generation capabilities.
Friendly-cicd-helper is a small demo tool that abstracts the mechanics of interacting with the Gemini APIs in Vertex AI.
A Cloud Build pipeline can be triggered when a developer opens a merge request in Gitlab.
The pipeline builds a container image with the updated code and deploys the application to a QA environment using Cloud Deploy.
In the pipeline, Gemini is used to generate an automated code review of our merge request and generating suggested release notes that describe the contained changes in the MR.
The practical example shows how to leverage Gemini models in Vertex AI within a continuous delivery pipeline to support code reviews and generate release notes for pull requests.
Automated AI tooling in a CI/CD pipeline can help streamline time-consuming tasks, reduce cognitive load and free up developer's time.