Skip to content

GitLab Duo Self-Hosted

  • Tier: Premium, Ultimate
  • Add-on: GitLab Duo Enterprise
  • Offering: GitLab Self-Managed

Version history

  • 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.
  • Generally available in GitLab 17.9.
  • Changed to include Premium in GitLab 18.0.

To maintain full control over your data privacy, security, and the deployment of large language models (LLMs) in your own infrastructure, use GitLab Duo Self-Hosted.

By deploying GitLab Duo Self-Hosted, you can manage the entire lifecycle of requests made to LLM backends for GitLab Duo features, ensuring that all requests stay in your enterprise network, and avoiding external dependencies.

For a click-through demo, see GitLab Duo Self-Hosted product tour.

For an overview, see GitLab Duo Self-Hosted: AI in your private environment.

Why use GitLab Duo Self-Hosted

With GitLab Duo Self-Hosted, you can:

  • Choose any GitLab-supported LLM, or bring your own compatible model.
  • Retain full control over data by keeping all request/response logs in your domain, ensuring complete privacy and security with no external API calls.
  • Isolate the GitLab instance, AI gateway, and models in your own environment.
  • Select specific GitLab Duo features tailored to your users.
  • Eliminate reliance on the shared GitLab AI gateway.

This setup ensures enterprise-level privacy and flexibility, allowing seamless integration of your LLMs with GitLab Duo features.

Supported GitLab Duo features

The following tables state:

  • The GitLab Duo features and whether those features are available on GitLab Duo Self-Hosted.
  • Which version of GitLab is needed to use those features on GitLab Duo Self-Hosted.
  • The status of those features. A feature's status on GitLab Duo Self-Hosted can be different to that same feature's status when it is hosted on GitLab.

To use these features with GitLab Duo Self-Hosted, you must have the Duo Enterprise add-on. This applies regardless of whether you can use these features with Duo Core or Duo Pro when GitLab hosts the models and connects to those models through the cloud-based AI gateway.

Code Suggestions

Feature Available on GitLab Duo Self-Hosted GitLab version Status
Code Suggestions {check-circle-filled} Yes GitLab 17.9 and later Generally available

Chat

Feature Available on GitLab Duo Self-Hosted GitLab version Status
General {check-circle-filled} Yes GitLab 17.9 and later Generally available
Code Explanation {check-circle-filled} Yes GitLab 17.9 and later Generally available
Test Generation {check-circle-filled} Yes GitLab 17.9 and later Generally available
Refactor Code {check-circle-filled} Yes GitLab 17.9 and later Generally available
Fix Code {check-circle-filled} Yes GitLab 17.9 and later Generally available
Root Cause Analysis {check-circle-filled} Yes GitLab 17.10 and later Beta
Vulnerability Explanation {check-circle-filled} Yes GitLab 18.1.2 and later Beta

For more examples of a question you can ask, see Ask about GitLab.

GitLab Duo in merge requests

Feature Available on GitLab Duo Self-Hosted GitLab version Status
Merge Commit Message Generation {check-circle-filled} Yes GitLab 18.1.2 and later Beta
Merge Request Summary {check-circle-filled} Yes GitLab 18.1.2 and later Beta
Code Review {check-circle-filled} Yes GitLab 18.3 and later Beta
Code Review Summary {check-circle-filled} Yes GitLab 18.1.2 and later Experiment

GitLab Duo in issues

Feature Available on GitLab Duo Self-Hosted GitLab version Status
Issue Description Generation {dash-circle} No Not applicable Not applicable
Discussion Summary {check-circle-filled} Yes GitLab 18.1.2 and later Beta

Other features

Feature Available on GitLab Duo Self-Hosted GitLab version Status
GitLab Duo for the CLI {check-circle-filled} Yes GitLab 18.1.2 and later Beta
GitLab Duo Agent Platform {dash-circle} No Not applicable Not applicable
Vulnerability Resolution {check-circle-filled} Yes GitLab 18.1.2 and later Beta
AI Impact Dashboard {check-circle-filled} Yes GitLab 17.9 and later Beta

Prerequisites

Before setting up the GitLab Duo Self-Hosted infrastructure, you must have:

Decide on your configuration type

GitLab Self-Managed customers can implement AI-native features using any of the following options:

