Skip to content

AI features based on 3rd-party integrations

Introduced in GitLab 15.11.

Features

  • Async execution of the long running API requests
    • GraphQL Action starts the request
    • Background workers execute
    • GraphQL subscriptions deliver results back in real time
  • Abstraction for
    • Google Vertex AI
    • Anthropic
  • Rate Limiting
  • Circuit Breaker
  • Multi-Level feature flags
  • License checks on group level
  • Snowplow execution tracking
  • Tracking of Token Spent on Prometheus
  • Configuration for Moderation check of inputs
  • Automatic Markdown Rendering of responses
  • Centralised Group Level settings for experiment and 3rd party
  • Experimental API endpoints for exploration of AI APIs by GitLab team members without the need for credentials
    • Google Vertex AI
    • Anthropic

Feature flags

Apply the following two feature flags to any AI feature work:

  • A general flag (ai_global_switch) that applies to all AI features.
  • A flag specific to that feature. The feature flag name must be different than the licensed feature name.

See the feature flag tracker for the list of all feature flags and how to use them.

Implement a new AI action

To implement a new AI action, connect to the preferred AI provider. You can connect to this API using either the:

  • Experimental REST API.
  • Abstraction layer.

All AI features are experimental.

Test AI features locally

NOTE: Use this snippet for help automating the following section.

  1. Enable the required general feature flags:

    Feature.enable(:ai_global_switch, type: :ops)

  2. Ensure you have followed the process to obtain an EE license for your local instance

  3. Simulate the GDK to simulate SaaS and ensure the group you want to test has an Ultimate license

  4. Enable Experimental features:

    1. Go to the group with the Ultimate license
    2. Group Settings > General -> Permissions and group features
    3. Enable Experiment features

  5. Enable the specific feature flag for the feature you want to test

  6. Set the required access token. To receive an access token:

    1. For Vertex, follow the instructions below.
    2. For all other providers, like Anthropic, create an access request where @m_gill, @wayne, and @timzallmann are the tech stack owners.

Set up the embedding database

NOTE: Use this snippet for help automating the following section.

For features that use the embedding database, additional setup is needed.

  1. Enable pgvector in GDK

  2. Enable the embedding database in GDK

      gdk config set gitlab.rails.databases.embedding.enabled true

  3. Run gdk reconfigure

  4. Run database migrations to create the embedding database

Setup for GitLab documentation chat (legacy chat)

To populate the embedding database for GitLab chat:

  1. Open a rails console
  2. Run this script to populate the embedding database

Configure GCP Vertex access

In order to obtain a GCP service key for local development, please follow the steps below:

  • Create a sandbox GCP project by visiting this page and following the instructions, or by requesting access to our existing group GCP project by using this template.
  • If you are using an individual GCP project, you may also need to enable the Vertex AI API:
    1. Go to APIs & Services > Enabled APIs & services.
    2. Select + Enable APIs and Services.
    3. Search for Vertex AI API.
    4. Select Vertex AI API, then select Enable.
  • Install the gcloud CLI
  • Authenticate locally with GCP using the gcloud auth application-default login command.
  • Open the Rails console. Update the settings to:
# PROJECT_ID = "your-gcp-project-name"

Gitlab::CurrentSettings.update(vertex_ai_project: PROJECT_ID)

Configure Anthropic access

Gitlab::CurrentSettings.update!(anthropic_api_key: <insert API key>)

Populating embeddings and using embeddings fixture

Embeddings are generated through VertexAI text embeddings endpoint. The sections below explain how to populate embeddings in the DB or extract embeddings to be used in specs.

VertexAI embeddings

To seed your development database with the embeddings for GitLab Documentation, you may use the pre-generated embeddings and a Rake task.

RAILS_ENV=development bundle exec rake gitlab:llm:embeddings:vertex:seed

The DBCleaner gem we use clear the database tables before each test runs. Instead of fully populating the table vertex_gitlab_docs where we store VertexAI embeddings for the documentations, we can add a few selected embeddings to the table from a pre-generated fixture.

For instance, to test that the question "How can I reset my password" is correctly retrieving the relevant embeddings and answered, we can extract the top N closet embeddings to the question into a fixture and only restore a small number of embeddings quickly. To faciliate an extraction process, a Rake task been written. You can add or remove the questions needed to be tested in the Rake task and run the task to generate a new fixture.

