Log agents

When working with agents, it can become challenging to track the flow of the agent and its interactions with the environment. Opik provides a way to track both the agent definition and it’s flow.

Opik includes an integration with many popular Agent frameworks (LangGrah, LLamaIndex) and can also be used to log agents manually using the @track decorator.

Track agent execution

You can track the agent execution by using either one of Opik’s integrations or the @track decorator:

1
from opik.integrations.langchain import OpikTracer
2
3
# create your LangGraph graph
4
graph = ...
5
app = graph.compile(...)
6
7
opik_tracer = OpikTracer(graph=app.get_graph(xray=True))
8
9
# Pass the OpikTracer callback to the Graph.stream function
10
for s in app.stream({"messages": [HumanMessage(content = QUESTION)]},
11
                    config={"callbacks": [opik_tracer]}):
12
    print(s)
13
14
# Pass the OpikTracer callback to the Graph.invoke function
15
result = app.invoke({"messages": [HumanMessage(content = QUESTION)]},
16
                    config={"callbacks": [opik_tracer]})

Once the agent is executed, you will be able to view the execution flow in the Opik dashboard. In the trace sidebar, you will be able to view each step that has been executed in chronological order:

Track the agent definition

If you are using out LangGraph integration, you can also track the agent definition by passing in the graph argument to the OpikTracer callback:

1
from opik.integrations.langchain import OpikTracer
2
3
# Graph definition
4
5
opik_tracer = OpikTracer(graph=app.get_graph(xray=True))

This allows you to view the agent definition in the Opik dashboard: