Enterprise RAG Knowledge Agent

Enterprise RAG Knowledge Agent, n8n, OpenAI APIs, Pinecone Vector DB, Google Workspace APIs

- Engineered a production-grade Retrieval-Augmented Generation (RAG) pipeline to automate document auditing and semantic searching

within large data sources (e.g., Google Drive/Sheets).

- Implemented advanced text chunking using Recursive Character Text Splitter and generated text embeddings through OpenAI to upsert vectors

into Pinecone DB.

- Configured an AI Agent node with conversational memory, enabling users to fetch exact, hallucination-free insights from corporate files.