yera.setup.provider_setup.llama_cpp
Obtain and validate llama.cpp provider configuration.
Symbols
LlamaCppProviderSetup
ProviderSetup[LlamaCppConnection]Provide presentation-independent llama.cpp setup operations.
Automatic discovery does not infer model directories from environment variables or conventional application caches. Validation reports inaccessible explicitly configured paths as recoverable warnings because removable or network storage may become available later.
Attributes
Configuration key for the llama.cpp provider.
Python import paths required by the integration.
Methods
LlamaCppProviderSetup.get_config
get_config() → SetupResult[tuple[LlamaCppConnection, ...]]Return no implicit llama.cpp connection candidates.
Model directories require explicit user selection because installation of the llama.cpp integration does not grant permission to inspect local model caches.
Returns
A valid result containing no automatically discovered connections.
LlamaCppProviderSetup.validate
validate(
config: LlamaCppConnection,
secret_store: SecretStore | None = None,
) → SetupResult[LlamaCppConnection]Validate configured llama.cpp model directories.
Missing directories are recoverable because external or removable storage may be mounted after setup.
Parameters
llama.cpp connection containing model directory paths.
Unused credential-store override accepted through the common provider validation interface.
Returns
The supplied configuration and warnings for empty or currently inaccessible directory configuration.