n8n workflow template · 13 nodes · OpenRouter
RAG:Context-Aware Chunking | Google Drive to Pinecone via OpenRouter & Gemini is a free n8n workflow template that starts when you run it manually in the n8n editor and works with OpenRouter, Pinecone, Google Gemini and Google Drive. It has 13 nodes, 6 of them AI nodes (OpenRouter Chat Model, Pinecone Vector Store, Google Gemini Embeddings and Default Data Loader). The notes inside the workflow say: “In this section, the agent node will prepare context for a section (chunk of text), which will then be passed for conversion into a vectors along with the section itself.” To run it, you add your own credentials for Google Drive OAuth2, Google Gemini (PaLM) API, Open Router API and Pinecone API.
The text below comes from the sticky notes inside the workflow. We removed links, code samples and anything that looks like a key or token.
In this section, the agent node will prepare context for a section (chunk of text), which will then be passed for conversion into a vectors along with the section itself.
This section is responsible for downloading the file from Google Drive, splitting the text into sections by detecting separators, and preparing them for looping.
In this step, the Pinecone node converts the provided text into vectors using Google Gemini and stores them in the Pinecone vector database.
The 13 nodes in file order (sticky notes excluded). Branches and connections determine execution order in n8n:
Configure your own credentials after importing. Create each credential in n8n, then select it in the node.
Do you need somewhere to run it? Read our guide to self-hosted n8n.
We can adapt this workflow to your apps, data and process, then deploy and support it.
Contact Us