> For the complete documentation index, see [llms.txt](https://help.openloyalty.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.openloyalty.io/implementation-guide/integrations-and-data-exchange/imports-exports/imports/sample-import-files/collections.md).
# Collections
How to import collections into Open Loyalty using CSV files for use in other modules.
Collections are groups of values (such as product SKUs, store IDs, or category names) that can be referenced in other modules. Use the collection import to load these values in bulk rather than entering them manually.
**File format:** CSV
### Sample file
{% file src="/files/lFmnSklhePMGJF3i4Dvu" %}
{% code title="collections-import-sample.csv" %}
```csv
value
SKU-001
SKU-002
SKU-003
SKU-004
SKU-005
```
{% endcode %}
### Format rules
* The file **must** include the header row `value`
* Each subsequent row contains one collection value
* The collection must contain **at least three records**
* No extra columns — only `value` is supported
* Save as `.csv` with UTF-8 encoding
{% hint style="warning" %}
**Minimum three records required.** Collections must contain at least three values. Files with fewer records will not be accepted.
{% endhint %}
{% hint style="info" %}
**Collections are used in other modules, e.g. campaign conditions or custom fields.** Once imported, you can reference the collection in campaign expressions — for example, to award points only for purchases of products whose SKU is in a specific collection.
{% endhint %}
### Common mistakes
Mistake
Fix
Fewer than three values
The minimum is three records
Missing description column
Both value and description columns are required, even if there is no description.
Missing header row
The value,description header is required
To find out more, please refer to the article below:
{% content-ref url="/pages/tEXVuJgauZZ0TVDNSUHc" %}
[Collections](/implementation-guide/integrations-and-data-exchange/collections.md)
{% endcontent-ref %}
---
# 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 following URL with the `ask` and `goal` query parameters:
```
GET https://help.openloyalty.io/implementation-guide/integrations-and-data-exchange/imports-exports/imports/sample-import-files/collections.md?ask=&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 `build a script that syncs our docs to a CMS` 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.