Qodo Context Engine
This feature is available for Enterprise users only.
What is Qodo Context Engine?
Qodo Context Engine is the code intelligence engine behind the Qodo platform. It connects to all your repos, analyzes architecture and patterns, and powers AI agents that help you search, understand, and solve technical problems.
Think of it as an AI-powered Principal Engineer, that understands your entire system and helps you move faster with confidence.
Why should I use it?
When used with Qodo Git interface, Qodo Context Engine brings deep, architecture-level understanding directly into your review workflow.
You ask the questions, and Qodo Context Engine finds the answers from across your entire codebase.
How does it work?
Qodo Context Engine uses Retrieval-Augmented Generation (RAG) and agentic reasoning to understand your codebase:
Indexing – Builds a deep internal map of your code
Retrieval – Pulls relevant code, docs, and patterns
Reasoning – AI agents analyze dependencies and logic
Generation – Produces grounded, accurate responses
Using Qodo Context Engine
In order to enable the RAG feature, add the following lines to your configuration file:
[rag_arguments]
enable_rag=trueThe /ask tool can access broader repository context through the RAG feature when answering questions that go beyond the PR scope alone.
The References section displays the additional repository content consulted to formulate the answer.
The /compliance tool offers the Codebase Code Duplication Compliance section which contains feedback based on the RAG references. This section highlights possible code duplication issues in the PR, providing developers with insights into potential code quality concerns.
The /implement tool utilizes the RAG feature to provide comprehensive context of the repository codebase, allowing it to generate more refined code output.
The References section contains links to the content used to support the code generation.
The /review tool offers the Focus area which contains feedback based on the RAG output.
The complete list of references found relevant to the PR will be shown in the References section, helping developers understand the broader context by exploring the provided references.
Configuration options
enable_rag
false
If set to true, repository enrichment using RAG will be enabled.
rag_repo_list
The repository from which the PR was opened.
A list of repositories that will be used by the semantic search for RAG.
Use ['all'] to consider the entire codebase, or a select list of repositories.
For example: ['my-org/my-repo', ...].
Last updated