Welcome to part three of our series on using Temporal to improve the reliability of applications built around LLMs like the one that powers ChatGPT. In part one, you learned how to use Temporal to clone a repo and ingest its documentation into an RAG Database for use with your LLM. Part two taught you how to use context injection to give users more accurate answers to prompts made against that documentation. In this post, you’ll use Temporal and another LLM to automatically test the accuracy of your application’s answers to the prompts from part two.
Loading
Backend 
Welcome to part two of our series about using Temporal to improve the reliability of applications built around Large Language Models (LLM) like the one that powers ChatGPT. Part one explained how to build a Temporal Workflow to process a series of documents and make them accessible to your LLM. This post will show how to develop a Temporal Workflow to find documents relevant to a user’s query and supply them as context to a prompt sent to the LLM using Context Injection. You’ll also learn how Temporal's abstraction will make your application more reliable and make it easier for you to extend it with new features.
Kevin Phillips
Director of Backend Development
Backend
Taking advantage of the burgeoning AI trend, many of today's applications are built around AI tools like ChatGPT and other Large Language Models (LLMs). AI-optimized applications often have complex software pipelines for collecting and processing data with the LLM. Temporal provides an abstraction that can significantly simplify data pipelines, making them more reliable and accessible to develop. In this post, you’ll discover why you should use Temporal to build applications around LLMs.
Kevin Phillips
Director of Backend Development
Backend
Implementing Temporal Cloud can present challenges for organizations offering cloud services that may be used by the federal government. One of the largest buyers of cloud technology, the federal government requires cloud services to be certified by the Federal Risk and Authorization Management Program (FedRAMP®). Each Cloud Service Offering (CSO) must have an independent authorization.
Kevin Phillips
Director of Backend Development
Backend 
Are you tired of relying on Directed Acyclic Graphs (DAGs) for your workflow orchestration? Consider transitioning from Apache Airflow to Temporal. With a focus on scalability and fault tolerance, Temporal is the perfect solution for complex workflows. Migrating from Airflow to Temporal can improve error handling and even solve looming tech debt.
Emil Kais
Backend 
Deploying an updated version of Temporal workflow code can result in errors if there are non-deterministic changes to the code. Determinism is verified during the “replay“ process that rebuilds the last known state of an ongoing workflow in order to continue its execution. Rebuilding execution state enables Temporal to support long-sleeping workflows and reliably relocate workflow executions to another worker when one crashes.
Nils Lundquist
Javascript Software Consultant
Backend
Using cloud services is standard practice for most backend application architectures. When using cloud services, it is important to understand and control what data is leaving your network and being sent to the cloud. Temporal Cloud has great options available to ensure that data sent to and from the cloud is securely encrypted. This post will showcase how Temporal Cloud might interact with your infrastructure by default and how you can customize Temporal to prevent any user or business-related data from being sent to the cloud.
Emil Kais
Backend
Managing your own Temporal cluster is a daunting task. Between the four core services, the myriad of metrics to monitor, and a separate persistence service, it's a sizeable undertaking for any team. This post begins a new series that will review the work involved in hosting Temporal yourself and try to demystify it.
Nils Lundquist
Javascript Software Consultant
Backend
Bitovi’s Backend Consulting team has had the pleasure of working with Temporal for several different use cases over the last few years. Temporal has greatly simplified complex distributed systems and helped our team focus more on achieving business goals and to spend less time handling errors, among many other things. Temporal isn’t a silver bullet, but it is helpful in a variety of different situations.
Kevin Phillips
Director of Backend Development
Backend
A skill our Node.js Consulting team practices often is the process of breaking down new product requirements into actionable technical requirements. This is one of the most critical capabilities for a developer to learn in order to help their organization swiftly deliver new features to their users. In this post, we’ll talk through the process we use on our projects.
Kevin Phillips
Director of Backend Development
Backend 
With the phasing out of the popular datetime library Moment.js, one of our Node.js consulting clients wanted to prioritize finding a replacement. We ultimately chose to migrate to Day.js, a minimalist JavaScript library. Among the alternatives, Day.js offered many advantages, chief among them being that it is lightweight and the most syntactically close to Moment.js.
Nicole Greene