gitlab-ce/doc/administration/gitlab_duo_self_hosted/configure_duo_features.md

stage	group	description	info	title
AI-Powered	Custom Models	Configure your GitLab instance to use GitLab Duo Self-Hosted.	To determine the technical writer assigned to the Stage/Group associated with this page, see https://handbook.gitlab.com/handbook/product/ux/technical-writing/#assignments	Configure GitLab to access GitLab Duo Self-Hosted

DETAILS: Tier: Ultimate with GitLab Duo Enterprise - Start a trial Offering: GitLab Self-Managed Status: Beta

• Introduced in GitLab 17.1 with a flag named ai_custom_model. Disabled by default.
• Enabled on GitLab Self-Managed in GitLab 17.6.
• Changed to require GitLab Duo add-on in GitLab 17.6 and later.
• Feature flag ai_custom_model removed in GitLab 17.8
• Ability to set AI gateway URL using UI added in GitLab 17.9.

Prerequisites:

• Upgrade GitLab to version 17.9 or later.

To configure your GitLab instance to access the available self-hosted models in your infrastructure:

1. Confirm that a fully self-hosted configuration is appropriate for your use case.
2. Configure your GitLab instance to access the AI gateway.
3. Configure the self-hosted model.
4. Configure the GitLab Duo features to use your self-hosted model.

Configure your GitLab instance to access the AI gateway

1. On the left sidebar, at the bottom, select Admin.
2. Select GitLab Duo.
3. In the GitLab Duo section, select Change configuration.
4. Under Local AI Gateway URL, enter your AI Gateway URL.
5. Select Save changes.

Configure the self-hosted model

Prerequisites:

• You must be an administrator.
• You must have an Ultimate license.
• You must have a Duo Enterprise license add-on.

To configure a self-hosted model:

1. On the left sidebar, at the bottom, select Admin.

2. Select Self-hosted models.

   • If the Self-hosted models menu item is not available, synchronize your subscription after purchase:
     1. On the left sidebar, select Subscription.
     2. In Subscription details, to the right of Last sync, select synchronize subscription ({retry}).

3. Select Add self-hosted model.

4. Complete the fields:

   • Deployment name: Enter a name to uniquely identify the model deployment, for example, Mixtral-8x7B-it-v0.1 on GCP.
   • Model family: Select the model family the deployment belongs to. Only GitLab-approved models are in this list.
   • Endpoint: Enter the URL where the model is hosted.
     • For models hosted through vLLM, you must suffix the URL with /v1. The default port is 8000, so the default endpoint URL is https://<hostname>:8000/v1.
   • API key: Optional. Add an API key if you need one to access the model.
   • Model identifier: This is a required field if your deployment method is vLLM, Bedrock or Azure. The value of this field is based on your deployment method, and should match the following structure:

     Deployment method	Format	Example
     vLLM	custom_openai/<name of the model served through vLLM>	custom_openai/Mixtral-8x7B-Instruct-v0.1
     Bedrock	bedrock/<model ID of the model>	bedrock/mistral.mixtral-8x7b-instruct-v0:1
     Azure OpenAI	azure/<model ID of the model>	azure/gpt-35-turbo
     Others	The field is optional

5. Select Create self-hosted model.

Configure self-hosted beta models

Prerequisites:

• You must be an administrator.
• You must have an Ultimate license.
• You must have a Duo Enterprise license add-on.

To enable self-hosted beta models:

1. On the left sidebar, at the bottom, select Admin.
2. Select GitLab Duo.
3. In the GitLab Duo section, select Change configuration.
4. Under Self-hosted AI models, select Use beta self-hosted models features.
5. Select Save changes.

NOTE: Turning on beta self-hosted models features also accepts the GitLab Testing Agreement.

For more information, see the list of available beta models under evaluation.

Configure GitLab Duo features to use self-hosted models

Prerequisites:

• You must be an administrator.
• You must have an Ultimate license.
• You must have a Duo Enterprise license add-on.

View configured features

1. On the left sidebar, at the bottom, select Admin.
2. Select Self-hosted models.
   • If the Self-hosted models menu item is not available, synchronize your subscription after purchase:
     1. On the left sidebar, select Subscription.
     2. In Subscription details, to the right of Last sync, select synchronize subscription ({retry}).
3. Select the AI-powered features tab.

Configure the feature to use a self-hosted model

Configure the GitLab Duo feature to send queries to the configured self-hosted model:

1. On the left sidebar, at the bottom, select Admin.
2. Select Self-hosted models.
3. Select the AI-powered features tab.
4. For the feature you want to configure, from the dropdown list, choose the self-hosted model you want to use. For example, Mistral.