> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.dev/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# DSPy

> Trace DSPy modules and the LiteLLM calls beneath them with OpenInference and send spans to Arize AX for LLM observability.

[DSPy](https://github.com/stanfordnlp/dspy) is a Stanford framework for declarative LLM programs — `Signature`, `Predict`, and other modules describe the structure of an LLM call without hard-coding prompts. Arize AX captures the DSPy module hierarchy plus the underlying LLM calls (DSPy routes through LiteLLM by default) via the [`openinference-instrumentation-dspy`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-dspy) and [`openinference-instrumentation-litellm`](https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-litellm) packages — install both for full visibility.

<CardGroup>
  <Card horizontal icon="https://storage.googleapis.com/arize-phoenix-assets/assets/images/phoenix-docs-images/gc.ico" href="https://colab.research.google.com/github/Arize-ai/phoenix/blob/main/tutorials/tracing/dspy_tracing_tutorial.ipynb" title="DSPy Tracing Tutorial (Google Colab)" />
</CardGroup>

## Prerequisites

* Python 3.10+
* An Arize AX account ([sign up](https://arize.com/sign-up/))
* An `OPENAI_API_KEY` from the [OpenAI Platform](https://platform.openai.com/api-keys)

## Launch Arize AX

1. Sign in to your [Arize AX account](https://app.arize.com/).
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

```bash theme={null}
pip install arize-otel \
  openinference-instrumentation-dspy \
  openinference-instrumentation-litellm \
  dspy
```

## Configure credentials

```bash theme={null}
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

```python theme={null}
# 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

```python theme={null}
# 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")
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

```text wrap theme={null}
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](#troubleshooting).

## 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`. 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-3-5-sonnet-20241022")`, `dspy.LM("groq/llama-3.3-70b-versatile")`, etc. The same `LiteLLMInstrumentor` covers them.

## Resources

<CardGroup>
  <Card icon="book-open" href="https://dspy.ai/" title="DSPy Documentation" horizontal />

  <Card icon="terminal" href="https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-dspy" title="OpenInference DSPy Instrumentor" horizontal />

  <Card icon="terminal" href="https://github.com/Arize-ai/openinference/tree/main/python/instrumentation/openinference-instrumentation-litellm" title="OpenInference LiteLLM Instrumentor" horizontal />

  <Card icon="github" href="https://github.com/stanfordnlp/dspy" title="DSPy GitHub" horizontal />
</CardGroup>