- Set up GitLab Duo Chat
- Working with GitLab Duo Chat
- Contributing to GitLab Duo Chat
- Testing GitLab Duo Chat with predefined questions
- GraphQL Subscription
- Enable Anthropic API features.
- Enable OpenAI support.
- Ensure the embedding database is configured.
Enable feature specific feature flag.
Feature.enable(:gitlab_duo) Feature.enable(:tanuki_bot) Feature.enable(:ai_redis_cache)
- Ensure that your current branch is up-to-date with
- To access the GitLab Duo Chat interface, in the lower-left corner of any page, select Help and Ask GitLab Duo Chat.
- 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 killand then
- 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.
diff --git a/ee/app/services/llm/chat_service.rb b/ee/app/services/llm/chat_service.rb index 5fa7ae8a2bc1..5fe996ba0345 100644 --- a/ee/app/services/llm/chat_service.rb +++ b/ee/app/services/llm/chat_service.rb @@ -5,7 +5,7 @@ class ChatService < BaseService private def perform - worker_perform(user, resource, :chat, options) + worker_perform(user, resource, :chat, options.merge(sync: true)) end def valid?
Prompts are the most vital part of GitLab Duo Chat system. Prompts are the instructions sent to the Large Language Model to perform certain tasks.
The state of the prompts is the result of weeks of iteration. If you want to change any prompt in the current tool, you must put it behind a feature flag.
If you have any new or updated prompts, ask members of AI Framework team to review, because they have significant experience with them.
The Chat feature uses a zero-shot agent that includes a system prompt explaining how the large language model should interpret the question and provide an answer. The system prompt defines available tools that can be used to gather information to answer the user’s question.
The zero-shot agent receives the user’s question and decides which tools to use to gather information to answer it. It then makes a request to the large language model, which decides if it can answer directly or if it needs to use one of the defined tools.
The tools each have their own prompt that provides instructions to the large language model on how to use that tool to gather information. The tools are designed to be self-sufficient and avoid multiple requests back and forth to the large language model.
After the tools have gathered the required information, it is returned to the zero-shot agent, which asks the large language model if enough information has been gathered to provide the final answer to the user’s question.
To add a new tool:
Create files for the tool in the
ee/lib/gitlab/llm/chain/tools/folder. Use existing tools like
resource_readeras a template.
Write a class for the tool that includes:
- Name and description of what the tool does
- Example questions that would use this tool
- Instructions for the large language model on how to use the tool to gather information - so the main prompts that this tool is using.
- Test and iterate on the prompt using RSpec tests that make real requests to the large language model.
Implement code in the tool to parse the response from the large language model and return it to the zero-shot agent.
Add the new tool name to the
ee/lib/gitlab/llm/completions/chat.rbso the zero-shot agent knows about it.
- Add tests by adding questions to the test-suite for which the new tool should respond to. Iterate on the prompts as needed.
The key things to keep in mind are properly instructing the large language model through prompts and tool descriptions, keeping tools self-sufficient, and returning responses to the zero-shot agent. With some trial and error on prompts, adding new tools can expand the capabilities of the Chat feature.
There are available short videos covering this topic.
To gather more insights about the full request, use the
Gitlab::Llm::Logger file to debug logs.
The default logging level on production is
INFO and must not be used to log any data that could contain personal identifying information.
To follow the debugging messages related to the AI requests on the abstraction layer, you can use:
export LLM_DEBUG=1 gdk start tail -f log/llm.log
Because success of answers to user questions in GitLab Duo Chat heavily depends on toolchain and prompts of each tool, it’s common that even a minor change in a prompt or a tool impacts processing of some questions. To make sure that a change in the toolchain doesn’t break existing functionality, you can use the following rspecs to validate answers to some predefined questions:
export OPENAI_API_KEY='<key>' export ANTHROPIC_API_KEY='<key>' REAL_AI_REQUEST=1 rspec ee/spec/lib/gitlab/llm/chain/agents/zero_shot/executor_spec.rb
When you need to update the test questions that require documentation embeddings, make sure a new fixture is generated and committed together with the change.
The GraphQL Subscription for Chat behaves slightly different because it’s user-centric. A user could have Chat open on multiple browser tabs, or also on their IDE.
We therefore need to broadcast messages to multiple clients to keep them in sync. The
aiAction mutation with the
chat action behaves the following:
- All complete Chat messages (including messages from the user) are broadcasted with the
resourceIdfrom the mutation as identifier, ignoring the
- Chunks from streamed Chat messages are broadcasted with the
To truly sync messages between all clients of a user, we need to remove the
resourceId as well, which will be fixed by this issue.