Python SDK Guide

The KLA Python SDK package is kla-otel-python. Import it as kla_otel_python. It initializes OpenTelemetry, adds KLA GenAI attributes, and exports helpers for FastAPI middleware, LangChain instrumentation, sampling, and evaluation publishing.

Install

pip install kla-otel-python

For the FastAPI quickstart:

pip install "kla-otel-python[fastapi]" uvicorn

Set the service and collector before the app starts:

export OTEL_SERVICE_NAME=claims-agent-api
export KLA_TENANT_ID=kpmg-reporting
export OTEL_EXPORTER_OTLP_ENDPOINT=<kla-otlp-grpc-endpoint>
export KLA_PII_MASK=true

FastAPI First Trace

Load the SDK before creating the app and any model clients.

# main.py
import kla_otel_python
from fastapi import FastAPI
from kla_otel_python import add_genai_attributes, tracer
from kla_otel_python.middleware import KLATracingMiddleware
from kla_otel_python.semantic_conventions import GenAIAttributes

app = FastAPI()
app.add_middleware(KLATracingMiddleware)


@app.post("/messages")
async def create_message(payload: dict):
    with tracer.start_as_current_span("agent.reply") as span:
        prompt = str(payload.get("prompt", ""))

        add_genai_attributes(
            span,
            {
                GenAIAttributes.SYSTEM: "openai",
                GenAIAttributes.REQUEST_MODEL: "gpt-4o-mini",
                GenAIAttributes.USAGE_PROMPT_TOKENS: 24,
                GenAIAttributes.USAGE_COMPLETION_TOKENS: 12,
                GenAIAttributes.USAGE_TOTAL_TOKENS: 36,
            },
        )

        return {"response": f"Handled: {prompt}"}

Run it:

uvicorn main:app --reload
curl -s http://localhost:8000/messages \
  -H 'content-type: application/json' \
  -d '{"prompt":"Summarize the claim"}'

Open KLA Control Plane, go to Lineage Explorer, and filter by claims-agent-api. The span should include gen_ai.system, gen_ai.request.model, and token usage attributes.

LangChain

Install the LangChain extra and enable the instrumentor before constructing chains, agents, or tools.

pip install "kla-otel-python[langchain]"

import kla_otel_python
from kla_otel_python.instrumentors import LangChainInstrumentor

LangChainInstrumentor().instrument()

For explicit model spans:

from kla_otel_python import add_genai_attributes, tracer
from kla_otel_python.semantic_conventions import GenAIAttributes

with tracer.start_as_current_span("langchain.agent.answer") as span:
    result = chain.invoke({"input": "Review this transaction"})

    add_genai_attributes(
        span,
        {
            GenAIAttributes.SYSTEM: "openai",
            GenAIAttributes.REQUEST_MODEL: "gpt-4o-mini",
            GenAIAttributes.USAGE_TOTAL_TOKENS: result.get("usage", {}).get("total_tokens"),
        },
    )

Package Verification

The SDK package dry-run runs in CI with:

python -m pip install --upgrade build twine
python -m build
python -m twine check dist/*