gemini-2.0-api 0.1.0

A user-friendly wrapper for the Google Gemini 2.0 API

Gemini 2.0 API Wrapper

A powerful, user-friendly Python wrapper for the Google Gemini 2.0 API, featuring a modern interface with strong type hints, streaming support, and comprehensive documentation.

Features

• 🚀 Modern, intuitive API interface
• 🔒 Type-safe with comprehensive type hints
• 🌊 Streaming support for all operations
• 💬 Advanced chat functionality with history management
• 🎯 Model fine-tuning capabilities
• 🖼️ Image analysis and vision model support
• 📦 Pydantic models for robust data validation
• ⚡ Async support for high-performance applications
• 🔬 Mock-friendly design for testing
• 📚 Detailed documentation with examples

Installation

Install using pip:

pip install gemini-2.0-api

Quick Start

from gemini_2_0_api import GeminiClient, TextGenerator

# Initialize client (using environment variable GEMINI_API_KEY)
client = GeminiClient.from_env()
generator = TextGenerator(client)

# Generate text
response = generator.generate("Tell me a story about a magical forest")
print(response.text)

# Use streaming
for chunk in generator.generate("Tell me a longer story", stream=True):
    print(chunk.text, end="")

# Chat functionality
from gemini_2_0_api import Chat

chat = Chat(client, system_prompt="You are a helpful assistant")
response = chat.send("What is machine learning?")
print(response.text)

follow_up = chat.send("Can you provide some examples?")
print(follow_up.text)

# Image analysis
from PIL import Image

image = Image.open("path/to/image.jpg")
response = generator.generate([
    "What can you see in this image?",
    image
])
print(response.text)

# Model tuning
from gemini_2_0_api import ModelTuner, TuningExample

tuner = ModelTuner(client)
examples = [
    TuningExample(
        input_text="What is 2+2?",
        output_text="4"
    ),
    TuningExample(
        input_text="What is 3+3?",
        output_text="6"
    )
]

model_id = tuner.tune(examples)
print(f"Tuned model ID: {model_id}")

Documentation

For detailed documentation and examples, see:

• API Reference
• Contributing Guide
• Changelog

Advanced Usage

Configuration

from gemini_2_0_api import GeminiClient, GenerationConfig

# Direct initialization with API key
client = GeminiClient(api_key="your-api-key-here")

# Custom configuration
config = GenerationConfig(
    temperature=0.9,
    max_output_tokens=1000,
    top_p=0.8
)

response = generator.generate(
    "Write a creative story",
    config=config
)

Streaming with Progress

from gemini_2_0_api import TextGenerator
import sys

generator = TextGenerator(client)

print("Generating story...", end="")
sys.stdout.flush()

for chunk in generator.generate(
    "Tell me an epic story",
    stream=True
):
    print(chunk.text, end="")
    sys.stdout.flush()

Chat with History

from gemini_2_0_api import Chat

chat = Chat(
    client,
    system_prompt="You are a knowledgeable professor"
)

# Send messages and get responses
response1 = chat.send("What is quantum physics?")
response2 = chat.send("Can you explain that simpler?")

# Access chat history
for message in chat.get_history():
    print(f"{message.role}: {message.content}")

Image Analysis with Options

from gemini_2_0_api import TextGenerator
from PIL import Image

generator = TextGenerator(client)

image = Image.open("scene.jpg")
response = generator.generate([
    "Analyze this image in detail. Focus on:",
    "1. Main subjects",
    "2. Colors and lighting",
    "3. Mood and atmosphere",
    image
])

Contributing

Contributions are welcome! Please read our Contributing Guide for details on our code of conduct and the process for submitting pull requests.

License

This project is licensed under the MIT License - see the LICENSE file for details.