Feature Self-hosted AI gateway Hybrid AI gateway and model configuration GitLab.com AI gateway
Infrastructure requirements Requires hosting your own AI gateway and models Requires hosting your own AI gateway and models No additional infrastructure needed
Model options Choose from supported self-hosted models Choose from supported self-hosted models or GitLab AI vendor models for each GitLab Duo feature Uses the default GitLab AI vendor models
Network requirements Can operate in fully isolated networks Requires internet connectivity for GitLab Duo features that use GitLab AI vendor models Requires internet connectivity
Responsibilities You set up your infrastructure, and do your own maintenance You set up your infrastructure, do your own maintenance, and choose which features use GitLab AI vendor models and AI gateway GitLab does the set up and maintenance

Self-hosted AI gateway and LLMs

In a fully self-hosted configuration, you deploy your own AI gateway and use only supported LLMs in your infrastructure, without using GitLab infrastructure or AI vendor models. This gives you full control over your data and security.

This configuration only includes models configured through your self-hosted AI gateway. If you use GitLab AI vendor models for any features, those features will connect to the GitLab-hosted AI gateway instead of your self-hosted gateway, making it a hybrid configuration rather than fully self-hosted.

While you deploy your own AI gateway, you can still use cloud-based LLM services like AWS Bedrock or Azure OpenAI as your model backend and they will continue to connect through your self-hosted AI gateway.

If you have an offline environment with physical barriers or security policies that prevent or limit internet access, and comprehensive LLM controls, you should use this fully self-hosted configuration.

For licensing, you must have a GitLab Premium or Ultimate subscription, and GitLab Duo Enterprise. Offline Enterprise licenses are available for those customers with fully isolated offline environments. To get access to your purchased subscription, request a license through the Customers Portal.

For more information, see:

Hybrid AI gateway and model configuration

  • Status: Beta

Version history

The availability of this feature is controlled by a feature flag. For more information, see the history.

In this hybrid configuration, you deploy your own AI gateway and self-hosted models for most features, but configure specific features to use GitLab AI vendor models. When a feature is configured to use a GitLab AI vendor model, requests for that feature are sent to the GitLab-hosted AI gateway instead of your self-hosted AI gateway.

This option provides flexibility by allowing you to:

  • Use your own self-hosted models for features where you want full control.
  • Use GitLab-managed vendor models for specific features where you prefer the models GitLab has curated.

When features are configured to use GitLab AI vendor models:

  • All calls to those features use the GitLab-hosted AI gateway, not the self-hosted AI gateway.
  • Internet connectivity is required for these features.
  • This is not a fully self-hosted or isolated configuration.

For licensing, you must have a GitLab Premium or Ultimate subscription, and GitLab Duo Enterprise. Offline licenses are not supported to use this configuration. To get access to your purchased subscription, request a license through the Customers Portal.

For more information, see:

GitLab.com AI gateway with default GitLab external vendor LLMs

If you do not meet the use case criteria for GitLab Duo Self-Hosted, you can use the GitLab.com AI gateway with default GitLab external vendor LLMs.

The GitLab.com AI gateway is the default Enterprise offering and is not self-hosted. In this configuration, you connect your instance to the GitLab-hosted AI gateway, which integrates with external vendor LLM providers, including:

These LLMs communicate through the GitLab Cloud Connector, offering a ready-to-use AI solution without the need for on-premise infrastructure.

For licensing, you must have a GitLab Premium or Ultimate subscription, and GitLab Duo Enterprise. To get access to your purchased subscription, request a license through the Customers Portal

For more information, see the GitLab.com AI gateway configuration diagram.

To set up this infrastructure, see how to configure GitLab Duo on a GitLab Self-Managed instance.

Set up a GitLab Duo Self-Hosted infrastructure

To set up a fully isolated GitLab Duo Self-Hosted infrastructure:

  1. Install a Large Language Model (LLM) Serving Infrastructure

    • We support various platforms for serving and hosting your LLMs, such as vLLM, AWS Bedrock, and Azure OpenAI. To help you choose the most suitable option for effectively deploying your models, see the supported LLM platforms documentation for more information on each platform's features.

    • We provide a comprehensive matrix of supported models along with their specific features and hardware requirements. To help select models that best align with your infrastructure needs for optimal performance, see the supported models and hardware requirements documentation.

  2. Install the GitLab AI gateway Install the AI gateway to efficiently configure your AI infrastructure.

  3. Configure GitLab Duo features See the Configure GitLab Duo features documentation for instructions on how to customize your environment to effectively meet your operational needs.

  4. Enable logging You can find configuration details for enabling logging in your environment. For help in using logs to track and manage your system's performance effectively, see the logging documentation.

Related topics