​
Overview

This example demonstrates how to use Weave by Weights & Biases (WandB) to log model calls from your Agno agent.

​
Code

import weave
from agno.agent import Agent
from agno.models.openai import OpenAIChat

# Create and configure the agent
agent = Agent(model=OpenAIChat(id="gpt-4o"), markdown=True, debug_mode=True)

# Initialize Weave with your project name
weave.init("agno")

# Define a function to run the agent, decorated with weave.op()
@weave.op()
def run(content: str):
    return agent.run(content)

# Use the function to log a model call
run("Share a 2 sentence horror story")

​
Usage

1

Install Weave

pip install agno openai weave
2

Authenticate with WandB

  • Go to WandB and copy your API key from here.
  • Enter your API key in the terminal when prompted, or export it as an environment variable:
export WANDB_API_KEY=<your-api-key>
3

Run the Agent

python cookbook/observability/weave_op.py

​
Notes

  • Initialization: Call weave.init("project-name") to initialize Weave with your project name.
  • Decorators: Use @weave.op() to decorate functions you want to log with Weave.