Google Gemini Provider

Use Google's Gemini models through SimplerLLM's unified interface with consistent, easy-to-use methods.

Overview

SimplerLLM provides seamless integration with Google's Gemini API, allowing you to use their models with just a few lines of code. The unified interface handles authentication, request formatting, and response parsing automatically.

Using Gemini Models

Google regularly releases new Gemini models and updates. You can use any Gemini model by specifying its name in the model_name parameter.

Model Examples

# Gemini 1.5 Pro (example)
model_name="gemini-1.5-pro"

# Gemini 1.5 Flash (example)
model_name="gemini-1.5-flash"

# You can use any model name from Google's catalog

Setup and Authentication

1. Get Your API Key

2. Configure Environment Variables

# .env file
GEMINI_API_KEY=your-gemini-api-key-here

Basic Usage

Simple Text Generation

from SimplerLLM.language.llm import LLM, LLMProvider

# Create Gemini LLM instance
llm = LLM.create(
    provider=LLMProvider.GEMINI,
    model_name="gemini-1.5-pro"
)

# Generate a response
response = llm.generate_response(
    prompt="Explain the concept of recursion in programming"
)

print(response)

With Custom Parameters

llm = LLM.create(
    provider=LLMProvider.GEMINI,
    model_name="gemini-1.5-pro",  # Use any Gemini model name
    temperature=0.7,               # Controls creativity
    max_tokens=1000,               # Maximum response length
    top_p=0.9                     # Nucleus sampling
)

response = llm.generate_response(
    prompt="Write a creative short story about AI"
)

print(response)

Advanced Features

Structured JSON Output

from pydantic import BaseModel, Field
from SimplerLLM.language.llm_addons import generate_pydantic_json_model

class ArticleSummary(BaseModel):
    title: str = Field(description="Article title")
    summary: str = Field(description="Brief summary")
    key_points: list[str] = Field(description="Main points")

llm = LLM.create(provider=LLMProvider.GEMINI, model_name="gemini-1.5-pro")

result = generate_pydantic_json_model(
    llm_instance=llm,
    prompt="Summarize an article about renewable energy",
    model_class=ArticleSummary
)

print(f"Title: {result.title}")
print(f"Summary: {result.summary}")

Configuration Options

Pricing Considerations

Google Gemini charges based on token usage. For current pricing, visit Google's pricing page.

Best Practices

Error Handling

from SimplerLLM.language.llm import LLM, LLMProvider

try:
    llm = LLM.create(
        provider=LLMProvider.GEMINI,
        model_name="gemini-1.5-pro"
    )

    response = llm.generate_response(prompt="Your prompt here")
    print(f"Response: {response}")

except ValueError as e:
    print(f"Configuration error: {e}")
except Exception as e:
    print(f"API error: {e}")

What's Next?