AI Agents

Generate Citations from OpenAI-Powered RAG File Retrieval

19 nodes 302 158 Automatic trigger
Download

Workflow Description

An automation that receives chat inquiries, processes them through OpenAI to generate evidence-based responses with citations from retrieved files, and maintains conversation memory for improved contextual answers over time.

How it works

  1. 1.Receive user questions via chat trigger and store them in conversation memory
  2. 2.Send queries to OpenAI with retained context to generate cited, verified responses
  3. 3.Process and format citations from retrieved files and return them alongside the answer

Use cases

  • Build a customer support system that answers from a defined knowledge base with source attribution
  • Create an intelligent search engine that cites original documents when answering queries
  • Develop a data analysis assistant that links conclusions back to reliable source materials

Requirements

  • Active OpenAI API account with valid API key configured
  • Reference files or texts loaded and prepared for retrieval in the system

Service Value

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

Apps Used

Memory Chat Trigger OpenAI

Details

Trigger Automatic trigger
Nodes 19
Apps 3
Views 302
Downloads 158

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 (19)

/

Aggregate

Aggregate

#1

Window Buffer Memory

Memory Buffer Window

#2

Sticky Note4

Sticky Note

#3

Sticky Note

Sticky Note

#4

Create a simple Trigger to have the Chat button within N8N

Chat Trigger

#5

OpenAI Assistant with Vector Store

OpenAI

#6

Sticky Note1

Sticky Note

#7

Get ALL Thread Content

HTTP Request

#8

Sticky Note2

Sticky Note

#9

Split all message iterations from a thread

Split Out

#10

Split all content from a single message

Split Out

#11

Split all citations from a single message

Split Out

#12

Retrieve file name from a file ID

HTTP Request

#13

Regularize output

Set

#14

Sticky Note3

Sticky Note

#15

Sticky Note5

Sticky Note

#16

Sticky Note6

Sticky Note

#17

Optional Markdown to HTML

Markdown

#18

Finnaly format the output

Code

#19