OpenInference

OpenInference instrumentors (the ones behind Arize Phoenix) work with Rius directly: they emit standard OpenTelemetry spans, so they only need an OTLP exporter pointed at the ingest endpoint.

Wiring an instrumentor

from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from openinference.instrumentation.openai import OpenAIInstrumentor
 
provider = TracerProvider()
provider.add_span_processor(
    BatchSpanProcessor(
        OTLPSpanExporter(
            endpoint="https://ingest.eu.console.rius-glassflow.com/v1/traces",
            headers={"Authorization": "Bearer <your API key>"},
        )
    )
)
OpenAIInstrumentor().instrument(tracer_provider=provider)

Note the exporter class: otlp.proto.http (protobuf over HTTP). The endpoint accepts no OTLP/JSON and no gRPC.

What gets captured

Everything. openinference.span.kind drives the span taxonomy (LLM, TOOL, CHAIN, …), input.value / output.value are captured as span content, and the LLM detail attributes (llm.model_name, llm.provider, llm.token_count.*, llm.input_messages.*) are normalized into their gen_ai.* equivalents at ingest, so OpenInference-instrumented calls get model analytics, token usage, and server-side cost like native spans. On streamed OpenAI calls the instrumentor’s first-token event is likewise normalized to gen_ai.first_token, feeding time-to-first-token.

Details of the mapping, including the native-wins precedence rule, are in the supported-conventions matrix.

Next steps

• Auto-instrumentation: the same instrumentors, wired by the SDK, if your app is Python.
• Span attribute reference: the full normalization contract.