AI-Powered Document Chatbot using Google Drive, OpenAI, and Pinecone
- Kwnstantinos Lambrou
- Jul 15
- 1 min read
Project Overview
A fully automated Retrieval-Augmented Generation (RAG) workflow that transforms documents uploaded to Google Drive into a smart chatbot that can answer questions based on their content — using n8n, OpenAI embeddings, and Pinecone vector search.
Use Case
Whenever a file is added to a shared Google Drive folder (e.g. reports, contracts, product manuals), this automation:
Downloads the file
Splits it into chunks
Creates embeddings using OpenAI
Stores them in a vector database (Pinecone)
Enables a chatbot to answer user queries based on that content in real-time.
⚙️ Tech Workflow (simplified for a general audience):
Trigger: New file is added to a Google Drive folder
Preprocessing: The file is downloaded and split into smaller text blocks
Embedding: Each block is transformed into vectors using OpenAI’s Embeddings API
Storage: Vectors are stored in Pinecone for fast semantic search
Interaction: When a user asks a question, relevant chunks are retrieved
Response: OpenAI’s chat model generates a response using the retrieved context
Visual Preview
Summary
A fully automated Retrieval-Augmented Generation (RAG) workflow that transforms documents uploaded to Google Drive into a smart chatbot that can answer questions based on their content — using n8n, OpenAI embeddings, and Pinecone vector search.
Comments