llm-watch-sdk 0.1.6

Lightweight LLM observability SDK

LLM Watch SDK

Lightweight SDK to send LLM usage telemetry to the LLM Watch backend.

Install

pip install llm-watch-sdk

Quickstart

LLM Watch reads config from env by default:

LLMWATCH_BACKEND_URL=http://127.0.0.1:8000
LLMWATCH_API_KEY=YOUR_PROJECT_KEY

from llm_watch import LLMWatch

watch = LLMWatch()  # reads env

You can still pass backend_url and project_api_key explicitly.

Providers

Instrument your provider client with the matching adapter, then call it as usual.

# OpenAI example (instrument existing client)
from openai import OpenAI

client = OpenAI(api_key="...")
client = watch.instrument_openai(client, model="gpt-4o-mini")

with watch.trace(actor_id="user-42"):
    resp = client.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": "hello"}],
    )

# Gemini example (google.genai)
from google import genai

client = genai.Client(api_key="...")
gm = watch.instrument_gemini(client, model="models/gemini-pro-latest")

with watch.trace(actor_id="user-42"):
    resp = gm.models.generate_content(
        model="models/gemini-pro-latest",
        contents="hello",
    )

# Bedrock example (wrap existing client)
import boto3

br = boto3.client("bedrock-runtime", region_name="eu-north-1")
br = watch.instrument_bedrock(client=br, model_id="arn:aws:bedrock:...")

with watch.trace(actor_id="user-42"):
    resp = br.invoke_model(
        modelId="arn:aws:bedrock:...",
        body=b'{"messages":[{"role":"user","content":[{"text":"hello"}]}]}',
        contentType="application/json",
        accept="application/json",
    )

Manual logging (if you prefer)

watch.log_llm_call(
    provider="openai",
    model="gpt-4o-mini",
    input_tokens=120,
    output_tokens=320,
    total_tokens=440,
    latency_ms=780,
    actor_id="user-42",
)

watch.trace() is optional. If you don’t create a trace, LLM Watch will auto-create one per call. Use trace() to group calls under a single workflow.