RAILS_ENV=development bundle exec rake gitlab:llm:embeddings:vertex:extract_embeddings

Using embeddings in specs

In the specs where you need to use the embeddings, use the RSpec config hook :ai_embedding_fixtures on a context.

context 'when asking about how to use GitLab', :ai_embedding_fixtures do
  # ...examples
end

Tips for local development

  1. When responses are taking too long to appear in the user interface, consider restarting Sidekiq by running gdk restart rails-background-jobs. If that doesn't work, try gdk kill and then gdk start.
  2. Alternatively, bypass Sidekiq entirely and run the chat service synchronously. This can help with debugging errors as GraphQL errors are now available in the network inspector instead of the Sidekiq logs. To do that temporary alter Llm::CompletionWorker.perform_async statements with Llm::CompletionWorker.perform_inline

Working with GitLab Duo Chat

View guidelines for working with GitLab Duo Chat.

Experimental REST API

Use the experimental REST API endpoints to quickly experiment and prototype AI features.

The endpoints are:

  • https://gitlab.example.com/api/v4/ai/experimentation/anthropic/complete
  • https://gitlab.example.com/api/v4/ai/experimentation/vertex/chat

These endpoints are only for prototyping, not for rolling features out to customers.

In your local development environment, you can experiment with these endpoints locally with the feature flag enabled:

Feature.enable(:ai_experimentation_api)

On production, the experimental endpoints are only available to GitLab team members. Use a GitLab API token to authenticate.

Abstraction layer

GraphQL API

To connect to the AI provider API using the Abstraction Layer, use an extendable GraphQL API called aiAction. The input accepts key/value pairs, where the key is the action that needs to be performed. We only allow one AI action per mutation request.

Example of a mutation:

mutation {
  aiAction(input: {summarizeComments: {resourceId: "gid://gitlab/Issue/52"}}) {
    clientMutationId
  }
}

As an example, assume we want to build an "explain code" action. To do this, we extend the input with a new key, explainCode. The mutation would look like this:

mutation {
  aiAction(input: {explainCode: {resourceId: "gid://gitlab/MergeRequest/52", code: "foo() { console.log()" }}) {
    clientMutationId
  }
}

The GraphQL API then uses the Anthropic Client to send the response.

How to receive a response

The API requests to AI providers are handled in a background job. We therefore do not keep the request alive and the Frontend needs to match the request to the response from the subscription.

WARNING: Determining the right response to a request can cause problems when only userId and resourceId are used. For example, when two AI features use the same userId and resourceId both subscriptions will receive the response from each other. To prevent this intereference, we introduced the clientSubscriptionId.

To match a response on the aiCompletionResponse subscription, you can provide a clientSubscriptionId to the aiAction mutation.

  • The clientSubscriptionId should be unique per feature and within a page to not interfere with other AI features. We recommend to use a UUID.
  • Only when the clientSubscriptionId is provided as part of the aiAction mutation, it will be used for broadcasting the aiCompletionResponse.
  • If the clientSubscriptionId is not provided, only userId and resourceId are used for the aiCompletionResponse.

As an example mutation for summarizing comments, we provide a randomId as part of the mutation:

mutation {
  aiAction(input: {summarizeComments: {resourceId: "gid://gitlab/Issue/52"}, clientSubscriptionId: "randomId"}) {
    clientMutationId
  }
}

In our component, we then listen on the aiCompletionResponse using the userId, resourceId and clientSubscriptionId ("randomId"):

subscription aiCompletionResponse($userId: UserID, $resourceId: AiModelID, $clientSubscriptionId: String) {
  aiCompletionResponse(userId: $userId, resourceId: $resourceId, clientSubscriptionId: $clientSubscriptionId) {
    content
    errors
  }
}

Note that the subscription for chat behaves differently.

To not have many concurrent subscriptions, you should also only subscribe to the subscription once the mutation is sent by using skip().

