Documentation Index
Fetch the complete documentation index at: https://docs.responsibleailabs.ai/llms.txt
Use this file to discover all available pages before exploring further.
Installation
pip install "rail-score-sdk[telemetry]"
Setup
from opentelemetry import trace
from opentelemetry.sdk.trace import TracerProvider
from opentelemetry.sdk.trace.export import BatchSpanProcessor
from opentelemetry.exporter.otlp.proto.grpc.trace_exporter import OTLPSpanExporter
from rail_score_sdk import RailScoreClient
from rail_score_sdk.telemetry import RAILTelemetry
# OTEL exporter configure करें
provider = TracerProvider()
exporter = OTLPSpanExporter(endpoint="http://localhost:4317")
provider.add_span_processor(BatchSpanProcessor(exporter))
trace.set_tracer_provider(provider)
# RAIL telemetry enable करें
rail = RailScoreClient(api_key="YOUR_RAIL_API_KEY")
RAILTelemetry.instrument(rail)
# अब सभी eval() calls automatically spans emit करेंगी
result = rail.eval(content="Your text here", mode="basic")
Span attributes
हर rail.eval() call इन attributes के साथ एक span emit करती है:
| Attribute | Type | Description |
|---|
rail.score | float | Overall RAIL score |
rail.confidence | float | Score confidence |
rail.mode | string | basic या deep |
rail.credits_consumed | float | Consume हुए credits |
rail.from_cache | bool | Result cache से आया या नहीं |
rail.dim.{name}.score | float | Per-dimension score |
rail.dim.{name}.confidence | float | Per-dimension confidence |
Traces देखें
RAIL spans किसी भी OTEL-compatible backend के साथ काम करते हैं: Jaeger, Tempo, Honeycomb, Datadog, New Relic, या Langfuse।
# Development के लिए local Jaeger instance start करें
docker run -p 16686:16686 -p 4317:4317 jaegertracing/all-in-one
http://localhost:16686 open करें।
