Contactez-nous Suivez-nous sur Twitter En francais English Language

Freely subscribe to our NEWSLETTER

Newsletter FR

Newsletter EN



New Relic Launches Industry’s OpenAI GPT-3 Observability Capability

March 2023 by Marc Jacob

New Relic announced a machine learning operations (MLOps) capability that allows engineering teams to monitor OpenAI GPT-3. 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. This new integration helps companies leverage the power of emerging AI technologies like ChatGPT to accelerate innovation and business goals while balancing considerations to cost. Engineers can quickly deploy the OpenAI quickstart from New Relic Instant Observability and access this capability for free with no credit card required and minimal setup by signing up for a forever free New Relic account.

Companies around the world are embracing GPT-3 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 optimize usage, reduce costs, and achieve better results. The new capability allows engineers to monitor:

● Get started for free: Access to New Relic Instant Observability and our out-of-the-box GPT-3 monitoring solution is the first of its kind, and included at no additional cost to all New Relic full platform users.
● Easy installation: 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-3 performance metrics.
● Monitor cost: Usage of OpenAI’s Davinci model costs $0.12 per 1000 tokens, which 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-3 usage.
● Optimize performance: New Relic gives engineering teams insight into the average response time and other key performance metrics around GPT-3 requests, allowing engineers to optimize usage and ensure the best possible response times.
● Analysis prompts and response: New Relic provides valuable information about the usage, speed, and effectiveness of GPT-3 to help engineering teams achieve better results from their ML models.

See previous articles


See next articles

Your podcast Here

New, you can have your Podcast here. Contact us for more information ask:
Marc Brami
Phone: +33 1 40 92 05 55

All new podcasts