In the dynamic landscape of software development, the adoption of DevOps has become a cornerstone for organizations aiming to deliver high-quality products at a rapid pace. DevOps, a fusion of development and operations, emphasizes collaboration, communication, and automation throughout the entire software development lifecycle.

In part 1 of this tutorial, we showed you how to build a large language model (LLM) application that uses retrieval-augmented generation (RAG) to query your own documentation and then test it using a CircleCI continuous integration (CI) pipeline.

Bitbucket Cloud is excited to introduce a new feature to streamline the way you communicate pull request feedback to your colleagues. You now have the option on pull requests to batch comments into a single review. By doing this, you submit all your feedback at once, letting other PR participants know – with a single email notification – that you have finished your code review.

In the swiftly evolving tech world, the need for agile and efficient development processes is paramount. This was the essence of our enlightening event, "Creating Ephemeral Environments for CI/CD Pipelines with Kubernetes," which garnered an impressive turnout of over 650 attendees. The event, now available on Youtube, focused on the transformative potential of ephemeral environments in modern CI/CD pipelines.

Kubernetes, often abbreviated as K8s, has revolutionised the way we manage containerized applications. It provides a robust platform for orchestrating and managing containers at scale. One of the key features that sets Kubernetes apart is its powerful metadata system, which includes labels and annotations. In this blog post, we’ll take a comprehensive look at how labels and annotations work in Kubernetes and how you can leverage them to enhance the management of your applications.

Generative AI has already shown its huge potential, but there are many applications that out-of-the-box large language model (LLM) solutions aren’t suitable for. These include enterprise-level applications like summarizing your own internal notes and answering questions about internal data and documents, as well as applications like running queries on your own data to equip the AI with known facts (reducing “hallucinations” and improving outcomes).