Skip to content

GeminiProReader

Overview

The GeminiProReader class is designed to interface with the Google Generative AI models (Gemini Pro) to extract relationships between entities in a given text. It extends the BaseLLMReader class and uses the google-generativeai library to communicate with the API.

Installation

  1. Install the google-generativeai library:
    pip install google-generativeai
    

Example Usage

Here's an example demonstrating how to use the GeminiProReader class:

from euler.llm_readers import GeminiProReader

# Initialize the GeminiProReader
gemini_reader = GeminiProReader(api_key='your_google_api_key_here')

# Read text and extract relationships
result = gemini_reader.read("Example text to analyze.")
print(result.text if result else "No response received.")

Using LLMReaderFactory

The LLMReaderFactory class can be used to easily initialize different LLM readers, including GeminiProReader.

from euler.llm_readers import LLMReaderFactory

# Initialize the GeminiProReader using LLMReaderFactory
gemini_reader = LLMReaderFactory.get_llm_reader(
    reader_type='gemini_pro',
    api_key='your_google_api_key_here'
)

# Read text and extract relationships
result = gemini_reader.read("Example text to analyze.")
print(result.text if result else "No response received.")

Classes and Methods

GeminiConfig

The GeminiConfig class is a configuration model that holds the API key and an optional default prompt.

Attributes: - api_key (str): The API key for accessing the Google Generative AI API. - default_prompt (Optional[str]): A default prompt to use if no custom prompt is provided.

GeminiProResponse

The GeminiProResponse class represents the response from the Gemini Pro API.

Attributes: - text (str): The response text generated by the Gemini Pro model.

GeminiProReader

The GeminiProReader class interfaces with the Google Generative AI models to extract relationships between entities in a given text.

Methods: - __init__(self, api_key: str, default_prompt: Optional[str] = None): Initializes the reader with the API key and optional default prompt. - read(self, text: str, custom_prompt: Optional[str] = None) -> Optional[GeminiProResponse]: Reads the text and returns the extracted relationships.

This documentation provides an overview, example usage, and detailed description of the GeminiProReader class and its associated classes and methods.