Lesson 3: Using the Gemini / OpenAI APIs

To build custom applications with Large Language Models, we connect to them programmatically using developer APIs. Let's learn how to use the Google Gemini and OpenAI developer libraries.

Google Generative AI SDK

Google provides the @google/generative-ai SDK to interact with the Gemini family of models. In Python, you initialize the client using GoogleGenerativeAI and request content from the fast, highly capable **gemini-2.5-flash** model:

from google import generativeai as genai

genai.configure(api_key="YOUR_API_KEY")
model = genai.GenerativeModel('gemini-2.5-flash')
response = model.generate_content("Explain APIs in one sentence.")
print(response.text)

The OpenAI Client Library

The **openai** library is another developer standard. While APIs differ slightly, they share common parameters: passing a model name, setting system instructions, and defining a **temperature** (which controls the randomness of generation).

Key API Parameters

Temperature: Ranges from 0 to 2. A temperature of 0 ensures deterministic, consistent outputs. A temperature of 1.0 or higher encourages creative, diverse generation.
Max Output Tokens: Sets the hard cutoff limit on the size of the generated text response.

Coding Challenge: API Client Initializer

Let's simulate a standard Gemini API model setup wrapper function in Python!

Create a mock class GoogleGenerativeAI.
Implement a constructor __init__(self, api_key) that saves the API key.
Implement a method generateContent(self, prompt) that returns a string containing the prompt and the model name "gemini-2.5-flash".
Instantiate the class and print the output of the generation function.

Write this simulation in the code execution sandbox on the right!