> For the complete documentation index, see [llms.txt](https://help.citrusad.com/retail-media-interface/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.citrusad.com/retail-media-interface/integration/data-api/api-overview/ad-generation-filtering-1.md).

# Ad generation filtering

When requesting ads, you should aim to support your customer's filtering by brand, categories, dietary restrictions, and more. If your e-commerce site supports filtering that uses the and/or functionality, Epsilon Retail Media can support this with the additional `filterMode` parameter in your request.

There are two types of filtering, as outlined below.

## `andOr` filtering (recommended)

`andOr` filtering is useful for contexts where the user has filtered deep in their search. It allows simpler context formatting, while still supporting deep filtering. This method follows the structure outlined below:

```json
"productFilters": [
     [ "" OR "" ] AND [ "" OR "" ] AND [ "" OR "" ]
    ],
    "options": {
     "filterMode": "AndOr"
    },
```

An example request looks like the following:

```http
POST $BASE_URL/v1/ads/generate HTTP/1.1
accept: application/json
content-type: application/json
Authorization: Basic <API_KEY>
{
    "customerId": "wertg5432a",
    "sessionId": "ec9-4e07-881d-3e9",
    "placement": "category",
    "catalogId": "628dbe95-2ec9-4e07-881d-3e9f92ab2e0b",
    "productFilters": [
     	 ["category:bread"],
    	 ["brand:brandA","brand:brandB"],
    	 ["price:below $10"],
    	 ["nutrition:organic","nutrition:vegan"]
    ],
    "options": {
   							 "filterMode": "AndOr"
 							 },
    "maxNumberOfAds": 3
}
```

This approach is typically easier for retailers to chain requests by type when customers filter deep into their searches.

{% hint style="warning" %}
You must specify the `filterMode` of `andOr` for this functionality to work correctly.
{% endhint %}

## `orAnd` filtering (default mode)

The default method of filtering product filters follows the structure outlined below:

```json
"productFilters": [
     [ "" AND "" ], OR [ "" AND "" ], OR [ "" AND "" ]
    ],
    "options": {
     "filterMode": "OrAnd"
    },
```

The same example presented above would be sent as a request like the below:

```http
POST $BASE_URL/v1/ads/generate HTTP/1.1
accept: application/json
content-type: application/json
Authorization: Basic <API_KEY>
{
    "customerId": "wertg5432a",
    "sessionId": "ec9-4e07-881d-3e9",
    "placement": "category",
    "catalogId": "628dbe95-2ec9-4e07-881d-3e9f92ab2e0b",
    "productFilters": [
     	 ["category:bread","brand:brandA","price:below $10","nutrition:organic"],
     	 ["category:bread","brand:brandB","price:below $10","nutrition:organic"],
     	 ["category:bread","brand:brandA","price:below $10","nutrition:vegan"],
     	 ["category:bread","brand:brandB","price:below $10","nutrition:vegan"],
    ],
    "options": {
   							 "filterMode": "OrAnd"
 							 },
    "maxNumberOfAds": 3
}
```

{% hint style="info" %}
You don’t need to specify a `filterMode` of `orAnd` for this functionality, as it is the default behaviour.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://help.citrusad.com/retail-media-interface/integration/data-api/api-overview/ad-generation-filtering-1.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.