OpenAI Integration

Updated on Aug 14, 2026

Use this integration when your app is implemented in Python, TypeScript, or .NET.

Setup

PythonTypeScript.NET

1. Install SDK

bash

pip install progress-observability

2. Instrument your app

python

Observability.instrument(
    app_name=os.getenv("OBSERVABILITY_APP_NAME"),
    api_key=os.getenv("OBSERVABILITY_API_KEY")
)

3. Complete example

python

import os

from dotenv import load_dotenv
from openai import OpenAI

from progress.observability import Observability

load_dotenv()

# LLM INSTRUMENTATION
Observability.instrument(
    app_name=os.getenv("OBSERVABILITY_APP_NAME"),
    api_key=os.getenv("OBSERVABILITY_API_KEY"),
)


def main() -> None:
    client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))
    model = os.getenv("OPENAI_MODEL", "gpt-4o-mini")

    response = client.chat.completions.create(
        model=model,
        max_tokens=256,
        messages=[
            {"role": "system", "content": "You are a helpful AI assistant."},
            {"role": "user", "content": "What is the capital of France?"},
        ],
    )



try:
    main()
finally:
    Observability.shutdown()

To get a richer trace tree when building agents on top of this provider, use the @agent, @tool, @workflow, or @task decorators. See the Python SDK for details.

1. Install SDK

bash

npm install @progress/observability

2. Instrument your app

TS

import '@progress/observability/register/hooks';
import { Observability } from '@progress/observability';
await Observability.instrument({
 appName: process.env.OBSERVABILITY_APP_NAME ?? 'my-openai-app',
 apiKey: process.env.OBSERVABILITY_API_KEY
});

3. Complete example

TS

import '@progress/observability/register/hooks';
import 'dotenv/config';

import { Observability } from '@progress/observability';

await Observability.instrument({
 appName: process.env.OBSERVABILITY_APP_NAME ?? 'my-openai-app',
 apiKey: process.env.OBSERVABILITY_API_KEY,
});

try {
 // Import the OpenAI SDK only after instrument(), so it gets patched.
 const { default: OpenAI } = await import('openai');
 const client = new OpenAI({ apiKey: process.env.OPENAI_API_KEY });

 const completion = await client.chat.completions.create({
  model: process.env.OPENAI_MODEL ?? 'gpt-4o-mini',
  max_tokens: 256,
  messages: [
   { role: 'system', content: 'You are a helpful AI assistant.' },
   { role: 'user', content: 'What is the capital of France?' },
  ],
 });

} finally {
 await Observability.shutdown();
}

To get a richer trace tree when building agents on top of this provider, use the @agent, @tool, @workflow, or @task decorators. See the TypeScript SDK for details.

1. Install SDK

bash

dotnet add package Progress.Observability.Instrumentation

2. Instrument your app

cs

try
{
 chatClient = chatClient.AddObservability((options) =>
 {
 options.AppName = Environment.GetEnvironmentVariable("OBSERVABILITY_APP_NAME")!;
 options.ApiKey = Environment.GetEnvironmentVariable("OBSERVABILITY_API_KEY")!;
 });
 
 // Your code here.
}
finally
{
 // Call the Shutdown() method before exiting your agent to flush any remaining data.
 ObservabilityTracer.Shutdown();
}

3. Complete example

cs

using Microsoft.Extensions.AI;
using OpenAI;
using Progress.Observability.Extensions.AI;
using DotNetEnv;

namespace Examples.OpenAI;

public class Program
{
 public static async Task Main(string[] args)
 {
     try
     {
         Env.Load(".env");

         IChatClient chatClient = new OpenAIClient(
             Environment.GetEnvironmentVariable("OPENAI_API_KEY")!)
             .GetChatClient("gpt-4o-mini")
             .AsIChatClient()
             .AddObservability((options) =>
             {
                 options.AppName = "OpenAI Example";
                 options.ApiKey = Environment.GetEnvironmentVariable("OBSERVABILITY_API_KEY")!;
             });

         var response = await chatClient.GetResponseAsync(
             "What is the capital of France?");

         Console.WriteLine(response.Text);
     }
     finally
     {
         ObservabilityTracer.Shutdown();
     }
 }
}

To get a richer trace tree when building agents on top of this provider, use custom spans. See the .NET SDK for details.