Automated RAG Chatbot with Google Drive & Ollama
detail.loadingPreview
This workflow automates the creation of a powerful Retrieval Augmented Generation (RAG) chatbot. It continuously syncs with your Google Drive, ingesting new documents to build a dynamic knowledge base using Ollama for embeddings and Qdrant as a vector store, enabling intelligent, context-aware conversations.
About This Workflow
This n8n workflow establishes a comprehensive RAG pipeline, transforming your Google Drive into a dynamic, AI-powered knowledge base. It automatically detects new or updated documents in Google Drive, processes their content, splits them into manageable chunks, and generates vector embeddings using Ollama. These embeddings are then stored in a Qdrant vector database, forming the backbone of your RAG system. The second part of the workflow powers an interactive chatbot, triggered by incoming messages. This chatbot leverages the stored knowledge in Qdrant, retrieves relevant information based on user queries, and generates accurate, context-rich responses using an Ollama Chat Model, enhancing conversational AI capabilities with your own data.
Key Features
- Google Drive Integration: Automatically monitor and ingest documents from specified Google Drive folders into your knowledge base.
- Retrieval Augmented Generation (RAG): Build a robust, context-aware knowledge base by embedding your private documents.
- Ollama Embeddings & Chat Models: Leverage local or self-hosted open-source language models for both embedding generation and conversational AI.
- Qdrant Vector Store: Efficiently store and retrieve document embeddings for fast and accurate context lookup during chat interactions.
- Intelligent Chatbot: Provide users with a dynamic chatbot capable of answering questions based on your unique, continually updated document repository.
How To Use
- Configure Google Drive Trigger & Google Drive: Connect your Google Drive account. For the trigger, specify the folder(s) to monitor for new or updated files. For the Google Drive node, ensure it's configured to download the content of the triggered file.
- Set Up Ollama Embeddings & Chat Model: Ensure your Ollama server is running and accessible. Configure both
Embeddings Ollamanodes with the correct model (e.g.,nomic-embed-text) and API endpoint. Similarly, configure theOllama Chat Modelwith your desired chat model (e.g.,llama2) and API endpoint. - Initialize Qdrant Vector Stores: Connect to your Qdrant instance. For both
Qdrant Vector Storenodes, define a collection name (e.g., "my_knowledge_base"). The first node will be for writing new documents, and the second for querying. - Configure Document Processing: Ensure the
Default Data Loaderis correctly set to handle the document type from Google Drive. AdjustRecursive Character Text Splitterparameters (e.g., chunk size, overlap) to optimize how your documents are broken down. - Activate Chat Trigger & AI Agent: The
When chat message receivednode automatically generates a webhook URL. Use this URL to connect your chatbot interface. TheAI Agentwill orchestrate the LLM and vector store to respond.
Apps Used
Workflow JSON
{
"id": "b03eed4f-2619-428b-b7ae-79fddc0f91b3",
"name": "Automated RAG Chatbot with Google Drive & Ollama",
"nodes": 23,
"category": "Operations",
"status": "active",
"version": "1.0.0"
}Note: This is a sample preview. The full workflow JSON contains node configurations, credentials placeholders, and execution logic.
Get This Workflow
ID: b03eed4f-2619...
About the Author
AI_Workflow_Bot
LLM Specialist
Building complex chains with OpenAI, Claude, and LangChain.
Statistics
Related Workflows
Discover more workflows you might like
Instant WooCommerce Order Notifications via Telegram
When a new order is placed on your WooCommerce store, instantly receive detailed notifications directly to your Telegram chat. Stay on top of your e-commerce operations with real-time alerts, including order specifics and a direct link to view the order.
On-Demand Microsoft SQL Query Execution
This workflow allows you to manually trigger and execute any SQL query against your Microsoft SQL Server database. Perfect for ad-hoc data lookups, administrative tasks, or quick tests, giving you direct control over your database operations.
Automate Getty Images Editorial Search & CMS Integration
This n8n workflow automates searching for editorial images on Getty Images, extracts key details and embed codes, and prepares them for seamless integration into your Content Management System (CMS), streamlining your content creation process.