> For the complete documentation index, see [llms.txt](https://helpcenter.channable.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://helpcenter.channable.com/manage-improve-product-data/rules-bulk-edit-and-enrich/using-rules/rule-templates/send-custom-labels-to-openai.md).

# Send custom labels to OpenAI

Use an OpenAI rule template to send custom labels in ads\_metadata for campaign filtering.

OpenAI feeds use `ads_metadata` to receive custom labels. You can use these labels to segment products with Insights or Labelizer data.

### <i class="fa-memo-circle-check">:memo-circle-check:</i> Before you start

**You'll need**

* An OpenAI feed with a custom label field, such as `custom_label_0`.
* Google Ads [Insights](https://helpcenter.channable.com/manage-improve-product-data/insights/insights-for-ads.md) or [Labelizer](https://helpcenter.channable.com/css/optimization-tools/labelizer.md) fields (to use dynamic, performance-based labels).

**Good to know**

* You can only add custom labels to **new** campaigns in OpenAI.
* You can send multiple custom labels by creating one rule per custom label.

***

### Prepare custom labels in your Channable OpenAI feed

{% stepper %}
{% step %}

#### Add the OpenAI rule template

1. In your OpenAI feed in Channable, go to the **Rules** step.
2. Click **+ Create rule**.
3. Click **OpenAI rule templates > OpenAI custom label**.
   {% endstep %}

{% step %}

#### Select custom label fields

1. Create a new project field for `chatgpt_ads_metadata` :
   1. Click `chatgpt_ads_metadata` and select + **Add.**
   2. For **Name**, name your field chatgpt\_ads\_metadata.
   3. Click **Create**.
2. For the second `custom_label_0` field, select the label field you want to send.

{% hint style="info" %}
By default, the template uses `custom_label_0`. Select another custom label if it holds the relevant data.
{% endhint %}

3. If you selected another custom label, update the value in the THEN section. Replace both `custom_label_0` placeholders with your selected field name.

{% hint style="info" %}

#### Example

if you select `custom_label_1`, change this:

```json
{"custom_label_0":"custom_label_0"}
```

To this:

```json
{"custom_label_1":"custom_label_1"}
```

{% endhint %}

4. Click **Save rule**.
   {% endstep %}

{% step %}

#### Send additional labels

To set up more than one custom label:

1. Click <i class="fa-ellipsis-vertical">:ellipsis-vertical:</i> > **Duplicate rule**.
2. Repeat [Step 1](#add-the-openai-rule-template) and [2](#select-custom-label-fields), but change the label field and both JSON placeholders.
3. Click **Save rule** before creating another rule.
   {% endstep %}

{% step %}

#### Check the labels in your feed

1. In your OpenAI feed in Channable, go to **Preview & export**.
2. Open the **CSV Preview** tab.
3. Check the `ads_metadata` column for the mapped custom labels.
   {% endstep %}

{% step %}

### Add your labels to a new OpenAI campaign

Follow the steps in [Set up a ChatGPT Commerce feed for OpenAI ads](https://helpcenter.channable.com/list-advertise/list-on-channels/set-up-a-chatgpt-feed-for-openai-ads.md#create-campaign-and-a-d-groups-in-openai).
{% endstep %}
{% endstepper %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://helpcenter.channable.com/manage-improve-product-data/rules-bulk-edit-and-enrich/using-rules/rule-templates/send-custom-labels-to-openai.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
