Index and Store Google Drive Documents Vectorially
Loading workflow…
Workflow Description
Scheduled automation that extracts documents from Google Drive, splits them into text chunks, generates vector embeddings via OpenAI, and stores them in Postgres and Pinecone for semantic search and retrieval.
How it works
- 1.Trigger automation on a defined schedule
- 2.Extract and load documents from Google Drive
- 3.Split text into manageable chunks
- 4.Generate vector embeddings using OpenAI
- 5.Store vectors in Pinecone and document data in Postgres
Use cases
- Build a semantic search index for internal document libraries
- Automate indexing of new files without manual effort
- Enable fast retrieval of contextually relevant documents
Requirements
- Connected Google Drive account with access to target files
- Valid OpenAI API key with sufficient quota
- Configured Postgres database and Pinecone index
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 (12)
Download file1
Google Drive
Pinecone Vector Store1
Vector Store Pinecone
Embeddings OpenAI1
OpenAI
Default Data Loader1
Document Default Data Loader
Recursive Character Text Splitter1
Text Splitter Recursive Character Text Splitter
Search files and folders1
Google Drive
Schedule Trigger1
Schedule Trigger
PDF Filter1
If
Insert or update rows in a table1
Postgres
Compare With DB1
Merge
Code1
Code
Fetch Cleaned File IDs1
Postgres
Fresh workflows, straight to your inbox
Get newly published DROPIDEA workflows, a clear overview of what they do, and a link to explore them.
- New workflows
- Clear overviews
- Setup guides