elizaOS Google GenAI Plugin (Python)

Python implementation of the elizaOS Google Generative AI plugin for Gemini models.

Installation

pip install elizaos-plugin-google-genai

Quick Start

import asyncio
from elizaos_plugin_google_genai import GoogleGenAIClient, GoogleGenAIConfig

async def main():
    # Load config from environment
    config = GoogleGenAIConfig.from_env()

    async with GoogleGenAIClient(config) as client:
        # Generate text
        response = await client.generate_text_large("What is the meaning of life?")
        print(response.text)

        # Generate embeddings
        embedding = await client.generate_embedding("Hello, world!")
        print(f"Embedding dimension: {len(embedding.embedding)}")

        # Generate structured JSON
        from elizaos_plugin_google_genai import ObjectGenerationParams

        result = await client.generate_object_small(ObjectGenerationParams(
            prompt="Generate a person profile with name and age",
            json_schema={
                "type": "object",
                "properties": {
                    "name": {"type": "string"},
                    "age": {"type": "number"}
                }
            }
        ))
        print(result.object)

asyncio.run(main())

Configuration

Set the following environment variables:

Features

• Text Generation: Generate text using Gemini models
• Embeddings: Generate text embeddings for semantic search
• Image Analysis: Analyze and describe images
• JSON Object Generation: Generate structured JSON with schema validation
• Async/Await: Full async support for efficient I/O
• Type Safety: Full type hints with Pydantic models

Development

# Install dev dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Type checking
mypy elizaos_plugin_google_genai

# Linting
ruff check .
ruff format .

License

MIT