Doku is an open-source LLMOps tool engineered to enables developers with comprehensive capabilities to monitor, analyze, and optimize LLM applications. It provides valuable real-time data on LLM usage, performance, and costs. Through seamless integrations with leading LLM platforms, including OpenAI, Cohere, Mistral and Anthropic, Doku acts as a central command center for all your LLM needs. It effectively guides your efforts, ensuring that your LLM applications not only operate at peak efficiency but also scale successfully.

This template automates the installation and pre-configuration of the following components:

• Doku Ingester
• Doku Client
• ClickHouse

Next Steps

🔑 Access Doku UI and Generate an API Key

With Doku running, the next step is to access the Doku UI and generate an API key for secure communication between your applications and Doku.

1. Open your browser and go to Doku UI at https://doku-client-.up.railway.app/login
2. Login using theb default credentials
   • Email as user@dokulabs.com
   • Password as dokulabsuser
3. Once you have logged into Doku UI, Go to API Keys page and create an API Key. Copy the generated API Key.

> 💡 Tip: Alternatively, you can use the HTTP API to create your Doku API Key. For further details, take a look at the API Reference section.

⚡️ Instrument your Application

Choose the appropriate SDK for your LLM application's programming language and follow the steps to integrate monitoring with just two lines of code.

Python

Install the dokumetry Python SDK using pip:

pip install dokumetry

Add the following two lines to your application code:

import dokumetry

dokumetry.init(llm=client, doku_url="https://doku-ingester-.up.railway.app/", api_key="YOUR_DOKU_TOKEN")

Example Usage for monitoring OpenAI Usage:

from openai import OpenAI
import dokumetry

client = OpenAI(
    api_key="YOUR_OPENAI_KEY"
)

# Pass the above `client` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
dokumetry.init(llm=client, doku_url="https://doku-ingester-.up.railway.app/", api_key="YOUR_DOKU_TOKEN")

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

Refer to the dokumetry Python SDK repository for more advanced configurations and use cases.

Node

Install the dokumetry NodeJS SDK using npm:

npm install dokumetry

Add the following two lines to your application code:

import DokuMetry from 'dokumetry';

DokuMetry.init({llm: openai, dokuUrl: "https://doku-ingester-.up.railway.app/", apiKey: "YOUR_DOKU_TOKEN"})

Example Usage for monitoring OpenAI Usage:

import OpenAI from 'openai';
import DokuMetry from 'dokumetry';

const openai = new OpenAI({
  apiKey: "YOUR_OPENAI_KEY", 
});

// Pass the above `openai` object along with your Doku Ingester URL and API key and this will make sure that all OpenAI calls are automatically tracked.
DokuMetry.init({llm: openai, dokuUrl: "https://doku-ingester-.up.railway.app/", apiKey: "YOUR_DOKU_TOKEN"})

async function main() {
  const chatCompletion = await openai.chat.completions.create({
    messages: [{ role: 'user', content: 'What are the key to effective observability?' }],
    model: 'gpt-3.5-turbo',
  });
}

main();

Refer to the dokumetry NodeJS SDK repository for more advanced configurations and use cases.

Visualize and Analyze

Once you have Doku Ingester and DokuMetry SDKs set up, you can instantly get insights into how your LLM applications in the Doku Client UI. Just head over to https://doku-client-.up.railway.app on your browser to start exploring.

With Doku, you get a simple, powerful view into important info like how much you’re spending on LLMs, which parts of your app are using them the most, and how well they’re performing. Find out which LLM models are favorites among your applications, and dive deep into performance details to make smart decisions. This setup is perfect for optimizing your app performance and keeping an eye on costs.

Appendix