root
/
gitlab-ce
mirror of https://gitlab.com/free-releases/gitlab-ce.git
1
0
Fork 0
Code Issues Actions Packages Projects Releases Wiki Activity
gitlab-ce/doc/user/ai_features.md

17 KiB
Raw Blame History

stage group description info
AI-powered AI Model Validation AI-powered features and functionality. 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

GitLab Duo

GitLab Duo is a set of AI-assisted features across the GitLab DevSecOps platform. These features aim to help increase velocity and solve key pain points across the software development lifecycle. GitLab Duo features are accessible through the IDE extension and the GitLab UI. Some of the features are also accessible through GitLab Duo Chat, which is available in both interfaces.

Some features are still in development. View features in the Experiment phase.

Learn more about how to turn GitLab Duo features on and off.

GitLab is transparent. As GitLab Duo features mature, the documentation will be updated to clearly state how and where you can access these capabilities.

Goal Feature Tier/Offering/Status
Helps you write code more efficiently by showing code suggestions as you type.

Watch overview		 Code Suggestions Tier: Premium and Ultimate with GitLab Duo Pro
Offering: GitLab.com, Self-managed, GitLab Dedicated
Status: Generally Available
Processes and generates text and code in a conversational manner. Helps you quickly identify useful information in large volumes of text in issues, epics, code, and GitLab documentation. Chat Tier: Freely available for Premium and Ultimate for a limited time
Offering: GitLab.com, Self-managed, GitLab Dedicated
Status: Generally Available
Helps you discover or recall Git commands when and where you need them. Git suggestions Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment
Assists with quickly getting everyone up to speed on lengthy conversations to help ensure you are all on the same page.

Watch overview		 Discussion summary Tier: Freely available for Ultimate for a limited time
In the future, will require GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment
Generates issue descriptions. Issue description generation Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment
Automates repetitive tasks and helps catch bugs early.

Watch overview		 Test generation Tier: Freely available for Premium and Ultimate for a limited time
In the future, will require Premium or Ultimate with GitLab Duo Pro
Offering: GitLab.com, Self-managed, GitLab Dedicated
Status: Beta
Generates a description for the merge request based on the contents of the template. Merge request template population Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment
Assists in creating faster and higher-quality reviews by automatically suggesting reviewers for your merge request.

Watch overview		 Suggested Reviewers Tier: Ultimate
Offering: GitLab.com
Status: Generally Available
Efficiently communicates the impact of your merge request changes. Merge request summary Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Beta
Helps ease merge request handoff between authors and reviewers and help reviewers efficiently understand suggestions. Code review summary Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment
Helps you remediate vulnerabilities more efficiently, boost your skills, and write more secure code.

Watch overview		 Vulnerability explanation Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Beta
Generates a merge request containing the changes required to mitigate a vulnerability. Vulnerability resolution Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment
Helps you understand code by explaining it in English language.

Watch overview		 Code explanation Tier: Freely available for Premium and Ultimate for a limited time
In the future, will require Premium or Ultimate with GitLab Duo Pro
Offering: GitLab.com
Status: Experiment
Assists you in determining the root cause for a pipeline failure and failed CI/CD build. Root cause analysis Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment
Assists you with predicting productivity metrics and identifying anomalies across your software development lifecycle. Value stream forecasting Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com, Self-managed, GitLab Dedicated
Status: Experiment
Processes and responds to your questions about your application's usage data. Product Analytics Tier: Freely available for Ultimate for a limited time
In the future, will require Ultimate with GitLab Duo Enterprise
Offering: GitLab.com
Status: Experiment

Disable GitLab Duo features for specific groups or projects or an entire instance

Disable GitLab Duo features by following these instructions.

Language models

Feature Large Language Model
Git suggestions Vertex AI Codey codechat-bison
Discussion summary Anthropic Claude-2.1
Issue description generation Anthropic Claude-2.1
Code Suggestions For Code Completion: Vertex AI Codey code-gecko For Code Generation: Anthropic Claude-3-Sonnet
Test generation Anthropic Claude-2.1
Merge request template population Vertex AI Codey text-bison
Suggested Reviewers GitLab creates a machine learning model for each project, which is used to generate reviewers View the issue
Merge request summary Vertex AI Codey text-bison
Code review summary Vertex AI Codey text-bison
Vulnerability explanation Vertex AI Codey text-bison Anthropic Claude-2.1 if degraded performance
Vulnerability resolution Vertex AI Codey code-bison
Code explanation Vertex AI Codey codechat-bison
GitLab Duo Chat Anthropic Claude-2.1 Vertex AI Codey textembedding-gecko
Root cause analysis Vertex AI Codey text-bison
Value stream forecasting Statistical forecasting
Product analytics Vertex AI Codey codechat-bison

Data usage

GitLab AI features leverage generative AI to help increase velocity and aim to help make you more productive. Each feature operates independently of other features and is not required for other features to function. GitLab selects the best-in-class large-language models for specific tasks. We use Google Vertex AI Models and Anthropic Claude.

Progressive enhancement

These features are designed as a progressive enhancement to existing GitLab features across our DevSecOps platform. They are designed to fail gracefully and should not prevent the core functionality of the underlying feature. You should note each feature is subject to its expected functionality as defined by the relevant feature support policy.

Stability and performance

These features are in a variety of feature support levels. Due to the nature of these features, there may be high demand for usage which may cause degraded performance or unexpected downtime of the feature. We have built these features to gracefully degrade and have controls in place to allow us to mitigate abuse or misuse. GitLab may disable beta and experimental features for any or all customers at any time at our discretion.

Data privacy

GitLab Duo AI features are powered by a generative AI models. The processing of any personal data is in accordance with our Privacy Statement. You may also visit the Sub-Processors page to see the list of our Sub-Processors that we use to provide these features.

Data retention

The below reflects the current retention periods of GitLab AI model Sub-Processors:

  • Anthropic discards model input and output data immediately after the output is provided. Anthropic currently does not store data for abuse monitoring. Model input and output is not used to train models.
  • Google discards model input and output data immediately after the output is provided. Google currently does not store data for abuse monitoring. Model input and output is not used to train models.

All of these AI providers are under data protection agreements with GitLab that prohibit the use of Customer Content for their own purposes, except to perform their independent legal obligations.

GitLab retains input and output for up to 30 days for the purpose of troubleshooting, debugging, and addressing latency issues.

Training data

GitLab does not train generative AI models based on private (non-public) data. The vendors we work with also do not train models based on private data.

For more information on our AI sub-processors, see:

Telemetry

GitLab Duo collects aggregated or de-identified first-party usage data through our Snowplow collector. This usage data includes the following metrics:

  • Number of unique users
  • Number of unique instances
  • Prompt lengths
  • Model used
  • Status code responses
  • API responses times

Model accuracy and quality

Generative AI may produce unexpected results that may be:

  • Low-quality
  • Incoherent
  • Incomplete
  • Produce failed pipelines
  • Insecure code
  • Offensive or insensitive
  • Out of date information

GitLab is actively iterating on all our AI-assisted capabilities to improve the quality of the generated content. We improve the quality through prompt engineering, evaluating new AI/ML models to power these features, and through novel heuristics built into these features directly.