Index and query financial documents with Qdrant and Mistral
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 16 nodes and runs manually, when you click “Execute workflow”. Along the way it connects Embeddings Mistral Cloud and Qdrant Vector Store.
How it runs
Trigger: Manually, when you click “Execute workflow”.
- Set Variables (Edit Fields (Set)): sets 5 fields: directory, file_added, file_changed…
- Handle File Event (Switch): routes items into 3 branches
- Search For Existing Point (HTTP Request): calls an HTTP API (POST)
- Search For Existing Point (HTTP Request): calls an HTTP API (POST)
- Read File (Read/Write Files from Disk): reads a file from disk
- Has Existing Point? (If): checks a condition and branches into true / false
- Has Existing Point? (If): checks a condition and branches into true / false
- Prepare Embedding Document (Edit Fields (Set)): sets 2 fields: data, file_location
- Delete Existing Point (HTTP Request): calls an HTTP API (POST)
- Delete Existing Point (HTTP Request): calls an HTTP API (POST)
…plus 2 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (10)
- Manual Trigger
n8n-nodes-base.manualTrigger - Edit Fields (Set)
n8n-nodes-base.set - Read/Write Files from Disk
n8n-nodes-base.readWriteFile - Embeddings Mistral Cloud
@n8n/n8n-nodes-langchain.embeddingsMistralCloud - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - HTTP Request
n8n-nodes-base.httpRequest - If
n8n-nodes-base.if - Switch
n8n-nodes-base.switch - Qdrant Vector Store
@n8n/n8n-nodes-langchain.vectorStoreQdrant
From the author
Quick Overview This workflow ingests local financial documents into a Qdrant vector database using Mistral Cloud embeddings, keeping the index in sync when files are added, changed, or deleted. How it works 1. Runs when you manually start the workflow (for…