splunk-otel-instrumentation-openai 0.1.2

Instrumenting all clients

When using the instrumentor, all clients will automatically trace OpenAI operations including chat completions and embeddings. You can also optionally capture prompts and completions as log events.

Make sure to configure OpenTelemetry tracing, logging, and events to capture all telemetry emitted by the instrumentation.

from opentelemetry.instrumentation.openai_v2 import OpenAIInstrumentor

OpenAIInstrumentor().instrument()

client = OpenAI()
# Chat completion example
response = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "user", "content": "Write a short poem on open telemetry."},
    ],
)

# Embeddings example
embedding_response = client.embeddings.create(
    model="text-embedding-3-small",
    input="Generate vector embeddings for this text"
)

Enabling message content

Message content such as the contents of the prompt, completion, function arguments and return values are not captured by default. To capture message content as log events, set the environment variable OTEL_INSTRUMENTATION_GENAI_CAPTURE_MESSAGE_CONTENT to true.

See the upstream OpenTelemetry documentation for more details.

Suppressing nested instrumentation

When using multiple instrumentations together (e.g., LangChain + OpenAI), the higher-level instrumentation automatically sets SUPPRESS_LANGUAGE_MODEL_INSTRUMENTATION_KEY in the OpenTelemetry context to prevent duplicate spans for the same underlying LLM call.

This is handled transparently — no user configuration is needed. For example, when LangChain instrumentation is active alongside OpenAI instrumentation, you will see LangChain spans without redundant nested OpenAI spans.

Uninstrument

To uninstrument clients, call the uninstrument method:

from opentelemetry.instrumentation.openai_v2 import OpenAIInstrumentor

OpenAIInstrumentor().instrument()
# ...

# Uninstrument all clients
OpenAIInstrumentor().uninstrument()