> For the complete documentation index, see [llms.txt](https://docs.ngsurvey.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ngsurvey.com/fr/installation-setup/system-settings/third-party-apis/microsoft.md).

# Microsoft

ngSurvey utilise Microsoft Cognitive Services pour analyser les sentiments des répondants et Microsoft Translator pour traduire automatiquement les textes.

{% hint style="info" %}
Pour de meilleurs résultats de traduction et d'analyse des sentiments, nous recommandons d'utiliser [AI suite edition](/fr/suite-ia.md).
{% endhint %}

## Microsoft Cognitive Services

Pour configurer Microsoft Cognitive Services, vous pouvez vous rendre sur votre [Azure portal](https://portal.azure.com/) et créer une nouvelle ressource cognitive dans votre compte.

  

![](https://186103257-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M8fLhS0bmfBRyq0HdUm%2F-MCB5ZEbGQHgLWILXmrH%2F-MCB6p9prk29sb3kicmc%2Fimage.png?alt=media\&token=d243cbda-4eaa-4e8c-9d9e-9e94d338b234)

La ressource cognitive doit être de type Text analytics

![](https://186103257-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M8fLhS0bmfBRyq0HdUm%2F-MeeyfR9H-bLG9cessQn%2F-MeeypX7pBBEt_ze8_x6%2Fimage.png?alt=media\&token=28a5cf3d-6fc3-4a83-98c9-49f4a38f401a)

Une fois la ressource créée, vous pouvez copier la key 1 et l'endpoint.

![](https://186103257-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M8fLhS0bmfBRyq0HdUm%2F-MCB5ZEbGQHgLWILXmrH%2F-MCB6YSu4kERG8CXqgE0%2Fimage.png?alt=media\&token=68fe05ff-a6d4-4f68-9396-1b12197e5d3b)

et dans vos paramètres ngSurvey, collez la key 1 et définissez votre URL d'endpoint en lui ajoutant la route suivante en suffixe ***text/analytics/v3.0/sentiment***

![](https://186103257-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M8fLhS0bmfBRyq0HdUm%2F-MeeyfR9H-bLG9cessQn%2F-Meez9MNZep_9WJWs8Mq%2Fimage.png?alt=media\&token=d16a2d45-f17a-495d-a8b3-2053c90ba02a)

## Microsoft Translator

Pour configurer Microsoft Translator, vous pouvez vous rendre sur votre [Azure portal](https://portal.azure.com/) et créer une nouvelle ressource dans votre compte.

![](https://186103257-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M8fLhS0bmfBRyq0HdUm%2F-MCB5ZEbGQHgLWILXmrH%2F-MCB8VDM5i3sEK2kWrRR%2Fimage.png?alt=media\&token=dee3dd43-8ab9-42d4-8926-679020b4ccac)

Une fois le service Translator créé, vous pouvez copier sa key 1

![](https://186103257-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M8fLhS0bmfBRyq0HdUm%2F-MCB5ZEbGQHgLWILXmrH%2F-MCB9WTeDRp2Y2a2eRvO%2Fimage.png?alt=media\&token=f3275b97-0136-4e6a-b673-ecc8cd23789c)

et la coller dans la page des paramètres de ngSurvey.

![](https://186103257-files.gitbook.io/~/files/v0/b/gitbook-legacy-files/o/assets%2F-M8fLhS0bmfBRyq0HdUm%2F-MCB5ZEbGQHgLWILXmrH%2F-MCB9dYVyFZp1LGx5EQD%2Fimage.png?alt=media\&token=f653acfb-88c5-452e-afc5-6cecebf0da04)


---

# 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://docs.ngsurvey.com/fr/installation-setup/system-settings/third-party-apis/microsoft.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.