Nemo Agent Toolkit simplifies building production-ready LLM applications by providing tools for creating, managing, and deploying agents. It offers features like memory management, tool usage, and observability, making it easier to integrate LLMs into real-world applications.
This article details the steps to move a Large Language Model (LLM) from a prototype to a production-ready system, covering aspects like observability, evaluation, cost management, and scalability.
OpenInference is a set of conventions and plugins that complements OpenTelemetry to enable tracing of AI applications, with native support from arize-phoenix and compatibility with other OpenTelemetry-compatible backends.
Version 3.0 of the popular open-source monitoring system Prometheus has been released, with enhancements focused on a new user interface, OpenTelemetry support, and other new features aimed at improving user experience and streamlining workflows.
This article discusses the benefits of a disaggregated observability (o11y) stack for modern distributed architectures, addressing issues of flexibility, high cost, and lack of autonomy in traditional solutions. It highlights key layers of a disaggregated stack — agents, collection, storage, and visualization — and suggests the use of systems like Apache Pinot and Grafana.