Current abstraction layer flow

The following graph uses VertexAI as an example. You can use different providers.

flowchart TD
A[GitLab frontend] -->B[AiAction GraphQL mutation]
B --> C[Llm::ExecuteMethodService]
C --> D[One of services, for example: Llm::GenerateSummaryService]
D -->|scheduled| E[AI worker:Llm::CompletionWorker]
E -->F[::Gitlab::Llm::Completions::Factory]
F -->G[`::Gitlab::Llm::VertexAi::Completions::...` class using `::Gitlab::Llm::Templates::...` class]
G -->|calling| H[Gitlab::Llm::VertexAi::Client]
H --> |response| I[::Gitlab::Llm::GraphqlSubscriptionResponseService]
I --> J[GraphqlTriggers.ai_completion_response]
J --> K[::GitlabSchema.subscriptions.trigger]

CircuitBreaker

The CircuitBreaker concern is a reusable module that you can include in any class that needs to run code with circuit breaker protection. The concern provides a run_with_circuit method that wraps a code block with circuit breaker functionality, which helps prevent cascading failures and improves system resilience. For more information about the circuit breaker pattern, see:

Use CircuitBreaker

To use the CircuitBreaker concern, you need to include it in a class. For example:

class MyService
  include Gitlab::Llm::Concerns::CircuitBreaker

  def call_external_service
    run_with_circuit do
      # Code that interacts with external service goes here

      raise InternalServerError
    end
  end
end

The call_external_service method is an example method that interacts with an external service. By wrapping the code that interacts with the external service with run_with_circuit, the method is executed within the circuit breaker. The circuit breaker is created and configured by the circuit method, which is called automatically when the CircuitBreaker module is included. The method should raise InternalServerError error which will be counted towards the error threshold if raised during the execution of the code block.

The circuit breaker tracks the number of errors and the rate of requests, and opens the circuit if it reaches the configured error threshold or volume threshold. If the circuit is open, subsequent requests fail fast without executing the code block, and the circuit breaker periodically allows a small number of requests through to test the service's availability before closing the circuit again.

Configuration

The circuit breaker is configured with two constants which control the number of errors and requests at which the circuit will open:

  • ERROR_THRESHOLD
  • VOLUME_THRESHOLD

You can adjust these values as needed for the specific service and usage pattern. The InternalServerError is the exception class counted towards the error threshold if raised during the execution of the code block. This is the exception class that triggers the circuit breaker when raised by the code that interacts with the external service.

NOTE: The CircuitBreaker module depends on the Circuitbox gem to provide the circuit breaker implementation. By default, the service name is inferred from the class name where the concern module is included. Override the service_name method if the name needs to be different.

Testing

To test code that uses the CircuitBreaker concern, you can use RSpec shared examples and pass the service and subject variables:

it_behaves_like 'has circuit breaker' do
  let(:service) { dummy_class.new }
  let(:subject) { service.dummy_method }
end

How to implement a new action

Register a new method

Go to the Llm::ExecuteMethodService and add a new method with the new service class you will create.

class ExecuteMethodService < BaseService
  METHODS = {
    # ...
    amazing_new_ai_feature: Llm::AmazingNewAiFeatureService
  }.freeze

Create a Service

  1. Create a new service under ee/app/services/llm/ and inherit it from the BaseService.
  2. The resource is the object we want to act on. It can be any object that includes the Ai::Model concern. For example it could be a Project, MergeRequest, or Issue.
# ee/app/services/llm/amazing_new_ai_feature_service.rb

module Llm
  class AmazingNewAiFeatureService < BaseService
    private

    def perform
      ::Llm::CompletionWorker.perform_async(user.id, resource.id, resource.class.name, :amazing_new_ai_feature)
      success
    end

    def valid?
      super && Ability.allowed?(user, :amazing_new_ai_feature, resource)
    end
  end
end

Authorization

We recommend to use policies to deal with authorization for a feature. Currently we need to make sure to cover the following checks:

  1. General AI feature flag (ai_global_switch) is enabled
  2. Feature specific feature flag is enabled
  3. The namespace has the required license for the feature
  4. User is a member of the group/project
  5. experiment_features_enabled settings are set on the Namespace

For our example, we need to implement the allowed?(:amazing_new_ai_feature) call. As an example, you can look at the Issue Policy for the summarize comments feature. In our example case, we want to implement the feature for Issues as well:

