**As** an OpenProject admin
**I want to** be able to connect OpenProject to a LLM
**so that** I can use the LLM for a multitude of new features

**Acceptance criteria**

* In the admin settings "Artificial Intelligence (AI)" a new menu entry called "LLM settings" is available.

* The "LLM settings" view contains 

* Displayed information: "The LLM server needs to support OpenAI-API compatible endpoints."

* Boolean: "Enabled" (deactivates the LLM server settings and all LLM related AI features)

* URL Input: "Base URL" (placeholder: [`https://example.com/v1/`](https://example.com/v1/)

* Question: Host Url or host?

* Text Input: "API key"

* Only visible when setting the API key

* Later on edit the saved API key should be shown masked

* Begin of the insertion"Connect"-ButtonEnd of the insertion Begin of the deletion "Save"-ButtonEnd of the deletion

* When clicked a request to fetch the installed models of the LLM are set

* `GET` [`https://example.com/v1/models`](https://example.com/v1/models)

* On error, the settings are not saved and following possible errors are shown inline

* "SSL error": an inline error is shown underneath the "Base URL" input

* "Host could not be reached": an inline error is shown underneath the "Base URL" input

* "Invalid API key": an inline error is shown underneath the "API key" input

* Other (unexpected) errors are shown as toast message.

* Info: This list is not complete yet

* On success

* Settings are saved


<br>

* Begin of the insertionLLM Models panelEnd of the insertion Begin of the deletion SidebarEnd of the deletion

* The Begin of the insertionpanelEnd of the insertion Begin of the deletion sidebarEnd of the deletion is only shown when the LLM was successfully setup already

* Begin of the insertionBelow the panel isEnd of the insertion Begin of the deletion The sidebar containsEnd of the deletion a &quot;Test connection&quot;-button

* When the user clicks the button, two request are made

* List models

* `GET` [`https://example.com/v1/models`](https://example.com/v1/models)

* A chat completion test

* `POST` [`https://example.com/v1/chat/completions`](https://example.com/v1/chat/completions)

* `{ "model": "FIRST_MODEL_IN_LIST", "messages": [ {"role": "system", "content": "You are a helpful assistant that answeres with one word."}, {"role": "user", "content": "Hi."} ] }`

* If the requests were successful, a success message is shown underneath the button

* &quot;Connection to LLM was successful. Following models are available: &quot;

* If an error occurred the error is shown underneath the button Begin of the insertion

End of the insertion Begin of the deletion


<br>


<br>

End of the deletion * Begin of the insertionA &quot;Disconnect&quot; button

* Shows a danger dialog

* Removes the connection and initialises the form to a state where an LLM service is not enabled

* End of the insertion When LLM settings checkbox is disabled the form underneath and the Begin of the insertionLLM panelEnd of the insertion Begin of the deletion sidebarEnd of the deletion are hidden.


**Technical notes**

* <br>


**Permissions and visibility considerations**

* Only administrators should be able to see or edit the AI settings page


**Translation considerations**

* _Key terms and phrases in the key languages_


**Out of scope**

* Enable AI features per project

* Enable AI features for specific users

* Usage counter and budget limits