PDF Q&A RAG Pipeline: LlamaIndex, OpenAI & Pinecone

Automates PDF ingestion from Google Drive: parses with LlamaIndex, normalizes, chunks, embeds with OpenAI, and stores in Pinecone for RAG-based Q&A chatbots.

This workflow builds a complete Retrieval-Augmented Generation (RAG) pipeline for PDF documents, ideal for structured content like insurance policies, legal docs, or compliance files. It triggers on new PDFs in a Google Drive folder, uploads them to LlamaIndex Cloud for accurate parsing into clean Markdown, then normalizes the text by stripping headers, footers, page numbers, and formatting artifacts using custom regex in a function node. Next, it intelligently splits the normalized content int
Platform
n8n
Category
Development & IT
Price
$24.99
Creator
Bryce Yu

How to import this workflow into n8n

  1. 1Purchase or download the workflow to get the n8n workflow JSON file.
  2. 2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
  3. 3Open each node marked with a credential warning and connect your own accounts and API keys.
  4. 4Run the workflow once manually to verify the data flow, then toggle it to Active.

Related Development & IT workflows

More from Bryce Yu

All Development & IT workflows →All n8n workflows →

Need this deployed? We'll set it up for you.

Our automation experts deploy this workflow in your stack, connect your accounts, and verify it works — or build a custom solution from scratch.

Get It DeployedCustom Build