This project showcases an advanced implementation of Retrieval-Augmented Generation (RAG) using the Google Gemini model. 🤖✨
Key Features:
- PDF Information Extraction: 📄🔍 Extracts relevant information from a given PDF document.
- Text Chunking: 🧩 Divides the extracted content into manageable chunks for more efficient processing.
- Embedding Conversion: 🔄 Converts text chunks into vector embeddings using state-of-the-art models.
- Chroma Database: 💾🔒 Stores and manages embeddings in a Chroma database for fast retrieval.
- Google Gemini Model: 🌟 Leverages the Gemini model to perform RAG, providing contextually relevant answers from the extracted content.