Observability for Agno with Opik

Agno is a lightweight, high-performance library for building AI agents.

Agno’s primary advantage is its minimal overhead and efficient execution, making it ideal for production environments where performance is critical while maintaining simplicity in agent development.

Getting started

To use the Agno integration with Opik, you will need to have the following packages installed:

$ pip install -U agno openai opentelemetry-sdk opentelemetry-exporter-otlp openinference-instrumentation-agno yfinance

In addition, you will need to set the following environment variables to configure the OpenTelemetry integration:

Opik Cloud

Enterprise deployment

Self-hosted instance

If you are using Opik Cloud, you will need to set the following environment variables:

$ export OTEL_EXPORTER_OTLP_ENDPOINT=https://www.comet.com/opik/api/v1/private/otel
$ export OTEL_EXPORTER_OTLP_HEADERS='Authorization=<your-api-key>,Comet-Workspace=default'

To log the traces to a specific project, you can add the projectName parameter to the OTEL_EXPORTER_OTLP_HEADERS environment variable:

$ export OTEL_EXPORTER_OTLP_HEADERS='Authorization=<your-api-key>,Comet-Workspace=default,projectName=<your-project-name>'

You can also update the Comet-Workspace parameter to a different value if you would like to log the data to a different workspace.

Using Opik with Agno

The example below shows how to use the Agno integration with Opik:

1 from agno.agent import Agent
2 from agno.models.openai import OpenAIChat
3 from agno.tools.yfinance import YFinanceTools
4 from openinference.instrumentation.agno import AgnoInstrumentor
5 from opentelemetry import trace as trace_api
6 from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
7 from opentelemetry.sdk.trace import TracerProvider
8 from opentelemetry.sdk.trace.export import SimpleSpanProcessor
9 
10 # Configure the tracer provider
11 tracer_provider = TracerProvider()
12 tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter()))
13 trace_api.set_tracer_provider(tracer_provider=tracer_provider)
14 
15 # Start instrumenting agno
16 AgnoInstrumentor().instrument()
17 
18 # Create and configure the agent
19 agent = Agent(
20     name="Stock Price Agent",
21     model=OpenAIChat(id="gpt-4o-mini"),
22     tools=[YFinanceTools()],
23     instructions="You are a stock price agent. Answer questions in the style of a stock analyst.",
24     debug_mode=True,
25 )
26 
27 # Use the agent
28 agent.print_response("What is the current price of Apple?")

Further improvements

If you would like to see us improve this integration, simply open a new feature request on Github.