Completions

Monitor OpenAI completions API usage for cost, performance & user interactions

Python

No Streaming

from openai import OpenAI
import dokumetry

client = OpenAI(
  api_key = "YOUR_OPENAI_API_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="YOUR_DOKU_INGESTER_URL", api_key="YOUR_DOKU_TOKEN")

response = client.completions.create(
  model="gpt-3.5-turbo-instruct",
  prompt="What is LLM Observablity?",
)

print(respomse.choices[0].text)

NodeJS

No Streaming

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

const openai = new OpenAI();

// 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: "YOUR_DOKU_INGESTER_URL", apiKey: "YOUR_DOKU_TOKEN"})

async function main() {
  const response = await openai.completions.create({
    model: "gpt-3.5-turbo-instruct",
    prompt: "How to monitor LLM Applications?",
  });

  console.log(response);
}
main();