# Build a cost estimation chatbot with Mistral and OCR: n8n workflow

> Started by someone opening a chat with it, and works across Gmail and Supabase. It puts Mistral behind a retrieval step, so answers are drawn from documents...

Source: https://millionrounds.com/workflow/build-a-cost-estimation-chatbot-with-mistral-and-ocr (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)

# Build a cost estimation chatbot with Mistral and OCR

Started by someone opening a chat with it, and works across Gmail and Supabase. It puts Mistral behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 16 steps, 1 branch: a working afternoon to understand properly.

Medium Calls a model: Mistral Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-cost-estimation-chatbot-with-mistral-and-ocr)

**16 steps** Medium: a working afternoon

**1** Branch: places the flow splits

**0** Loops or waits

**2** Services it connects to

## The flow

Starts it 1 Model 4 Logic 4 Service 7

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

- 1 **Mistral Cloud Chat Model4** Lm Chat Mistral Cloud *Model*
- 2 **Simple Memory1** Memory Buffer Window *Model*
- 3 **Calculator1** Tool Calculator *Model*
- 4 **When chat message received** Chat trigger *Starts it*
- 5 **Send a message in Gmail** Gmail Tool *Service*
- 6 **OCR (ANY OCR API)** Http Request *Service*
- 7 **Supabase Get** Supabase Tool *Service*
- 8 **ai agent cost estimate** Agent *Model*
- 9 **CHECK IF BINARY FILE IS PRESENT OR NOT** If *Logic*
- 10 **Split Out** Split Out *Logic*
- 11 **Merge** Merge *Logic*
- 12 **NORMALIZE binary file** Code *Logic*
- 13 **Mistral Upload** Http Request *Service*
- 14 **Mistral Signed URL** Http Request *Service*
- 15 **Mistral DOC OCR** Http Request *Service*
- 16 **STORE OCR OUTPUT** Supabase *Service*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 16, with 1 branch
- **Size:** Medium: a working afternoon
- **Connects to:** Gmail, Supabase
- **Model:** Mistral
- **Retrieval:** Answers are drawn from documents you supply, not from the model alone

## Questions

What does it need to run?

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

What starts it?

It starts on someone opening a chat with it.

Does it use AI?

Yes. It calls Mistral. 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. 16 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 16 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%2Fbuild-a-cost-estimation-chatbot-with-mistral-and-ocr)
- **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.

## Connects to

Each opens the other workflows that use it.

[Gmail](https://millionrounds.com/workflows?service=Gmail#library)[Supabase](https://millionrounds.com/workflows?service=Supabase#library)

## Workflows like it

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

- [**Bank Statement OCR to Oracle Database with Mistral and OpenAI** 16 steps · calls a model · Gmail](https://millionrounds.com/workflow/bank-statement-ocr-to-oracle-database-with-mistral-and-opena)
- [**Send specific PDF attachments from Gmail to Google Drive** 16 steps · calls a model · Gmail, Google Drive](https://millionrounds.com/workflow/send-specific-pdf-attachments-from-gmail-to-google-drive)
- [**Organize Gmail attachments in Google Drive folders based on** 16 steps · Gmail, Google Drive](https://millionrounds.com/workflow/organize-gmail-attachments-in-google-drive-folders-based-on)
- [**Aggregate & update documentation from Slack, Teams & GitHub** 17 steps · calls a model · GitHub, Gmail](https://millionrounds.com/workflow/aggregate-and-update-documentation-from-slack-teams-and-gith)
- [**Analyze Instagram profiles with Apify and Gemini** 17 steps · calls a model · Apify, Supabase](https://millionrounds.com/workflow/analyze-instagram-profiles-with-apify-and-gemini)
- [**Analyze Instagram profiles with Apify and Gemini** 17 steps · calls a model · Apify, Supabase](https://millionrounds.com/workflow/analyze-instagram-profiles-with-apify-and-gemini-2)