Skip to main content
DSPy traces can include module inputs, outputs, prompts, completions, and optimizer data. Review Data Governance before enabling production traffic.

​
Install

pip install dspy-ai openinference-instrumentation-dspy \
            opentelemetry-sdk opentelemetry-exporter-otlp-proto-http

​
Setup

import os, dspy
from openinference.instrumentation.dspy import DSPyInstrumentor
from openinference.instrumentation import using_attributes
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter

os.environ["OTEL_EXPORTER_OTLP_ENDPOINT"] = "https://otel.agnost.ai"
os.environ["OTEL_EXPORTER_OTLP_HEADERS"] = "X-Agnost-Org-ID=<your-org-id>"

provider = TracerProvider()
provider.add_span_processor(BatchSpanProcessor(OTLPSpanExporter()))
trace.set_tracer_provider(provider)
DSPyInstrumentor().instrument(tracer_provider=provider)

dspy.settings.configure(lm=dspy.LM("openai/gpt-4o-mini"))
qa = dspy.Predict("question -> answer")

with using_attributes(session_id="sess-123", user_id="u-42"):
    qa(question="What is OTel?")
Module/program/optimizer spans nest properly and carry dspy.module, dspy.signature, plus standard OpenInference input.value / output.value. Pair with a provider instrumentation (e.g. OpenAIInstrumentor) for the deepest trace tree.

​
Alternative: MLflow

If you already use MLflow, mlflow.dspy.autolog() works too: Agnost reads mlflow.spanInputs / mlflow.spanOutputs.

​
Verify

Run one DSPy module call, then open Raw logs in Agnost. Confirm dspy.module and input/output attributes are present.

​
Troubleshooting

  • Instrument DSPy before calling modules.
  • Pair DSPy instrumentation with provider instrumentation if you need LLM-level spans.
  • Confirm OTEL_EXPORTER_OTLP_HEADERS contains X-Agnost-Org-ID=<your-org-id>.

​
References