Instrumenting BeeAI with OpenInference
Explore how to add traceability to your custom Agent
Overview
To enable full observability for your BeeAI agents, you can instrument them using OpenInference, follow the steps below for both Python and JavaScript frameworks. These instructions will guide you through the installation and setup of OpenInference instrumentation, enabling you to capture and export telemetry data effectively.
⚠️ Note: This guide only covers frameworks that are officially supported by the OpenInference ecosystem. If a framework is not part of OpenInference, we do not provide instrumentation guidance for it.
Be sure you have already run the Phoenix server. See the Agent Traceability site for more details.
Python Instrumentation example
- Install Required Packages: Begin by installing the necessary packages:
- Instrument BeeAI Framework: Apply the OpenInference instrumentation to the BeeAI framework:
- Use BeeAI as Usual: Proceed with your standard BeeAI agent implementations. The instrumentation will automatically capture and export relevant telemetry data.
See OpenInference Instrumentation for BeeAI on how to run the instrumentation outside of the BeeAI.
JavaScript Instrumentation example
- Install Required Packages: Begin by installing the necessary packages:
- Instrument BeeAI Framework: Apply the OpenInference instrumentation to the BeeAI framework:
- Use BeeAI as Usual: Proceed with your standard BeeAI agent implementations. The instrumentation will automatically capture and export relevant telemetry data.
See OpenInference Instrumentation for BeeAI on how to run the instrumentation outside of the BeeAI.