Skip to main content
Automatically capture module executions, signature predictions, and underlying LLM calls in DSPy programs.

​
Setup

import traceroot
from traceroot import Integration

traceroot.initialize(integrations=[Integration.DSPY])

​
Usage

Once initialized, every DSPy module call and underlying LLM request is traced automatically: 
import dspy
import traceroot
from traceroot import Integration

traceroot.initialize(integrations=[Integration.DSPY])

# DSPy resolves the API key from OPENAI_API_KEY in the environment.
dspy.configure(lm=dspy.LM("openai/gpt-4o-mini", max_tokens=1024))


class CoTQA(dspy.Module):
    """Chain-of-thought question-answering module."""

    def __init__(self):
        super().__init__()
        self.cot = dspy.ChainOfThought("question -> answer")

    def forward(self, question: str):
        return self.cot(question=question)


qa = CoTQA()

# The forward call, the chain-of-thought step, and the LLM call are all captured
result = qa(question="Why does ice float on water?")
print(result.reasoning)
print(result.answer)

traceroot.flush()

​
What Gets Captured

AttributeDescription
Module callsEach Module.__call__ / Module.forward invocation
PredictorsPredict, ChainOfThought, ReAct, etc. as nested spans
SignaturesInput/output fields declared on each signature
LLM callsRaw completion requests to the configured dspy.LM
Tokens & CostAggregated token usage and pricing
LatencyDuration per module call and per LLM call

​
Run the example

Clone the repo and run a complete agent end-to-end.

Python

Run the Python example