PDF Proposal KB: S3, OpenAI GPT-4o & Qdrant RAG Agent
Ingests PDFs from S3, extracts/chunks text, embeds with OpenAI, and indexes into Qdrant. Enables RAG chat agent for querying proposal knowledge base.
This workflow provides an end-to-end solution for building a knowledge base from PDF proposals stored in AWS S3. It starts with listing objects in an S3 bucket, looping through PDF files, downloading them, and extracting text. The text is then chunked into manageable pieces, embedded using OpenAI embeddings, and indexed into a Qdrant vector database with metadata for efficient retrieval.
The second part exposes a chat interface via a trigger node connected to an AI Agent powered by OpenAI GPT-4
Platform
n8n
Category
HR Management
Price
$24.99
Creator
Bryce Yu
RAG
Qdrant
OpenAI
GPT-4o
S3
PDF
Embeddings
Knowledge Base
AI Agent
Vector DB
How to import this workflow into n8n
1Purchase or download the workflow to get the n8n workflow JSON file.
2In your n8n instance, open Workflows and choose "Import from File" (or paste the JSON with Ctrl+V on the canvas).
3Open each node marked with a credential warning and connect your own accounts and API keys.
4Run the workflow once manually to verify the data flow, then toggle it to Active.