Gemini API with OpenAI Python Library: Complete 2025 Tutorial for Beginners

gcptutorials.com Gemini

Why Gemini + OpenAI?

Google's Gemini models integrate seamlessly with the OpenAI Python library, allowing developers to access cutting-edge AI capabilities without switching tools. This tutorial covers:

Unified development workflow for OpenAI and Gemini
Multimodal capabilities (text, images, structured data)
Production-ready error handling
Real-time streaming responses

1. Installation & Configuration

Prerequisites

Python 3.8+
Gemini API key from Google AI Studio

pip install openai python-dotenv

Environment Setup

from openai import OpenAI
import os

# Configure with your API key
client = OpenAI(
    api_key=os.getenv("GEMINI_API_KEY"),
    base_url="https://generativelanguage.googleapis.com/v1beta/"
)

2. Basic Chat Completions

response = client.chat.completions.create(
    model="gemini-1.5-flash",
    messages=[
        {"role": "system", "content": "You are a technical documentation expert"},
        {"role": "user", "content": "Explain gradient descent in simple terms"}
    ]
)
print(response.choices[0].message.content)

Streaming Responses

stream = client.chat.completions.create(
    model="gemini-1.5-flash",
    messages=[{"role": "user", "content": "Describe quantum computing"}],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end='', flush=True)

3. Advanced Implementations

Function Calling

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "description": "Get weather for a location",
        "parameters": {
            "type": "object",
            "properties": {
                "location": {"type": "string"},
                "unit": {"enum": ["celsius", "fahrenheit"]}
            },
            "required": ["location"]
        }
    }
}]

response = client.chat.completions.create(
    model="gemini-1.5-flash",
    messages=[{"role": "user", "content": "What's Chicago's weather?"}],
    tools=tools,
    tool_choice="auto"
)
print(response.choices[0].message.tool_calls[0].function.arguments)

Image Processing

import base64

def encode_image(image_path):
    with open(image_path, "rb") as image_file:
        return base64.b64encode(image_file.read()).decode('utf-8')

response = client.chat.completions.create(
    model="gemini-1.5-flash",
    messages=[
        {
            "role": "user",
            "content": [
                {"type": "text", "text": "Describe this image"},
                {"type": "image_url", "image_url": {
                    "url": f"data:image/png;base64,{encode_image('diagram.png')}"
                }}
            ]
        }
    ]
)
print(response.choices[0].message.content)

4. Production-Grade Implementation

Timeout Handling

try:
    response = client.chat.completions.create(
        model="gemini-1.5-flash",
        messages=[...],
        timeout=10  # Seconds
    )
except openai.APITimeoutError:
    print("Request timed out - implement retry logic")

Rate Limit Management

from time import sleep

def safe_request(prompt, retries=3):
    for attempt in range(retries):
        try:
            return client.chat.completions.create(...)
        except openai.RateLimitError:
            sleep(2 ** attempt)  # Exponential backoff
    raise Exception("Max retries exceeded")