Just wrapped up a simple automation for an architecture firm client struggling with slow, manual document processing🙌 . 😍 Here’s what I built:

This system monitors a Google Drive folder, converts PDF documents into clean text chunks with Unstructured, generates OpenAI embeddings, and upserts vectors into Pinecone. It’s a practical, production-ready starting point for Retrieval-Augmented Generation (RAG) that you can plug into a chatbot, semantic search, or internal knowledge tools.

🚀 Results: Saved 10+ hours per week in document prep. Improved document analyse speed by 80%. Improves understanding of the necessary information by 16%.