AI is most useful when it sits inside the rest of your automation, not as a separate manual step. The Mistral AI integration lets your workflows call Mistral language models, generate embeddings for semantic search, and analyze images using your own Mistral API key, with the response available as a workflow variable for any later step.
Retrieving Your API Key
To get your API key, start logging in to “ console.mistral.ai ” with your usual credentials.
Open API Keys and click Create new key.
Give it a recognizable name, add any other relevant details, such as an Expiration time or Connector access scope, and lastly, click Create new key.
Copy the key and save it in an accessible place, as you'll need it for the connection.
How to Set Up Mistral AI
You can connect your Mistral AI in one of two ways:
Via the Workflow Builder
Create or edit a workflow in the Automation section.
Add an Action, switch to the Apps tab, then select any Mistral AI action.
Click Connect your account on the action card.
Via Settings
Go to the Integrations section inside your account settings. In there, locate Mistral AI in the integrations list and click Connect.
Paste your Mistral API key.
Click Save to complete the connection.
Available Actions
Once connected, you can start using the following Mistral AI actions:
Create Chat Completion
Send a prompt (and optional system prompt) to a Mistral language model and receive a generated text response.
Create Embeddings
Convert input text into a 1024-dimensional vector for semantic search, RAG, classification, or clustering.
Analyze Image (Vision)
Send an image URL and a prompt to a vision-capable Mistral model and receive a natural-language answer about the image.
Using these actions, you can easily implement multilingual customer reply generation and semantic FAQ matching for inbound questions, as well as extract receipts and documents from images, making your business more efficient and accessible across the board. We hope you enjoy it!