Python APIopenai

Core

Instrumentation

Python · Instrumentation

openinference-instrumentation-openai

OpenInference OpenAI Instrumentation

Module
openinference.instrumentation.openai
Version
0.1.74
Python
>=3.10, <3.16
Instruments
openai >= 2.8.0

Install

pip install openinference-instrumentation-openai

Usage

Instrument once, at startup, before the library is used. The OpenAIInstrumentor reference below lists the options.

from opentelemetry.sdk.trace import TracerProvider
from openinference.instrumentation import TraceConfig
from openinference.instrumentation.openai import OpenAIInstrumentor

tracer_provider = TracerProvider()
# ...add a span processor that exports to Phoenix or any OTLP backend.

OpenAIInstrumentor().instrument(
    tracer_provider=tracer_provider,
    config=TraceConfig(hide_inputs=True),  # optional
)

openinference.instrumentation.openai

OpenAIInstrumentor

classSource ↗
class OpenAIInstrumentor(BaseInstrumentor)

An instrumentor for openai

instrument

method
def instrument(
    *,
    tracer_provider: Optional[TracerProvider] = None,
    config: Optional[TraceConfig] = None,
    skip_dep_check: bool = False,
) -> None

Start tracing openai: patch it so its calls make OpenInference spans. Calling it again does nothing. Inherited from OpenTelemetry’s BaseInstrumentor.

Parameters

NameDescription
tracer_provider

The tracer provider the spans are made with. Defaults to the global one, opentelemetry.trace.get_tracer_provider().

config

What the spans record: hide inputs, outputs or messages, or limit image sizes. Defaults to TraceConfig(), which reads the OPENINFERENCE_* environment variables. See TraceConfig.

skip_dep_check

Instrument even if the installed version of openai is outside the supported range.

uninstrument

method
def uninstrument() -> None

Stop tracing: undo the patches instrument() made. Inherited from OpenTelemetry’s BaseInstrumentor.

instrumentation_dependencies

methodSource ↗
def instrumentation_dependencies() -> Collection[str]