RAG chatbot for company documents using Google Drive and Gemini

The workflow uses Google's Gemini AI for both embeddings and response generation, ensuring high-quality answers and intelligent context retrieval.

How it works

The workflow uses two Google Drive Trigger nodes: one for detecting new files added to a specified Google Drive folder, and another for detecting file updates in that same folder.

Automated Indexing: When a new or updated document is detected

1. Google Drive download: The file is downloaded automatically.
2. Data Loading: The Default Data Loader node loads the document content.
3. Text Splitting: The Recursive Character Text Splitter breaks the document into smaller chunks.
4. Embeddings: The Embeddings Google Gemini node generates embeddings for each chunk using text-embedding-004.
5. Indexing: The Pinecone Vector Store indexes the chunks and embeddings in a specified index.

Intelligent Querying

• The Chat Trigger node receives user questions through a chat interface.
• The AI Agent node uses a Vector Store Tool to retrieve relevant text chunks from Pinecone.
• Gemini Pro generates a comprehensive answer based on the retrieved documents.
• Window Buffer Memory provides context-aware conversations.

Set up steps

Prerequisites

1. Google Cloud Project & Vertex AI: Create a project and enable the Vertex AI API.
2. Google AI API Key: Obtain a key from Google AI Studio.
3. Pinecone Account: Create a free account, get an API key, and create an index named company-files.
4. Google Drive: Create a dedicated folder for your company documents.

n8n Configuration

Update both Google Drive Trigger nodes to watch the specific folder you created in your Google Drive. Configure the Pinecone Vector Store nodes to use your company-files index.

Tools Used

• Google Drive
• Pinecone Vector Database
• Google Gemini (PaLM/Pro)
• n8n