AI Knowledge Base Agent for Google Drive & Gemini

Unlock Instant Answers from Your Company Knowledge with this AI Agent

This workflow builds a powerful, self-updating AI agent that acts as an expert on your company's internal documents. It continuously monitors a specified Google Drive folder, and whenever a file is added or updated, it automatically processes the content, creates vector embeddings using Google Gemini, and stores them in a Pinecone knowledge base.

This creates a Retrieval-Augmented Generation (RAG) system that allows you or your team to ask complex questions in natural language via a simple chat interface. The agent retrieves the most relevant information from your documents and uses a Gemini chat model to synthesize an accurate, concise answer, complete with conversation history for context.

Key Features & Benefits

• Automated Knowledge Sync: The agent watches a Google Drive folder and automatically indexes new or updated files, ensuring its knowledge is always current.
• Conversational Q&A: Provides a chat interface for asking natural language questions about your documents, making information instantly accessible.
• RAG Powered by Gemini: Leverages Google's Gemini models for both embedding documents and generating accurate, context-aware answers.
• Scalable Knowledge Base: Uses Pinecone for efficient vector storage and retrieval, capable of handling large volumes of information.
• Customizable Persona: The agent's system prompt (e.g., from HR assistant to technical support) can be easily modified to fit your exact needs.

• An n8n instance (Cloud or self-hosted).
• A Google Cloud Project with the Vertex AI API enabled.
• A Google AI API Key from Google AI Studio.
• A Pinecone account with an API key.
• A Pinecone index created (e.g., 'company-files').
• A Google Drive account with a dedicated folder for your documents.
• Configured n8n credentials for Google Drive (OAuth2), Google Gemini, and Pinecone.

1. Import the workflow into your n8n instance.
2. Ensure your credentials for Google Drive, Google Gemini, and Pinecone are correctly configured in n8n.
3. In the 'Google Drive File Created' and 'Google Drive File Updated' trigger nodes, select the specific folder you want the agent to monitor.
4. In both 'Pinecone Vector Store' nodes (for insertion and retrieval), select your configured Pinecone index.
5. Customize the system message in the 'AI Agent' node to define your agent's persona and instructions.
6. Activate the workflow. The agent will begin indexing any files you add to the folder.
7. Use the Chat Trigger's webhook URL to interact with your new AI Knowledge Base Agent.