Skip to content
Book a demo
Open the menu Close the menu
Call us 06 59 01 09 31 Book a demo

Ollama

AI on your email, without the email leaving your servers

Point Loop & Roll at your Ollama server and its models power your AI steps. No account, no key, and the content of your email stays on machines you control.

Connection
Server address
Actions
5
Book a demo Read the setup guide
Sort sensitive email locally Hover a node to see its role · Drag to move the graph
Email receivedEmail receivedEmail receivedCategorize with Ollama — CategorizeCategorize with OllamaCategorizeMatchesotherModelMoveMoveMove
Sort sensitive email locally

What you can automate with Ollama

Link the Ollama (local) model node to the Model port of any AI node: that step then runs on Ollama.

Actions

The AI steps this model can power.

  • Categorize

    Classifies the email into the categories you define and routes it down the matching branch.

  • Extract

    Extracts the fields you declare from the email (number, date, amount…) into the working data.

  • Summarize

    Summarizes the email in a few lines, in the style and length you choose.

  • Compose (AI)

    Has the model write a message from your instructions and the recipient profile (formality, tone, language, signature).

  • Free instruction (AI)

    Gives the model a free-form instruction about the email and the working data.

Workflows you can build

Each one starts from a real situation and uses only nodes that exist today. Test it on past emails before you publish it.

  • Sort sensitive email locally

    Requests are classified by a model running on your server, then filed — nothing is sent to an outside AI provider.

    1. Email received
    2. Categorize with Ollama
    3. Move

  • Extract fields from confidential documents

    Attachments are read and their fields extracted on your own hardware before being written to a table.

    1. Email received
    2. Read attachments
    3. Extract with Ollama
    4. Table — insert or update

How to connect Ollama

An administrator points Loop & Roll at the Ollama server address. No account and no key are needed.

Before you start

  • A running Ollama server with at least one model pulled.
  • The server reachable from the Loop & Roll server, which makes the calls.
  • An administrator account on Loop & Roll.

The full guide in the documentation

  1. Pull a model on your Ollama server and make it reachable from the Loop & Roll server.
  2. As an administrator, open Connections and, in the Artificial intelligence section, click Configure on the Ollama row.
  3. Enter the server address, choose the enabled models, then click Save and Test.
  4. In a workflow, link an Ollama model node to the Model port of any AI node.

See also

Related integrations

See all integrations

Automate Ollama with Loop & Roll

We build the workflow around your processes, test it on your past emails and put it into service with your teams.

Book a demo Ask to be called back 06 59 01 09 31

Product names and logos on this page belong to their respective owners and are used only to identify their services. Loop & Roll is not affiliated with or endorsed by them.