# Replicate

{% hint style="info" %}
See the changelog of this Action type [here](/actions/replicate.md).
{% endhint %}

{% hint style="warning" %}
Note that this Action is only available in certain Tenants. [Contact us](/support/support.md) if you need to use it and don't see it in your Tenant.
{% endhint %}

## Overview

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

{% hint style="warning" %}
In order to configure this action, you must first link it to a Listener. Go to [Building a Pipeline ](/the-workspace/pipelines/building-a-pipeline.md)to learn how to link.
{% endhint %}

## Ports <a href="#ports" id="ports"></a>

These are the input and output ports of this Action:

<details>

<summary>Input ports</summary>

* **Default port** - All the events to be processed by this Action enter through this port.

</details>

<details>

<summary>Output ports</summary>

* **Default port** - Events are sent through this port if no error occurs while processing them.
* **Error port** - Events are sent through this port if an error occurs while processing them.

</details>

## Configuration

{% stepper %}
{% step %}
Find **MLReplicate** in the **Actions** tab (under the **Enrichment** group) and drag it onto the canvas. Link it to the required [Listener](https://docs.onum.com/the-workspace/listeners) and [Data sink](https://docs.onum.com/the-workspace/pipelines/data-sinks).
{% endstep %}

{% step %}
To open the configuration, click the Action in the canvas and select **Configuration**.
{% endstep %}

{% step %}
Enter the required parameters:

<table><thead><tr><th width="215">Parameter</th><th>Description</th></tr></thead><tbody><tr><td><strong>Token</strong><mark style="color:red;"><strong>*</strong></mark></td><td>The API token of the model you wish to </td></tr><tr><td><strong>Version</strong><mark style="color:red;"><strong>*</strong></mark></td><td>The version can usually be located by running a command on the machine using Replicate API.</td></tr><tr><td><strong>Input</strong> </td><td>This will be the input IP.</td></tr><tr><td><strong>Output</strong> </td><td>Specify a name for the output event.</td></tr></tbody></table>
{% endstep %}

{% step %}
Click **Save** to complete.
{% endstep %}
{% endstepper %}

### Where to find these values

It is possible to use all the public models from <https://replicate.com/collections/language-models> related to process natural language.

<div data-full-width="false"><figure><img src="https://lh7-us.googleusercontent.com/aondLJf4DYTh5aV0skudDLvSQ44reZASafQAcObi1SBaMQMR1VmRepajkF1aBB8Vz0MJfUr44rEJLQlF9aNC37ga3cW2fi6bW2NFHkL95urricXGFifPaTtMHK8h8e5bSC7aPUfgRaGFwdRNgJqx_WI" alt=""><figcaption></figcaption></figure></div>

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.<br>

<figure><img src="https://lh7-us.googleusercontent.com/wFsbX-ERxKxrVjiJkVSFah5YvSKp76poIbqEYZi6gf1FLe9euQAeBRHoBqCcHcE96XIX8CtTAdzeQj0IgDX52HwotXdJUwCUbTT8VmGFNwPmjf7ExKLksFWVfnFBRZPbaam4EZB90uv-kNFlijivC7Y" alt=""><figcaption></figcaption></figure>

Just in case, if the version does not appear, choose the Cog tag and copy the version like in the following picture.&#x20;

<figure><img src="https://lh7-us.googleusercontent.com/KS00OIh4Acb6Fmq5W-zNzlDaX_JQR6vfS9I0JTid5aMu6DWzuTee4k48LBETPttO7GFJVLEhU2gcXIQ6iCZFgVNhjOcK9Gek-hxI7k2_wD2PRt-b3o8Okv2vTYQpNDstLlfMGS9aJe1iM6YJGHB0O_c" alt=""><figcaption></figcaption></figure>

A version identifies every model and requires a set of input parameters.&#x20;


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.onum.com/the-workspace/pipelines/actions/ai/replicate.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.