New Relic, the observability platform, has launched a Machine Learning Operations (MLOps) capability that allows engineering teams to monitor applications built with OpenAI’s GPT series APIs. With just two lines of code, engineering teams can monitor OpenAI completion queries while simultaneously tracking performance and cost metrics in real-time in a single view with New Relic.
The integration will allow New Relic to ingest raw OpenAI data and help companies leverage the power of emerging AI technologies like OpenAI’s ChatGPT to accelerate innovation and business goals while balancing considerations to cost. This integration expands New Relic’s catalogue of supported data and extends New Relic’s access to a wider audience of developers.
New Relic Chief Growth Officer and GM of Observability Manav Khurana said, “This is an exciting time for companies who are embracing GPT and building modern applications with Generative AI. Observability is a game changer when it comes to helping companies extract value from GPT. We are making it so that any engineer using GPT APIs can easily monitor their cost and performance with easy set-up and at no cost. This aligns with our mission to put the power of observability into the hands of every engineer.”
Companies around the world are embracing GPT to power help desk tickets and live chat logs, develop content and images, and accelerate semantic searches. New Relic monitoring for OpenAI is fast, easy to use, and unlocks real-time metrics that can help engineering teams optimise usage, reduce costs, and achieve better results.
The new capability allows engineers to get started for free with access to New Relic Instant Observability and the out-of-the-box GPT monitoring solution. Easy installation is also guaranteed. With just two lines of code, users can import the monitor module from the nr_openai_monitor library and automatically generate a dashboard that displays a variety of key GPT performance metrics.
New Relic also offers real-time cost tracking of GPT usage. Usage of OpenAI’s Davinci model costs can add up quickly and make it difficult to operate at scale. New Relic provides engineering teams with real-time cost tracking of their GPT usage. In addition, New Relic gives engineering teams insight into the average response time and other key performance metrics around GPT requests, allowing engineers to optimise usage and ensure the best possible response times.
New Relic provides valuable information about the usage, speed, and effectiveness of GPT to help engineering teams achieve better results from their ML models. The OpenAI GPT integration with New Relic is included at no additional cost to New Relic full platform users. New Relic supports all current OpenAI GPT versions including the recently released GPT-4.
For more information on how to set-up New Relic MLOps or integrate GPT applications in observability infrastructure, visit the New Relic documentation here.