# Configuring Generative AI Access

The ADF admin can get into the configuration screen by clicking on the upper-right setting menu,

<figure><img src="/files/7RKZmtil8PLLXYwbNy1U" alt=""><figcaption></figcaption></figure>

Selecting the top tab *ingest Configuration* to get into the general ADF settings. Scrolling down the settings page further will display Generative AI settings in two separate locations:  Azure AI deployment and OpenAI deployment.  &#x20;

<figure><img src="/files/UAcd0cqNXT4JpHqvcJSn" alt=""><figcaption><p>Azure AI Related Configuration</p></figcaption></figure>

<figure><img src="/files/qDKHsIrU42hqQpXiGfe0" alt=""><figcaption><p>OpenAI Related Confiugration</p></figcaption></figure>

The ADF platform supports major GenAI vendors, specifically Azure AI or OpenAI backends. The admin user first needs to specify and fill the *OPENAI\_VENDOR* blank with the vendor name: azure or openai. Depending on the vendor configuration, the admin then needs to complete the detailed access information. &#x20;

For Azure deployment, the configuration blanks that need to be filled are:

* *AZURE\_OPENAI\_DEPLOYMENT\_NAME*
* *AZURE\_OPENAI\_ENDPOINT*
* *AZURE\_OPENAI\_KEY*
* *OPEN\_AI\_MODEL*

For OpenAI deployment, the configuration blanks that need to be filled are:

* *OPENAI\_KEY*
* *ASURE\_OPENAI\_ENDPOINT*
* *OPEN\_AI\_MODEL*

Notice that as of August 2024, the ADF Azure deployment supports models:

* gpt-4
* gpt-4o
* gpt-4o-mini
* gpt-3.5-turbo


---

# 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.apica.io/autonomous-insights/log-explained-using-generative-ai/configuring-generative-ai-access.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.