​
🤝 OpenAI Integration

Lucidic makes it easy to automatically track OpenAI completions as part of your agent’s behavior — no code changes required.

​
⚙️ How It Works

When you set:

lai.init(..., providers=["openai"])

Lucidic will:

  • Monkey patch openai.ChatCompletion.create
  • Automatically log each LLM call as an Event
  • Attach the call to the currently active Step

This means:

  • You don’t need to call create_event() or end_event() manually
  • You get full observability into prompt, model, cost, result, and more — out of the box

​
✅ What Gets Captured

We automatically capture the following when you pass it to openai.ChatCompletion.create:

  • Input: your prompt to Open AI (e.g. "What's the capital of France?")
  • Model: the model name (e.g. gpt-4, gpt-3.5-turbo)
  • Output: OpenAI response

Based on your input, we automatically calculate the following:

  • Cost: calculated based on token usage

​
🧠 Why This Matters

LLM calls are a core part of most agent workflows — but without visibility, it’s impossible to debug or optimize:

  • Which call caused the failure?
  • Which step was it part of?
  • How much did it cost?
  • What was the actual response?

This integration gives you full transparency, with zero boilerplate.

​
🧪 Example

import lucidicai as lai
import openai

lai.init(
    session_name="chatbot_run",
    agent_id="your-agent-id",
    lucidic_api_key="your-api-key",
    providers=["openai"]
)

lai.create_step(state="Intro", goal="Ask user for name")

# This call is automatically tracked!
response = openai.ChatCompletion.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "What's your name?"}]
)

lai.end_step(is_successful=True, action="Generated greeting")

​
🛠️ Notes

  • Only openai.ChatCompletion.create is currently patched
  • You must have an active session and step for events to be attached
  • You can always override or add custom events using create_event() if needed