hello! i am prototyping a multi-agent system on LangGraph. I'm just getting started on ai observability and cannot seem to properly set up Phoenix tracing. I have a .env variables PHOENIX_API_KEY, PHOENIX_COLLECTOR_ENDPOINT, PHOENIX_PROJECT_NAME, with the following code:
# Load environment variables
load_dotenv()
# Configure observability platform
tracer_provider = register(project_name="...", auto_instrument=True)
LangChainInstrumentor().instrument(tracer_provider=tracer_provider)
I am getting these logs:
馃敪 OpenTelemetry Tracing Details 馃敪 | Phoenix Project: ... | Span Processor: SimpleSpanProcessor | Collector Endpoint: localhost:4317 | Transport: gRPC | Transport Headers: {'user-agent': '****'} | | Using a default SpanProcessor. add_span_processor will overwrite this default. | | 鈿狅笍 WARNING: It is strongly advised to use a BatchSpanProcessor in production environments. | | register has set this TracerProvider as the global OpenTelemetry default. | To disable this behavior, call register with set_global_tracer_provider=False. Attempting to instrument while already instrumented Transient error StatusCode.UNAVAILABLE encountered while exporting traces to localhost:4317, retrying in 1s.Transient error StatusCode.UNAVAILABLE encountered while exporting traces to localhost:4317, retrying in 2s. Transient error StatusCode.UNAVAILABLE encountered while exporting traces to localhost:4317, retrying in 4s. Transient error StatusCode.UNAVAILABLE encountered while exporting traces to localhost:4317, retrying in 8s.
