All Collections
Generative AI model API keys
Generative AI model API keys
Debby Shepard avatar
Written by Debby Shepard
Updated over a week ago

To enable Glean Generative AI features, you need to select a generative AI model and setup a key. We recommend using Glean's Azure OpenAI key. We also support using your own Azure OpenAI or “vanilla” OpenAI key.

Both Glean's Azure OpenAI Key and the "vanilla" OpenAI key can be setup in Workspace Settings. To use your own Azure OpenAI, please work with your Glean sales or technical services person.

Please note: to use your own key, you'll need GPT-4 access. Find more details on requesting GPT-4 access here.

Glean’s Azure Open AI key (recommended)

Glean has a signed agreement with Azure Open AI promising:

  • 0-day retention: Your data will not be stored by Azure.

  • Data will not be used to train any custom large language models.

  • Data encryption: All data is encrypted in transit.

  • Compliance: Azure is compliant with a variety of industry standards. See details here

The advantages of this approach are

  • Guaranteed capacity: Scale to all your users

  • Performance: Low latency

  • Access to all the necessary models out of the box.

  • 0-day retention isn’t default on Azure Open AI.

Your own key: Azure OpenAI or OpenAI

We also support your own provisioned OpenAI or Azure OpenAI key.

You should ensure your key has sufficient:

  • Capacity: Assuming 2 calls to GPT-4 per query, we ask that you ensure your key has the right TPM (tokens per minute) and RPM (requests per minute) to support this.

  • Access: We require access to GPT-4, GPT4-32k and GPT-3.5-turbo models.

You will able to set your "vanilla" OpenAI in the Glean Assistant settings. Please work with Glean sales or customer success to configure your Azure OpenAI key

If I want to use my own key, but don’t have GPT-4 access currently, how do I get access?

GPT-4 access is required on OpenAI or Azure OpenAI

We recommend OpenAI on Azure. To get access, you will first need to fill out the following Azure OpenAI Service form. Once that has been approved, you will need to request access to GPT-4 public preview here.

If you choose to use OpenAI, you need to apply for the OpenAI GPT-4 waitlist.

After that has been completed, please reference the RPM and TPM requirements for your company size and submit a request to increase the quotas to the appropriate levels.

We currently do not have estimates on how long you will be on the waitlist to get access via either OpenAI directly or on Azure.

Did this answer your question?