In a previous blog post, we built a small Python application that queries Elasticsearch using a mix of vector search and BM25 to help find the most relevant results in a proprietary data set. The top hit is then passed to OpenAI, which answers the question for us. In this blog, we will instrument a Python application that uses OpenAI and analyze its performance, as well as the cost to run the application.

At Traceloop, we’re solving the single thing engineers hate most: writing tests for their code. More specifically, writing tests for complex systems with lots of side effects, such as this imaginary one, which is still a lot simpler than most architectures I’ve seen: As you can see, when an API call is made to a service, there are a lot of things happening asynchronously in the backend; some are even conditional.

Generative Artificial Intelligence (AI) is commanding conversations these days, a never-before-seen system that’s captured many millions of users since its debut in November 2022. A machine learning innovation that creates content of all kinds (and that’s just the beginning), generative AI also comes up with new product designs and optimizes business processes. We have only begun to exploit and understand this disruption.

Generative AI projects like ChatGPT have motivated enterprises to rethink their AI strategy and make it a priority. In a report published by PwC, 72% of respondents said they were confident in the ROI of artificial intelligence. More than half of respondents also state that their AI projects are compliant with applicable regulations (57%) and protect systems from cyber attacks, threats or manipulations (55%). Production-grade AI initiatives are not an easy task.

Earlier this month, we released the first version of our new natural language querying interface, Query Assistant. People are using it in all kinds of interesting ways! We’ll have a post that really dives into that soon. However, I want to talk about something else first. There’s a lot of hype around AI, and in particular, Large Language Models (LLMs).

Honeycomb recently released our Query Assistant, which uses ChatGPT behind the scenes to build queries based on your natural language question. It's pretty cool. While developing this feature, our team (including Tanya Romankova and Craig Atkinson) built tracing in from the start, and used it to get the feature working smoothly. Here's an example. This trace shows a Query Assistant call that took 14 seconds. Is ChatGPT that slow? Our traces can tell us!

Azure OpenAI is a service for deploying AI applications on Azure resources. With its easy-to-use REST APIs, you can leverage the service to access OpenAI’s powerful language models, such as ChatGPT, for your applications while taking advantage of the reliability and security of the Azure platform. Datadog already offers an out-of-the-box integration for OpenAI so you can monitor key performance trends, such as API usage patterns, token consumption, and more.

Five worthy reads is a regular column on five noteworthy items we have discovered while researching trending and timeless topics. This week, we explore the amalgamation of the rapidly evolving world of artificial intelligence (AI) in cryptocurrency. Designed by Dhanwant Kumar The world of cryptocurrency has come a long way since the introduction of Bitcoin in 2009. Today, there are thousands of cryptocurrencies available, each with unique features and scenarios.