Replicate
Most recent version: v0.1.0
Last updated
Was this helpful?
Most recent version: v0.1.0
Last updated
Was this helpful?
See the changelog of this Action type .
Note that this Action is only available in certain Tenants. Contact us if you need to use it and don't see it in your Tenant.
This action offers automatic integration with models available on the Replicate platform, whether publicly accessible or privately deployed. This component simplifies accessing and utilizing a wide array of models without manual integration efforts.
Integrating Onum with replicate.com can offer several benefits, enhancing the platform's capabilities and the value it delivers:
Access to a Broad Range of Models
Ease of Model Deployment
Scalability
Continuous Model Updates
Cost-Effective AI Integration
Rapid Prototyping and Experimentation
Enhanced Data Privacy and Security
In order to configure this action, you must first link it to a Listener. Go to Building a Pipeline to learn how to link.
These are the input and output ports of this Action:
To open the configuration, click the Action in the canvas and select Configuration.
Enter the required parameters:
Token*
The API token of the model you wish to
Version*
The version can usually be located by running a command on the machine using Replicate API.
Input
This will be the input IP.
Output
Specify a name for the output event.
Click Save to complete.
It is possible to use all the public models from https://replicate.com/collections/language-models related to process natural language.
To fill in the values, you need to utilize the information about the user and model from Replicate.com and execute a copy/paste. The following image illustrates how to locate the required parameters on the Replicate.com model website.
Just in case, if the version does not appear, choose the Cog tag and copy the version like in the following picture.
A version identifies every model and requires a set of input parameters.