Extract Google Drive documents and answer questions using AI
Workflow Description
Automation loads PDF files from Google Drive, splits them into segments, converts them to intelligent embeddings, and stores them in a vector database. It answers user inquiries about file content using OpenAI's advanced language models with semantic search.
How it works
- 1.Trigger the automation manually or via Webhook to start the workflow
- 2.Load PDF files from Google Drive and process their content
- 3.Split text into logical chunks and convert them to embeddings
- 4.Query Qdrant vector database in response to user questions
- 5.Send the question to GPT model to generate answers based on retrieved content
Use cases
- Get instant answers to questions about company documents stored in Google Drive
- Build an intelligent document search engine that understands context and delivers accurate responses
Requirements
- Connected Google Drive account in n8n with file access permissions
- OpenAI API key to use advanced AI language models
- Active Qdrant vector database to store embeddings and enable vector search
Service Value
Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (17)
Embeddings OpenAI1
OpenAI
On new manual Chat Message
Manual Chat Trigger
Sticky Note1
Sticky Note
Retrieval QA Chain
Chain Retrieval Qa
Respond to Webhook
Webhook
Vector Store Retriever
Retriever Vector Store
Webhook1
Webhook
When clicking "Execute Workflow"
Manual Trigger
Google Drive
Google Drive
Binary to Document
Document Binary Input Loader
Recursive Character Text Splitter
Text Splitter Recursive Character Text Splitter
Embeddings OpenAI
OpenAI
Sticky Note
Sticky Note
Qdrant Vector Store
Vector Store Qdrant
Qdrant Vector Store1
Vector Store Qdrant
OpenAI Chat Model
OpenAI
Sticky Note2
Sticky Note