> ## Documentation Index
> Fetch the complete documentation index at: https://docs.techeval.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Install and Configure the Kovi Python SDK for AI Interviews

> Install kovi-sdk from PyPI using pip, configure your API key, and verify your setup with a connection test before scheduling your first interview.

The `kovi-sdk` Python package gives you programmatic access to the Kovi interview platform. Install it from PyPI and initialize it with your API key to start scheduling interviews from your code.

<Note>
  kovi-sdk requires Python 3.8 or higher.
</Note>

## Requirements

<Info>
  Before you install the SDK, make sure you have the following:

  * **Python 3.8 or higher** installed on your system. Run `python --version` to check.
  * **A Techeval account** with an active API key. Sign up at [techeval.ai](https://techeval.ai) — new accounts receive 10 free credits on sign-up.
</Info>

## Install with pip

Run the following command to install `kovi-sdk` from PyPI:

```bash theme={null}
pip install kovi-sdk
```

We recommend working inside a virtual environment to keep your project dependencies isolated:

<Steps>
  <Step title="Create a virtual environment">
    ```bash theme={null}
    python -m venv .venv
    ```
  </Step>

  <Step title="Activate the virtual environment">
    ```bash theme={null}
    # macOS / Linux
    source .venv/bin/activate

    # Windows (PowerShell)
    .venv\Scripts\Activate.ps1
    ```
  </Step>

  <Step title="Install the SDK">
    ```bash theme={null}
    pip install kovi-sdk
    ```
  </Step>
</Steps>

## Initialize the Client

Import `KoviClient` and pass your API key to create a client instance:

```python client_init.py theme={null}
from kovi import KoviClient

client = KoviClient(api_key="YOUR_LIVE_API_KEY_HERE")
```

<Warning>
  Never hardcode your API key in source code. Use environment variables or a secrets manager instead — see the section below.
</Warning>

## Using Environment Variables (Recommended)

Store your API key in an environment variable and read it at runtime to keep credentials out of your codebase:

```python client_env.py theme={null}
import os
from kovi import KoviClient

client = KoviClient(api_key=os.environ.get("KOVI_API_KEY"))
```

Set the environment variable in your shell before running your script:

```bash theme={null}
# macOS / Linux
export KOVI_API_KEY="YOUR_LIVE_API_KEY_HERE"

# Windows (PowerShell)
$env:KOVI_API_KEY = "YOUR_LIVE_API_KEY_HERE"
```

For persistent configuration, add the `export` line to your `~/.bashrc`, `~/.zshrc`, or equivalent shell profile file. In production, inject the variable through your deployment platform's secrets manager (e.g., AWS Secrets Manager, GCP Secret Manager, or a CI/CD environment variable store).

## Verify Your Setup

Instantiate the client to confirm the SDK is installed and your import paths are correct. No network call is made at construction time, so this step does not consume any credits:

```python verify_setup.py theme={null}
import os
from kovi import KoviClient

# No network call is made here — safe to run as a smoke test
client = KoviClient(api_key=os.environ.get("KOVI_API_KEY"))
print("KoviClient initialized successfully.")
```

<Note>
  Calling `client.schedule_interview(...)` initiates a live interview session and **consumes one credit** when the interview starts. Run verification using only the constructor until you are ready to schedule a real interview.
</Note>

Once your client initializes without errors, you are ready to schedule your first interview. See the [KoviClient Reference](/sdk/kovi-client) for the full API, or jump straight to the [Examples](/sdk/examples) to copy a working integration.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.