DSPy

DSPy Tracing Tutorial (Google Colab)

​

Prerequisites

• Python 3.10+
• An Arize AX account (sign up)
• An OPENAI_API_KEY from the OpenAI Platform

​

Launch Arize AX

1. Sign in to your Arize AX account.
2. From Space Settings, copy your Space ID and API Key. You will set them as ARIZE_SPACE_ID and ARIZE_API_KEY below.

​

Install

pip install arize-otel \
  openinference-instrumentation-dspy \
  openinference-instrumentation-litellm \
  dspy

​

Configure credentials

export ARIZE_SPACE_ID="<your-space-id>"
export ARIZE_API_KEY="<your-api-key>"
export ARIZE_PROJECT_NAME="dspy-tracing-example"
export OPENAI_API_KEY="<your-openai-api-key>"

​

Setup tracing

# instrumentation.py
import os

from arize.otel import register
from openinference.instrumentation.dspy import DSPyInstrumentor
from openinference.instrumentation.litellm import LiteLLMInstrumentor

tracer_provider = register(
    space_id=os.environ["ARIZE_SPACE_ID"],
    api_key=os.environ["ARIZE_API_KEY"],
    project_name=os.environ["ARIZE_PROJECT_NAME"],
)

DSPyInstrumentor().instrument(tracer_provider=tracer_provider)
LiteLLMInstrumentor().instrument(tracer_provider=tracer_provider)
print("Arize AX tracing initialized for DSPy.")

​

Run DSPy

# example.py

# Importing instrumentation first ensures tracing is set up
# before `dspy` is imported.
from instrumentation import tracer_provider

import dspy

# DSPy uses LiteLLM under the hood; LiteLLM reads OPENAI_API_KEY from env.
lm = dspy.LM("openai/gpt-5.5")
dspy.configure(lm=lm)


class BasicQA(dspy.Signature):
    """Answer questions concisely with a one-sentence factoid."""

    question = dspy.InputField()
    answer = dspy.OutputField()


qa = dspy.Predict(BasicQA)
result = qa(question="Why is the ocean salty?")

print(result.answer)

​

Expected output

Arize AX tracing initialized for DSPy.
The ocean is salty because rivers carry dissolved minerals from rocks and soil into the sea, where the water evaporates but the salts remain, accumulating over millions of years.

​

Verify in Arize AX

1. Open your Arize AX space and select project dspy-tracing-example.
2. You should see a new trace within ~30 seconds containing a DSPy Predict(BasicQA).forward parent span (the BasicQA signature) wrapping LiteLLM completion child spans with the prompt, response, and token usage attached.
3. If no traces appear, see Troubleshooting.

​

Check from the skill, CLI, or SDK

npx skills add Arize-ai/arize-skills

ax spans export "$ARIZE_PROJECT_NAME" --space "$ARIZE_SPACE_ID" \
  --limit 5 --stdout | jq 'length'

import os
from arize import ArizeClient

client = ArizeClient(api_key=os.environ["ARIZE_API_KEY"])
resp = client.spans.list(
    project=os.environ["ARIZE_PROJECT_NAME"],
    space=os.environ["ARIZE_SPACE_ID"],
    limit=5,
)
count = len(resp.spans)
print(
    f"{count} span(s) found" if count else "No spans yet — recheck setup"
)

// Reads ARIZE_API_KEY from the environment.
import { listSpans } from "@arizeai/ax-client";

const { data: spans } = await listSpans({
  project: process.env.ARIZE_PROJECT_NAME!,
  space: process.env.ARIZE_SPACE_ID!,
  limit: 5,
});
const count = spans.length;
console.log(
  count ? `${count} span(s) found` : "No spans yet — recheck setup",
);

client, err := arize.NewClient(
    arize.Config{APIKey: os.Getenv("ARIZE_API_KEY")},
)
if err != nil {
    log.Fatal(err)
}
resp, err := client.Spans.List(ctx, spans.ListRequest{
    Project: os.Getenv("ARIZE_PROJECT_NAME"),
    Space:   os.Getenv("ARIZE_SPACE_ID"),
    Limit:   5,
})
if err != nil {
    log.Fatal(err)
}
fmt.Printf("%d span(s) found\n", len(resp.Spans))

​

Troubleshooting

• No traces in Arize AX. Confirm ARIZE_SPACE_ID and ARIZE_API_KEY are set in the same shell that runs example.py. Enable OpenTelemetry debug logs with export OTEL_LOG_LEVEL=debug and re-run.
• DSPy spans appear but no LLM-call detail. DSPy delegates model calls to LiteLLM; install and instrument openinference-instrumentation-litellm (already in the install command above).
• 401 from OpenAI. Verify OPENAI_API_KEY is set and has access to gpt-5.5. Swap the model string in dspy.LM("openai/<model>") for one your key can call.
• Other LLM providers. DSPy via LiteLLM supports many providers — dspy.LM("anthropic/claude-sonnet-4-6"), dspy.LM("groq/llama-3.3-70b-versatile"), etc. The same LiteLLMInstrumentor covers them.

​

Resources