# Automatic retrieval

The goal of this programmed task is to be able to create and initiate retrieval tasks automatically, without having to access the control web interface, to create the associated retrieval job.

Automatic retrieval has a directory as the starting point. The directory path is configured initially during the installation process, and later on the systems administrator will be able to change the path.

The basic operation of the automatic retrieval consists of the creation of a folder, naming it with a specific syntax.

There are two ways of indicating the object we want to retrieve:

* **By its** **LUOI:**

\[*LUOI*].LUOI.\[*request suffix*]  (i.e.: 45.3.LUOI.Request)

* **By object name:**

\[*name of the object*].Identifier.\[*request suffix*] (i.e.: BBL\_003.Identifier.Request)

{% hint style="info" %}
**Note**: in order to use the retrieval by object name method, the object name must be a metadata and it must be configured as a versioning collision group.
{% endhint %}

Where:                                       

* LUOI: identifier for the object identifier search in **LIBSAFE**
* Identifier: identifier for the object name search
* Request suffix: it is a suffix that can be configured by the systems administrator. The automatic retrieval process will recognize it to identify a retrieval request.

To create an automatic retrieval job:

* Access the automatic retrieval base directory that has been configured.
* Create a folder, renaming it as previously explained.
* The retrieval job will start automatically.

{% hint style="info" %}
**Note**: both the base directory path and the request suffix can be configurable. It is the systems administrator responsibility to manage said variables. Contact him/her if you need information about that, or contact the LIBNOVA consultants, who may also be able to advise you.
{% endhint %}

If any automatic retrieval job would end in error, the process will rename the folder with the “error” suffix. To know more about the state of the jobs, please consult the logs.


---

# 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.libnova.com/libsafe-advanced-preservation-administrator-manual/annexes/automatic-ingestion-and-retrieval-processes/automatic-retrieval.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.