FindOrg 1.0.0

Extract organization names from text using LLMs (OpenAI or Google Gemini).

FindOrg - Named Entity Recognition for Organizations using GPT

FindOrg is a Python package designed to perform Named Entity Recognition (NER), specifically targeting organizations within a given text. Leveraging OpenAI's powerful GPT models, it extracts organization names efficiently.

Installation

Before using FindOrg, ensure you have the necessary dependencies installed:

• openai
• pandas

Usage

from FindOrg import org

# Provide your OpenAI API key
openai_key = "YOUR_OPENAI_API_KEY"

# Sample text for analysis
text = "In the heart of Silicon Valley, a collaboration has emerged between global tech giants such as Google, Apple, and Facebook, aiming to revolutionize the digital landscape."

# Call the function
result_df = org(text, openai_key, model='gpt-3.5-turbo', save=False)

# Display the extracted organizations
print(result_df)

Arguments

• text (str): Text to be analyzed.
• openai_key (str): Your OpenAI API key.
• model (str, optional): Model to be used for the analysis. Defaults to 'gpt-3.5-turbo'.
• save (bool, optional): If True, the output will be saved as an Excel file named 'organizations.xlsx'. Defaults to False.

Returns

• pandas.DataFrame: DataFrame containing the extracted organizations.

Output

The output DataFrame consists of a single column named "Organizations", containing the extracted organization names.

How to cite

Neves, L. F. F. (2024). FindOrg: Named Entity Recognition for Organizations using GPT [Python package]. https://pypi.org/project/FindOrg/.

Contact

[e-mail]