Python APIpipecat

Core

Instrumentation

Python · Instrumentation

openinference-instrumentation-pipecat

OpenInference Pipecat Instrumentation

Module
openinference.instrumentation.pipecat
Version
2.0.13
Python
>=3.11, <3.15
Instruments
pipecat-ai>=1.3

Install

pip install openinference-instrumentation-pipecat

Usage

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

from opentelemetry.sdk.trace import TracerProvider
from openinference.instrumentation import TraceConfig
from openinference.instrumentation.pipecat import PipecatInstrumentor

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

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

openinference.instrumentation.pipecat

OpenInference instrumentation for Pipecat.

PipecatInstrumentor

classSource ↗
class PipecatInstrumentor(BaseInstrumentor)

An instrumentor for Pipecat pipelines.

Automatically instruments PipelineWorker to observe frame flow and create OpenInference-compliant spans for LLM, TTS, and STT services. The deprecated PipelineTask alias (a thin subclass of PipelineWorker) is covered transparently because its __init__ calls super().__init__.

instrument

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

Start tracing pipecat-ai: 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 pipecat-ai 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]

create_observer

methodSource ↗
def create_observer() -> Any

Create an OpenInferenceObserver manually.

Returns

TypeDescription
Any

OpenInferenceObserver instance

Raises

TypeDescription
RuntimeError

If instrumentor is not instrumented yet