# Facebook Messenger Chatbot That Learns From Your Documents: n8n workflow

> Started by another system calling it. It calls services over plain HTTP rather than through connectors.

Source: https://millionrounds.com/workflow/facebook-messenger-chatbot-that-learns-from-your-documents (Millionrounds; every figure on the page links to its filing or article)

[Automation library](https://millionrounds.com/workflows) · [Documents and files](https://millionrounds.com/workflows?category=Documents+and+files#library)

# Facebook Messenger Chatbot That Learns From Your Documents

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 20 steps, 3 branches, 1 loop or waits: a working afternoon to understand properly.

Medium Calls a model: OpenAI Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ffacebook-messenger-chatbot-that-learns-from-your-documents)

**20 steps** Medium: a working afternoon

**3** Branches: places the flow splits

**1** Loop or waits

**0** Services by connector: it calls them over plain HTTP

## The flow

Starts it 5 Model 3 Logic 8 Service 4

The steps in the order they run, from what starts it.

- 1 **Facebook Verification Webhook** Webhook *Starts it*
- 2 **Facebook Message Webhook** Webhook *Starts it*
- 3 **Conversation Memory** Memory Buffer Window *Model*
- 4 **OpenAI Chat Model** Lm Chat Open Ai *Model*
- 5 **Get context snippets in Pinecone Assistant** Pinecone Assistant Tool *Service*
- 6 **Is Token Valid?** If *Logic*
- 7 **Acknowledge Event** Respond To Webhook *Starts it*
- 8 **AI Agent1** Agent *Model*
- 9 **Respond with Challenge** Respond To Webhook *Starts it*
- 10 **Respond Forbidden** Respond To Webhook *Starts it*
- 11 **Filter Valid Messages** If *Logic*
- 12 **Format Response** Code *Logic*
- 13 **Store Message for Batching** Code *Logic*
- 14 **Send Response to User** Http Request *Service*
- 15 **Send Seen Indicator** Http Request *Service*
- 16 **Success** Set *Logic*
- 17 **Wait 3 Seconds** Wait *Logic*
- 18 **Retrieve Batched Messages** Code *Logic*
- 19 **Has Messages to Process?** If *Logic*
- 20 **Send Typing Indicator** Http Request *Service*

## How it's built

- **Starts on:** Another system calling it
- **Steps:** 20, with 3 branches, 1 loop or waits
- **Size:** Medium: a working afternoon
- **Connects to:** Nothing by connector; it calls services over plain HTTP
- **Model:** OpenAI
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

An n8n account, and a key for OpenAI. You connect your own accounts after importing it; none are included.

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 20 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

**Before you run it**

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 20 steps before you point it at anything that matters.

## Run it in n8n

- **Create your n8n account** Free to start. n8n is where the workflow runs. [Create an n8n account ↗](https://millionrounds.com/n8n)
- **Download the workflow** Free with a Millionrounds account. [Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Ffacebook-messenger-chatbot-that-learns-from-your-documents)
- **Paste it into n8n** Open a new workflow in n8n and paste. Then connect your own accounts.

Stored with the author's traces removed: canvas notes, instance identifiers, saved credential names and any live document they had left behind.

## Workflows like it

Also documents and files, with the same services where possible, closest in size first.

- [**Automate purchase bill processing with QuickBooks** 20 steps · calls a model](https://millionrounds.com/workflow/automate-purchase-bill-processing-with-quickbooks)
- [**Build an OpenAI RAG system with Postgres** 20 steps · calls a model · Postgres](https://millionrounds.com/workflow/build-an-openai-rag-system-with-postgres)
- [**Document-based chatbot with OpenAI and Pinecone** 20 steps · calls a model · Airtable, Google Drive](https://millionrounds.com/workflow/document-based-chatbot-with-openai-and-pinecone)
- [**Financial document extraction from Gmail to Google Sheets** 20 steps · calls a model · Gmail, Google Sheets](https://millionrounds.com/workflow/financial-document-extraction-from-gmail-to-google-sheets)
- [**Generate DOCX documents from Gmail with OpenAI** 20 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/generate-docx-documents-from-gmail-with-openai)
- [**Generate SharePoint Word documents from Outlook emails** 20 steps · calls a model · Outlook](https://millionrounds.com/workflow/generate-sharepoint-word-documents-from-outlook-emails)