Setup and Installation | Confident AI Docs

Overview

To use Confident AI, you will need to setup initially through DeepEval, our open-source SDK for running LLM evals. You’ll need to:

Create a free account
Login with your Confident API key in DeepEval

Python

Typescript

Install DeepEval

At the root of your project directory, install deepeval:

$ pip install -U deepeval

Create an account

Navigate to app.confident-ai.com and create a free account. Once logged in, you’ll be able to access your project API key from the dashboard.

Set API key as env variable

Set your project API key as an environment variable:

$ export CONFIDENT_API_KEY="confident_us..."

Alternatively, you can login directly using DeepEval:

$ deepeval login

This will prompt you to enter your API key and save it locally.

Confident AI’s data lives in the US by default, but if you’re a customer with a data residency in the EU, you’ll need to run this command to point deepeval to use Confdient AI’s API endpoints on our EU servers and databases instead:

$ export CONFIDENT_BASE_URL="https://eu.api.confident-ai.com"

This step is only required if you’ve created an account in the EU data region.

Next Steps

Now that you have Confident AI set up, the next section will guide you through LLM evaluation in development. This is where you’ll learn to systematically test and improve your AI applications before deployment.

No dataset yet? Start with LLM Tracing instead to run ad-hoc evals and automatically build datasets from your production traces.