Team Members:
This project developed a natural language processing system that uses RAG (Retrieval-Augmented Generation) to analyze SEC 10-K filings. The team collected data from 20 companies using Python's EDGAR library, processed the files using RE, Beautiful Soup, and Transformers libraries for tokenization and embedding, and integrated with OpenAI's GPT models through their API. The system allows users to query company information from 10-K filings in their database, with plans to add a user interface for improved accessibility.