[ AI ]
LocalAI integration for your workflows.
Connect LocalAI to Collabase once and use 6 actions in your workflows. No code needed, hosted in Switzerland.
LocalAI in Collabase
Connect LocalAI to Collabase once and use 6 actions in your workflows. No code needed, hosted in Switzerland.
[ About the service ]
The free, Self-hosted, community-driven and local-first. Drop-in replacement for OpenAI running on consumer-grade hardware. No GPU required.
How to connect it
- Open the integrations in the workspace settings.
- Choose LocalAI and connect your account.
- Add a trigger or an action to the workflow.
LocalAI triggers
LocalAI does not start a workflow on its own. You use its actions after any other trigger.
LocalAI actions
| Name | Description | Fields |
|---|---|---|
| Ask LocalAI | Ask LocalAI anything you want! |
+ 2
|
| List Models | List the models installed on your LocalAI server. |
|
| Create Embedding | Turn text into a vector for semantic search or clustering. |
|
| Text to Speech | Turn text into a spoken audio file. |
|
| Transcribe Audio | Turn speech in an audio file into text. |
|
| Custom API Call | Make a custom API call to a specific endpoint |
+ 3
|
[ AI ]
Related integrations
Tools that often share a workflow.
Questions about LocalAI
What can I automate with LocalAI in Collabase?
LocalAI brings 6 actions and 0 triggers, for example Ask LocalAI, List Models, Create Embedding, Text to Speech and 2 more. You combine them in a workflow without code and mix them with every other integration.
How do I connect LocalAI to Collabase?
You open the integrations in the workspace settings, choose LocalAI and connect your account once, using custom credentials. After that all triggers and actions are available in the workflow.
Does the LocalAI integration cost extra?
No. All integrations are included in every licence, in the Isolated Cloud and in Self-Hosted operation. There is no module price.
Test it against your own content. A proof of concept is ready within days.
We set up an instance with your content and you test it against real workflows. In a first conversation we clarify scope, operating model and timing.