--- 
## Introduction
---

To let Synerise track data related to items, you must import an item feed. It is the list of all items and their attributes. 

In most cases, you upload the data into a catalog (catalogs allow you to store all kinds of data) which is then used to configure AI engine. In case of Google Merchant XML files, it's also possible to import the data from a URL when configuring the AI engine.

You can use the data to:
- generate recommendations,
- offer an item search engine,
- [enrich events](/docs/assets/events/adding-event-parameters#enriching-events-with-data-from-catalogs) (not covered in this article) with data from the catalog, so you don't need to store all the data on the item's web page (this doesn't require configuring an AI model for the catalog),
- you can also use this data in campaign inserts to display product data.

**From this chapter you will learn:**
<br></br><img src="/api/docs/image/54176ad07f146575310749eba44b7c2f42c1b327/icons/check-s.svg" alt="Arrow down icon" class="icon">how to import an item feed to a Synerise catalog from a CSV, JSON, or Google Merchant XML file (recommended),
<br></br><img src="/api/docs/image/54176ad07f146575310749eba44b7c2f42c1b327/icons/check-s.svg" alt="Arrow down icon" class="icon">how to use that item feed to create an AI model for recommendations.

<br> 

<img src="/api/docs/image/54176ad07f146575310749eba44b7c2f42c1b327/themes/book/static/images/icon-api.svg" alt="Arrow down icon" class="icon"> **Why you need this integration:** To store data about your items in Synerise

<img src="/api/docs/image/54176ad07f146575310749eba44b7c2f42c1b327/themes/book/static/images/icon-communication.svg" alt="Arrow down icon" class="icon">**What type of campaigns require such integration:** All campaigns that have a product context, such as abandoned cart, last viewed product, AI recommendations, AI search, and so on.

## Importing manually
---
You can import data manually when:
- It meets the requirements listed in the ["Requirements for item catalogs" section of this article](/docs/ai-hub/item-feed/item-feed-in-catalog).
  If the file doesn't meet the requirements, use [Automation](#importing-with-automation) to transform it.
- You only want to import the data once.  
  If you want to import data periodically, it's better to [automate](#importing-with-automation) the process.

### From CSV

CSV files can be imported manually into a catalog in the **Data Modeling Hub**.

If the file meets the requirements listed in the ["Requirements for item catalogs" section of this article](/docs/ai-hub/item-feed/item-feed-in-catalog), you can import it:
1. Go to **Data Modeling Hub > Catalogs**.
2. Click **New Catalog**.
3. Enter a name for the catalog.
4. Open the catalog.
5. Click **Import CSV** and upload the file.
6. As the **Primary key**, select the **itemId** column.  
  If your file doesn't have this column, it doesn't meet the requirements and the file can't be imported this way as an item feed.

You can now use data from the catalog to enrich events. If you want to use it for recommendations, proceed to ["Selecting the catalog as the item feed for recommendations"](#selecting-a-catalog-as-the-item-feed-for-recommendations).  
Enabling AI search for the catalog is covered in later lessons.

Watch our video to see how to do it in practice.

<div class="youtube-embed youtube-facade not-prose" data-youtube-id="GOtLNyeEjqU" role="button" tabindex="0" aria-label="Play YouTube video"><img src="https://img.youtube.com/vi/GOtLNyeEjqU/hq720.jpg" alt="YouTube video" class="youtube-facade-thumb" loading="lazy" /><span class="youtube-facade-play" aria-hidden="true"><svg viewBox="0 0 68 48" width="68" height="48"><path d="M66.52 7.74c-.78-2.93-2.49-5.41-5.42-6.19C55.79.13 34 0 34 0S12.21.13 6.9 1.55c-2.93.78-4.64 3.26-5.42 6.19C.06 13.05 0 24 0 24s.06 10.95 1.48 16.26c.78 2.93 2.49 5.41 5.42 6.19C12.21 47.87 34 48 34 48s21.79-.13 27.1-1.55c2.93-.78 4.64-3.26 5.42-6.19C67.94 34.95 68 24 68 24s-.06-10.95-1.48-16.26z" fill="red"/><path d="M45 24 27 14v20" fill="white"/></svg></span></div>

### From JSON (API only)

JSON files can be manually imported into a catalog by using the API.

If the file meets the requirements listed in the ["Requirements for item catalogs" section of this article](/docs/ai-hub/item-feed/item-feed-in-catalog), you can import it:
1. Go to **Data Modeling Hub > Catalogs**.
2. Click **New Catalog**.
3. Use the ["Batch add items" API endpoint](https://developers.synerise.com/DataManagement/DataManagement.html#operation/addItemsBatch).

You can now use data from the catalog to enrich events. If you want to use it for recommendations, proceed to ["Selecting the catalog as the item feed for recommendations"](#selecting-a-catalog-as-the-item-feed-for-recommendations).  
Enabling AI search for the catalog is covered in later lessons.

## Importing from a Google Merchant Center XML file
---

<div class="admonition admonition-note"><div class="admonition-icon"><svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 24 24" stroke="currentColor" stroke-width="2.5"><path stroke-linecap="round" stroke-linejoin="round" d="M13 16h-1v-4h-1m1-4h.01M21 12a9 9 0 11-18 0 9 9 0 0118 0z" /></svg></div><div class="admonition-body"><div class="admonition-content">

This is the recommended solution.

</div></div></div>


The Google Merchant Center XML can be imported in the following ways:
- If it meets the requirements listed in [Google Merchant Center XML item feed](/developers/product-feed), you can import from a URL it when configuring the AI engine.  
  
- If it doesn't meet the requirements, you must use [Automation](#importing-with-automation) to transform the data and import into a catalog.


After you upload the data or have the Google Merchant Center XML file available under a URL, you can import it as described in the User Guide: [AI Engine Configuration](/docs/settings/configuration/ai-engine-configuration).



## Importing With Automation
---
You can use Automation to:
- Import data periodically.  
  If you only need to import CSV data once and it meets all the requirements, it may be more convenient to do it from the Data Management module.
- Import data that needs to be transformed first.  
  If the data doesn't meet the requirements (for example, column names need to be changed) you can use the data transformation capabilities of Automation to modify the data "on the fly" while importing.


  <div class="admonition admonition-note"><div class="admonition-icon"><svg xmlns="http://www.w3.org/2000/svg" fill="none" viewBox="0 0 24 24" stroke="currentColor" stroke-width="2.5"><path stroke-linecap="round" stroke-linejoin="round" d="M13 16h-1v-4h-1m1-4h.01M21 12a9 9 0 11-18 0 9 9 0 0118 0z" /></svg></div><div class="admonition-body"><div class="admonition-content">

  You can now use data from the catalog to enrich events. If you want to use it for recommendations, proceed to ["Selecting the catalog as the item feed for recommendations"](#selecting-a-catalog-as-the-item-feed-for-recommendations).  
  Enabling AI search for the catalog is covered in later lessons.

  </div></div></div>



- [Automation](/docs/automation) - automation lets you import data periodically and/or modify it during the process.


## Selecting a catalog as the item feed for recommendations
---
Create an AI model from the catalog according to the User Guide: [AI Engine Configuration](/docs/settings/configuration/ai-engine-configuration).

When you choose a catalog as the base of an AI model, the model is updated whenever the catalog's content changes (the update may take up to an hour).



This section provides a verification checklist **for ITEM FEED** to ensure that all of the necessary steps are taken. It includes a list of information that must be collected and evaluated to make sure that everything works. 





