Automatically extract Drive documents and organize them in Sheets
Workflow Description
This automation retrieves documents from Google Drive, analyzes them using Google's Gemini AI, automatically classifies the content, and records results in Google Sheets. It enables intelligent document organization with deduplication and semantic search capabilities for better content management.
How it works
- 1.Trigger the workflow and fetch document list from Google Drive
- 2.Split and analyze documents using Google Gemini AI model
- 3.Remove duplicate entries and filtered redundant content
- 4.Classify extracted content using natural language processing
- 5.Store embeddings and results in vector database for semantic search
- 6.Write final data and summaries to Google Sheets
Use cases
- Organize corporate document libraries with automatic categorization and smart search
- Process multiple reports and extract key data points automatically
- Centralize content from various sources into structured spreadsheets
Requirements
- Google Workspace account with access to Google Sheets and Google Drive
- Valid API key for Google Gemini service
- Sufficient permissions to read documents and modify spreadsheets
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 (88)
When clicking ‘Test workflow’
Manual Trigger
Web Search For API Schema
HTTP Request
Scrape Webpage Contents
HTTP Request
Results to List
Split Out
Recursive Character Text Splitter1
Text Splitter Recursive Character Text Splitter
Content Chunking @ 50k Chars
Set
Split Out Chunks
Split Out
Default Data Loader
Document Default Data Loader
Set Embedding Variables
Set
Execute Workflow Trigger
Execute Workflow Trigger
Execution Data
Execution Data
EventRouter
Switch
Google Gemini Chat Model
Gemini Model
Successful Runs
Filter
For Each Document...
Split In Batches
Embeddings Google Gemini
Gemini Model
Has API Documentation?
If
Store Document Embeddings
Vector Store Qdrant
Embeddings Google Gemini1
Gemini Model
Google Gemini Chat Model1
Gemini Model
Extract API Operations
Information Extractor
Search in Relevant Docs
Vector Store Qdrant
Wait
Wait
Remove Dupes
Remove Duplicates
Filter Results
Filter
Research
Execute Workflow
Has Results?
If
Response Empty
Set
Response OK
Set
Combine Docs
Aggregate
Template to List
Split Out
Query Templates
Set
Google Gemini Chat Model2
Gemini Model
For Each Template...
Split In Batches
Query & Docs
Set
Identify Service Products
Information Extractor
Extract API Templates
Set
Embeddings Google Gemini2
Gemini Model
Search in Relevant Docs1
Vector Store Qdrant
Combine Docs1
Aggregate
Query & Docs1
Set
For Each Template...1
Split In Batches
Merge Lists
Code
Remove Duplicates
Remove Duplicates
Append Row
Google Sheets
Response OK1
Set
Has Operations?
If
Response Empty1
Set
Research Pending
Google Sheets
Research Result
Google Sheets
Research Error
Google Sheets
Extract Pending
Google Sheets
Research Event
Set
Extract Event
Set
Extract
Execute Workflow
Extract Result
Google Sheets
Extract Error
Google Sheets
Get API Operations
Google Sheets
Contruct JSON Schema
Code
Upload to Drive
Google Drive
Set Upload Fields
Set
Response OK2
Set
Generate Event
Set
Generate Pending
Google Sheets
Generate
Execute Workflow
Generate Error
Google Sheets
Generate Result
Google Sheets
Get All Extract
Google Sheets
Get All Research
Google Sheets
For Each Research...
Split In Batches
For Each Extract...
Split In Batches
Wait1
Wait
All Research Done?
If
All Extract Done?
If
Get All Generate
Google Sheets
All Generate Done?
If
For Each Generate...
Split In Batches
Wait2
Wait
Has Results?1
If
Response Scrape Error
Set
Has Results?3
If
Response No API Docs
Set
Sticky Note
Sticky Note
Sticky Note1
Sticky Note
Sticky Note2
Sticky Note
Sticky Note3
Sticky Note
Sticky Note4
Sticky Note
Sticky Note5
Sticky Note