GenAI observability setup

GenAI Observability provides comprehensive monitoring for Large Language Model (LLM) applications including performance metrics, token usage tracking, cost analysis, and user interaction patterns.

Install the instrumentation SDK

Install the OpenLIT SDK in your Python environment:

pip install openlit

Configure OTEL environment variables

Get your Grafana Cloud OTEL credentials

If you haven’t already obtained your OTEL credentials during the main AI Observability setup, follow these steps:

Sign in to Grafana Cloud and go to the Grafana Cloud Portal
Select your organization if you have access to multiple
Click your stack from the sidebar or main stack list
Under Manage your stack, click the Configure button in the OpenTelemetry section
Scroll down to the Password / API Token section and click Generate now (if you don’t have a token)
Enter a name for the token and click Create token
Click Close - you don’t need to copy the token manually
Scroll down and copy the OTEL_EXPORTER_OTLP_ENDPOINT and OTEL_EXPORTER_OTLP_HEADERS values from the Environment variables section

Set the environment variables

Set up the OpenTelemetry endpoints using the values you copied:

export OTEL_EXPORTER_OTLP_ENDPOINT="<YOUR_GRAFANA_OTEL_GATEWAY_URL>"
export OTEL_EXPORTER_OTLP_HEADERS="<YOUR_GRAFANA_OTEL_GATEWAY_AUTH>"

Replace the values with those you copied:

Replace <YOUR_GRAFANA_OTEL_GATEWAY_URL> with the OTEL_EXPORTER_OTLP_ENDPOINT value
Example: https://otlp-gateway-<ZONE>.grafana.net/otlp
Replace <YOUR_GRAFANA_OTEL_GATEWAY_AUTH> with the OTEL_EXPORTER_OTLP_HEADERS value
Example: Authorization=Basic%20<BASE64 ENCODED INSTANCE ID AND API TOKEN>

Instrument your application

Add the following two lines to your application code:

import openlit

openlit.init()

The OpenLIT SDK automatically use the OTEL environment variables to send telemetry data to your Grafana Cloud instance.

Examples by LLM provider

OpenAI

from openai import OpenAI
import openlit

openlit.init()

client = OpenAI(
    api_key="YOUR_OPENAI_KEY"
)

chat_completion = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "What is LLM Observability?",
        }
    ],
    model="gpt-3.5-turbo",
)

Anthropic

import anthropic
import openlit

openlit.init()

client = anthropic.Anthropic(
    api_key="YOUR_ANTHROPIC_KEY"
)

message = client.messages.create(
    model="claude-3-sonnet-20240229",
    max_tokens=1000,
    messages=[
        {"role": "user", "content": "What is AI Observability?"}
    ]
)

Refer to the OpenLIT documentation for more advanced configurations and additional LLM providers.

Visualize and analyze

With the LLM Observability data now being collected and sent to Grafana Cloud, the next step is to visualize and analyze this data to get insights into your LLM application’s performance, behavior, and identify areas of improvement.

Navigate to the GenAI Observability dashboard in your Grafana Cloud instance to start exploring. The dashboard provides: