What This Workflow Does This RAG Pipeline in n8n automates document ingestion from Google Drive, vectorizes it using OpenAI embeddings, stores it in Pinecone, and enables chat-based retrieval using LangChain agents. Main Functions: π Auto-detects new files uploaded to a specific Google Drive folder. π§ Converts the file into embeddings using OpenAI. π¦ Stores them in a Pinecone vector database. π¬ Allows a user to query the knowledge base through a chat interface. π€ Uses a GPT-4o-mini model wi

What This Workflow Does This RAG Pipeline in n8n automates document ingestion from Google Drive, vectorizes it using OpenAI embeddings, stores it in Pinecone, and enables chat-based retrieval using LangChain agents. Main Functions: π Auto-detects new files uploaded to a specific Google Drive folder. π§ Converts the file into embeddings using OpenAI. π¦ Stores them in a Pinecone vector database. π¬ Allows a user to query the knowledge base through a chat interface. π€ Uses a GPT-4o-mini model with LangChain to generate intelligent responses using retrieved context. βοΈ Setup Instructions 1. Connect Accounts Ensure these services are connected in n8n: β Google Drive (OAuth2) β OpenAI β Pinecone You can do this in n8n > Credentials > New and use the matching names from the file: Google Drive: "Google Drive account 2" OpenAI: "OpenAi success" Pinecone: "PineconeApi account 2" 2. Folder Setup Upload your documents to this folder in Google Drive: π Power Folder The workflow is triggered every minute when a new file is uploaded. 3. Workflow Overview A. File Ingestion Path Google Drive Trigger β detects new file. Google Drive (Download) β downloads the new file. Recursive Text Splitter β splits text into chunks. Default Data Loader β loads content as LangChain documents. OpenAI Embeddings β converts text chunks into embeddings. Pinecone Vector Store β stores them in "ragfile" index. B. Chat Retrieval Path When chat message received β AI Agent β LangChain agent managing tools. OpenAI Chat Model (GPT-4o-mini) β generates replies. Pinecone Vector Store (retrieval) β retrieves matching content. Embeddings OpenAI1 β helps match queries to document chunks.
Download the workflow JSON file after purchase.
Open n8n β click the menu β Import from File.
Select the downloaded JSON and import.
Set up credentials for each node that requires them.
Click Execute Workflow to test, then activate.
Setup guide included
Purchase to unlock the full step-by-step guide
No reviews yet
Be the first to buy and share your experience.
Leave a review
Sign in to share your experience with this workflow.
Create a free account to purchase workflows.
Need help setting this up?
Book a 3-hour live setup session with an Agility consultant.