# ee/app/policies/ee/issue_policy.rb

module EE
  module IssuePolicy
    extend ActiveSupport::Concern
    prepended do
      with_scope :subject
      condition(:ai_available) do
        ::Feature.enabled?(:ai_global_switch, type: :ops)
      end

      with_scope :subject
      condition(:amazing_new_ai_feature_enabled) do
        ::Feature.enabled?(:amazing_new_ai_feature, subject_container) &&
          subject_container.licensed_feature_available?(:amazing_new_ai_feature)
      end

      rule do
        ai_available & amazing_new_ai_feature_enabled & is_project_member
      end.enable :amazing_new_ai_feature
    end
  end
end

Pairing requests with responses

Because multiple users' requests can be processed in parallel, when receiving responses, it can be difficult to pair a response with its original request. The requestId field can be used for this purpose, because both the request and response are assured to have the same requestId UUID.

Caching

AI requests and responses can be cached. Cached conversation is being used to display user interaction with AI features. In the current implementation, this cache is not used to skip consecutive calls to the AI service when a user repeats their requests.

query {
  aiMessages {
    nodes {
      id
      requestId
      content
      role
      errors
      timestamp
    }
  }
}

This cache is especially useful for chat functionality. For other services, caching is disabled. (It can be enabled for a service by using cache_response: true option.)

Caching has following limitations:

  • Messages are stored in Redis stream.
  • There is a single stream of messages per user. This means that all services currently share the same cache. If needed, this could be extended to multiple streams per user (after checking with the infrastructure team that Redis can handle the estimated amount of messages).
  • Only the last 50 messages (requests + responses) are kept.
  • Expiration time of the stream is 3 days since adding last message.
  • User can access only their own messages. There is no authorization on the caching level, and any authorization (if accessed by not current user) is expected on the service layer.

Check if feature is allowed for this resource based on namespace settings

There is one setting allowed on root namespace level that restrict the use of AI features:

  • experiment_features_enabled

To check if that feature is allowed for a given namespace, call:

Gitlab::Llm::StageCheck.available?(namespace, :name_of_the_feature)

Add the name of the feature to the Gitlab::Llm::StageCheck class. There are arrays there that differentiate between experimental and beta features.

This way we are ready for the following different cases:

  • If the feature is not in any array, the check will return true. For example, the feature was moved to GA.

To move the feature from the experimental phase to the beta phase, move the name of the feature from the EXPERIMENTAL_FEATURES array to the BETA_FEATURES array.

Implement calls to AI APIs and the prompts

The CompletionWorker will call the Completions::Factory which will initialize the Service and execute the actual call to the API. In our example, we will use VertexAI and implement two new classes:

# /ee/lib/gitlab/llm/vertex_ai/completions/amazing_new_ai_feature.rb

module Gitlab
  module Llm
    module VertexAi
      module Completions
        class AmazingNewAiFeature < Gitlab::Llm::Completions::Base
          def execute
            prompt = ai_prompt_class.new(options[:user_input]).to_prompt

            response = Gitlab::Llm::VertexAi::Client.new(user).text(content: prompt)

            response_modifier = ::Gitlab::Llm::VertexAi::ResponseModifiers::Predictions.new(response)

            ::Gitlab::Llm::GraphqlSubscriptionResponseService.new(
              user, nil, response_modifier, options: response_options
            ).execute
          end
        end
      end
    end
  end
end
# /ee/lib/gitlab/llm/vertex_ai/templates/amazing_new_ai_feature.rb

module Gitlab
  module Llm
    module VertexAi
      module Templates
        class AmazingNewAiFeature
          def initialize(user_input)
            @user_input = user_input
          end

          def to_prompt
            <<-PROMPT
            You are an assistant that writes code for the following context:

            context: #{user_input}
            PROMPT
          end
        end
      end
    end
  end
end

Because we support multiple AI providers, you may also use those providers for the same example:

Gitlab::Llm::VertexAi::Client.new(user)
Gitlab::Llm::Anthropic::Client.new(user)

Monitoring Ai Actions

  • Error ratio and response latency apdex for each Ai action can be found on Sidekiq Service dashboard under SLI Detail: llm_completion.
  • Spent tokens, usage of each Ai feature and other statistics can be found on periscope dashboard.

Add Ai Action to GraphQL

TODO

Security

Refer to the secure coding guidelines for Artificial Intelligence (AI) features.