Build a Secure Document Q&A System with Llama3, Postgres, Qdrant, and Google Drive
Create a private, on-premises AI assistant that leverages your documents for intelligent Q&A. This workflow integrates Google Drive, Llama3, Postgres, and Qdrant to ensure data privacy while providing robust AI capabilities.
This workflow is designed for self-hosted n8n instances, enabling you to create a secure and private AI assistant that uses your own documents to answer questions. By monitoring specified Google Drive folders, the system downloads and processes new or updated files, extracts text, and generates embeddings using a local Llama3 model. These embeddings are stored in a Qdrant vector database. During interactions, the system retrieves relevant information using vector search, combines it with chat hi
Platform
n8n
Category
AI
Price
Free
Creator
Eli Brooks
set
stickyNote
googleDrive
agent
extractFromFile
lmOllama
googleDriveTrigger
chatTrigger
lmChatOllama
toolVectorStore
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.