AI Agents

Build an intelligent agent that retrieves documents and answers with OpenAI

23 nodes 293 176 Automatic trigger
Download

Workflow Description

An automation that collects Google Drive documents, segments them, and stores them in a Qdrant vector store, then uses an AI agent powered by OpenAI to answer questions based on retrieved content while maintaining conversation history.

How it works

  1. 1.Receive questions via webhook and trigger the agent
  2. 2.Load documents from Google Drive and split them for processing
  3. 3.Convert text to embeddings and store them in Qdrant
  4. 4.Search vectors and retrieve relevant documents
  5. 5.Generate answers using OpenAI model while preserving conversation context
  6. 6.Respond to the original request with the final answer

Use cases

  • Enterprise assistant that answers employee questions based on company documentation
  • Customer support system that retrieves answers from an automatically updated knowledge base

Requirements

  • Active OpenAI account with valid API key
  • Google Drive account containing documents to process
  • Running Qdrant instance or Qdrant Cloud account

Service Value

Ideal as a smart automation service combining integrations and AI to produce ready-to-use results.

Apps Used

AI Agent Vector Store OpenAI Google Drive Document Default Data Loader Text Splitter Memory

Details

Trigger Automatic trigger
Nodes 23
Apps 7
Views 293
Downloads 176

How to Use

  1. 1.Click "Download Template"
  2. 2.Open your n8n dashboard
  3. 3.Go to Workflows > Import from File
  4. 4.Select downloaded file and configure credentials

Nodes Used (23)

/

AI Agent

Agent

#1

Vector Store Tool

Tool Vector Store

#2

Qdrant Vector Store

Vector Store Qdrant

#3

Embeddings OpenAI

OpenAI

#4

Sticky Note4

Sticky Note

#5

Sticky Note

Sticky Note

#6

When clicking ‘Test workflow’

Manual Trigger

#7

Create collection

HTTP Request

#8

Refresh collection

HTTP Request

#9

Get folder

Google Drive

#10

Download Files

Google Drive

#11

Default Data Loader

Document Default Data Loader

#12

Token Splitter

Text Splitter Token Splitter

#13

Sticky Note3

Sticky Note

#14

Qdrant Vector Store1

Vector Store Qdrant

#15

Embeddings OpenAI1

OpenAI

#16

Sticky Note5

Sticky Note

#17

Respond to ElevenLabs

Webhook

#18

OpenAI

OpenAI

#19

Listen

Webhook

#20

Window Buffer Memory

Memory Buffer Window

#21

OpenAI Chat Model

OpenAI

#22

Sticky Note6

Sticky Note

#23