Skip to main content

​
Overview

This guide walks you through setting up Google’s Gemini API for AI-powered features in your Africa’s Talking applications.

​
Getting a Gemini API Key

  1. Visit Google AI Studio
  2. Sign in with your Google account
  3. Click Get API Key or Create API Key
  4. Copy your API key - you’ll need it for configuration
Keep your API key secure! Never commit it to version control or share it publicly.

​
Installing the SDK

Install the Google Generative AI SDK using pip: 
pip install google-genai python-dotenv
The python-dotenv package is used to manage environment variables securely.

​
Configuring Credentials

​
1. Create a .env file

In your project root, create a .env file: 
# .env
GEMINI_API_KEY=your_api_key_here
MODEL_ID=gemini-2.5-flash

​
2. Add .env to .gitignore

Ensure your .env file is not tracked by Git: 
echo ".env" >> .gitignore

​
3. Load Environment Variables

The AI utilities automatically load your credentials:
utils/ai_utils.py
import os
from dotenv import load_dotenv
from google import genai

# Load environment variables from .env
load_dotenv()

# Setup Gemini client
GEMINI_API_KEY = os.getenv("GEMINI_API_KEY")
if not GEMINI_API_KEY:
    raise ValueError("Missing GEMINI_API_KEY in environment")

client = genai.Client(api_key=GEMINI_API_KEY)

# Default model (can override in function calls)
DEFAULT_MODEL = os.getenv("MODEL_ID", "gemini-2.5-flash")

​
Configuration Options

​
DEFAULT_MODEL

The DEFAULT_MODEL is set to gemini-2.5-flash by default, which provides:
  • Fast response times (ideal for real-time applications)
  • Cost-effective API usage
  • Good balance of quality and speed
You can override this in your .env file or when calling AI functions: 
# Use default model
response = ask_gemini("Hello, how are you?")

# Override with a specific model
response = ask_gemini("Hello, how are you?", model="gemini-2.0-pro")

​
Available Models

  • gemini-2.5-flash - Fast, optimized for speed (default)
  • gemini-2.0-pro - More powerful, better for complex tasks
  • gemini-1.5-pro - Previous generation, stable

​
Verifying Your Setup

Test your configuration with a simple script: 
from utils.ai_utils import ask_gemini

try:
    response = ask_gemini("Say hello!")
    print(f"✓ Gemini is working: {response}")
except Exception as e:
    print(f"✗ Setup error: {e}")
If configured correctly, you should see a greeting response from Gemini.

​
Troubleshooting

​
”Missing GEMINI_API_KEY in environment”

  • Ensure your .env file exists in the project root
  • Check that the variable name is exactly GEMINI_API_KEY
  • Verify you’ve called load_dotenv() before accessing the key

​
”Invalid API key” or authentication errors

  • Verify your API key is correct (no extra spaces)
  • Check that your API key is active in Google AI Studio
  • Ensure you have API access enabled for your Google account

​
Next Steps

AI Utilities

Learn about the three main AI utility functions

Examples

See real-world examples with SMS, Voice, and USSD

Build docs developers (and LLMs) love

Get started for freeTalk to us