Build a PDF Q&A system with LlamaIndex, OpenAI embeddings & Pinecone vector DB

by Alok Kumar ✓ · 724 views · created 2025-08-22 · AI RAG, Multimodal AI

What this workflow does

This AI workflow has 13 nodes and runs on Google Drive events (file created). Along the way it connects Google Drive, Embeddings OpenAI and Pinecone Vector Store. It also calls api.cloud.llamaindex.ai over HTTP.

How it runs

Trigger: On Google Drive events (file created).

1. Download file (Google Drive): download
2. Upload to Llama Cloud (HTTP Request): calls api.cloud.llamaindex.ai (POST)
3. Wait: waits 30 seconds
4. Check Parsing Status (HTTP Request): calls an HTTP API
5. If: checks a condition and branches into true / false
6. Extract Markdown from Llama Cloud (HTTP Request): calls an HTTP API
7. Wait: waits 60 seconds
8. Normalize Text (Code): runs custom JavaScript code
9. Store in Pinecone (Pinecone Vector Store): stores documents in the Pinecone vector store, with embeddings: Generate Embeddings; document loader: Default Data Loader

Services it uses

Google DriveEmbeddings OpenAIPinecone Vector Store

HTTP calls to: api.cloud.llamaindex.ai

Before you upgrade to n8n 3.0

Nodes used (10)

• Google Drive Triggern8n-nodes-base.googleDriveTrigger
• Google Driven8n-nodes-base.googleDrive
• Default Data Loader@n8n/n8n-nodes-langchain.documentDefaultDataLoader
• Waitn8n-nodes-base.wait
• Ifn8n-nodes-base.if
• HTTP Requestn8n-nodes-base.httpRequest
• Coden8n-nodes-base.code
• Recursive Character Text Splitter@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter
• Embeddings OpenAI@n8n/n8n-nodes-langchain.embeddingsOpenAi
• Pinecone Vector Store@n8n/n8n-nodes-langchain.vectorStorePinecone

From the author

Parse, Normalize, Extract, and Store PDF Content for RAG in Pinecone This workflow automates a full RAG pipeline for structured documents (like insurance policies). What it does - Watches a Google Drive folder for new PDFs - Uploads to LlamaIndex Cloud for…

View the original on n8n.io → Check your own copy