Advanced RAG System with PDF Parsing

Dragutin Oreški

I successfully designed and implemented a cutting-edge RAG system, tailored to enhance data retrieval accuracy and efficiency. The project involved parsing PDFs to extract and structure data, creating embeddings, and storing them in the vector database for optimized retrieval. Some of the techniques used are Rewrite-Retrieve-Read, Hyde, query router, and hierarchical indexing. These methods collectively improved the system’s performance, ensuring accurate and quick data retrieval.
Like this project

Posted Aug 19, 2024

Generalized approach of parsing PDFs and creating a system to chat with them