# Build a financial documents assistant with Qdrant and Mistral: n8n workflow

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

Source: https://millionrounds.com/workflow/build-a-financial-documents-assistant-with-qdrant-and-mistra (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 financial documents assistant with Qdrant and Mistral

Started by someone opening a chat with it, and works across Qdrant. It puts Mistral behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 23 steps, 3 branches: large, and worth reading before you trust it with anything live.

Large Calls a model: Mistral Retrieval

[Download free](https://millionrounds.com/login?next=%2Fapp%2Fworkflow%2Fbuild-a-financial-documents-assistant-with-qdrant-and-mistra)

**23 steps** Large: read it before trusting it with anything live

**3** Branches: places the flow splits

**0** Loops or waits

**1** Service it connects to

## The flow

Starts it 3 Model 9 Logic 6 Service 5

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

- 1 **Local File Trigger** Local File trigger *Starts it*
- 2 **When clicking "Test workflow"** Manual trigger *Starts it*
- 3 **Embeddings Mistral Cloud** Embeddings Mistral Cloud *Model*
- 4 **Recursive Character Text Splitter** Text Splitter Recursive Character Text Splitter *Model*
- 5 **Chat Trigger** Chat trigger *Starts it*
- 6 **Mistral Cloud Chat Model** Lm Chat Mistral Cloud *Model*
- 7 **Embeddings Mistral Cloud1** Embeddings Mistral Cloud *Model*
- 8 **Set Variables** Set *Logic*
- 9 **Qdrant Vector Store** Vector Store Qdrant *Model*
- 10 **Default Data Loader** Document Default Data Loader *Model*
- 11 **Question and Answer Chain** Chain Retrieval Qa *Model*
- 12 **Qdrant Vector Store1** Vector Store Qdrant *Model*
- 13 **Handle File Event** Switch *Logic*
- 14 **Vector Store Retriever** Retriever Vector Store *Model*
- 15 **Search For Existing Point** Http Request *Service*
- 16 **Search For Existing Point1** Http Request *Service*
- 17 **Read File** Read Write File *Service*
- 18 **Has Existing Point?** If *Logic*
- 19 **Has Existing Point?1** If *Logic*
- 20 **Prepare Embedding Document** Set *Logic*
- 21 **Delete Existing Point1** Http Request *Service*
- 22 **Delete Existing Point** Http Request *Service*
- 23 **Remap for File_Added Flow** Set *Logic*

## How it's built

- **Starts on:** Someone opening a chat with it
- **Steps:** 23, with 3 branches
- **Size:** Large: read it before trusting it with anything live
- **Connects to:** Qdrant
- **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 Qdrant account, 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?

Take your time. At 23 steps it is large: read it before trusting it with anything live.

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 23 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-financial-documents-assistant-with-qdrant-and-mistra)
- **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.

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

## Workflows like it

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

- [**Process documents & build semantic search with OpenAI** 23 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/process-documents-and-build-semantic-search-with-openai)
- [**Document RAG & chat agent: Google Drive to Qdrant with Mistral** 25 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/document-rag-and-chat-agent-google-drive-to-qdrant-with-mist)
- [**Filter by keyword within given documents with OpenAI** 18 steps · calls a model · Qdrant](https://millionrounds.com/workflow/filter-by-keyword-within-given-documents-with-openai)
- [**Automated document compliance validation with a local model** 17 steps · calls a model · Qdrant](https://millionrounds.com/workflow/automated-document-compliance-validation-with-a-local-model)
- [**Build a PDF Document RAG System with Mistral and Qdrant** 29 steps · calls a model · Google Drive, Qdrant](https://millionrounds.com/workflow/build-a-pdf-document-rag-system-with-mistral-and-qdrant)
- [**Index and query financial documents with Qdrant and Mistral** 16 steps · Qdrant](https://millionrounds.com/workflow/index-and-query-financial-documents-with-qdrant-and-mistral)