Learn how to configure your R2R deployment
R2R offers a flexible configuration system that allows you to customize your Retrieval-Augmented Generation (RAG) applications. This guide introduces the key concepts and methods for configuring R2R.
R2R supports two main levels of configuration:
The default settings for a light
R2R installation are specified in the r2r.toml
file.
When doing a full
installation the R2R CLI uses the full.toml
to override some of the default light default settings with those of the added providers.
To create your own custom configuration:
my_r2r.toml
in your project directory.R2R will use your specified settings, falling back to defaults for any unspecified options.
When calling endpoints, you can override server configurations on-the-fly. This allows for dynamic control over search settings, model selection, prompt customization, and more.
For example, using the Python SDK:
For more detailed information on configuring specific components of R2R, please refer to the following pages:
Learn how to configure your R2R deployment
R2R offers a flexible configuration system that allows you to customize your Retrieval-Augmented Generation (RAG) applications. This guide introduces the key concepts and methods for configuring R2R.
R2R supports two main levels of configuration:
The default settings for a light
R2R installation are specified in the r2r.toml
file.
When doing a full
installation the R2R CLI uses the full.toml
to override some of the default light default settings with those of the added providers.
To create your own custom configuration:
my_r2r.toml
in your project directory.R2R will use your specified settings, falling back to defaults for any unspecified options.
When calling endpoints, you can override server configurations on-the-fly. This allows for dynamic control over search settings, model selection, prompt customization, and more.
For example, using the Python SDK:
For more detailed information on configuring specific components of R2R, please refer to the following pages: